WO2022057890A1 - 口腔检测方法、口腔检测装置以及计算机可读存储介质 - Google Patents

口腔检测方法、口腔检测装置以及计算机可读存储介质 Download PDF

Info

Publication number
WO2022057890A1
WO2022057890A1 PCT/CN2021/119036 CN2021119036W WO2022057890A1 WO 2022057890 A1 WO2022057890 A1 WO 2022057890A1 CN 2021119036 W CN2021119036 W CN 2021119036W WO 2022057890 A1 WO2022057890 A1 WO 2022057890A1
Authority
WO
WIPO (PCT)
Prior art keywords
threshold
picture
intermediate picture
comparison
comparison threshold
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2021/119036
Other languages
English (en)
French (fr)
Inventor
刘凤兴
严二平
武庆斌
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Johnson and Johnson China Ltd
Original Assignee
Johnson and Johnson China Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Johnson and Johnson China Ltd filed Critical Johnson and Johnson China Ltd
Priority to EP21868712.7A priority Critical patent/EP4216151A4/en
Priority to US18/026,982 priority patent/US12511751B2/en
Publication of WO2022057890A1 publication Critical patent/WO2022057890A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G06T7/0014—Biomedical image inspection using an image reference approach
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0012—Biomedical image inspection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N9/00—Details of colour television systems
    • H04N9/64—Circuits for processing colour signals
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/24—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor for the mouth, i.e. stomatoscopes, e.g. with tongue depressors; Instruments for opening or keeping open the mouth
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20004—Adaptive image processing
    • G06T2207/20012—Locally adaptive
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20024—Filtering details
    • G06T2207/20032—Median filtering
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30004—Biomedical image processing
    • G06T2207/30036—Dental; Teeth
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment

Definitions

  • the present disclosure relates to the field of oral cavity detection, and more particularly, to an oral cavity detection method, an oral cavity detection device, and a computer-readable storage medium for executing the above-mentioned oral cavity detection method.
  • US2019/0167115 A1 discloses a system for processing an image of an oral cavity, the system for processing an image of the oral cavity comprising: an image capture device; configured to attach to an image capture device and mount the image capture device relative to a user's mouth An oral accessory in a fixed position; a display and a processing unit, wherein the processing unit is configured to: receive oral image data from an image capture device; and identify in the image data an analysis area corresponding to the teeth and gums; from the analysis of the image data extracting a set of image attribute features from the region; passing the image attribute features through a conditional classifier configured to compare the values of the extracted image attribute features with preset parameters to identify areas of analysis indicative of oral health sub-region; and send result data corresponding to the identified sub-region to the display.
  • the existing oral image processing system does not perform targeted detection that conforms to its own characteristics for different subjects.
  • a first aspect of the present disclosure proposes an oral detection method.
  • the oral detection method includes:
  • the ratio of the pixels located within the comparison threshold to the pixels of the second intermediate picture is determined.
  • different comparison thresholds can be set according to the subject's own tooth color, so that the targeted detection that conforms to its own characteristics can be carried out for different subjects, so that based on the first The second intermediate picture and the ratio of the pixels within the comparison threshold determined by the comparison threshold to the pixels in the second intermediate picture. It is more accurate and effective than the ratio determined by traditional methods, which is conducive to subsequent oral health assessment.
  • the first intermediate picture includes an area of teeth in the picture and the comparison threshold includes a calculus comparison threshold, and wherein based on the second intermediate picture and the Determining the ratio of the pixels within the comparison threshold to the pixels in the second intermediate picture by comparing the threshold further includes:
  • the ratio of the pixel points located within the dental calculus comparison threshold to the pixel points of the second intermediate picture is determined.
  • the first intermediate picture includes a gingival area in the picture and the comparison threshold includes a gingivitis comparison threshold, and wherein based on the second intermediate picture and the Determining the ratio of the pixels within the comparison threshold to the pixels in the second intermediate picture by comparing the threshold further includes:
  • the proportion of the pixels located within the gingivitis comparison threshold to the pixels of the second intermediate picture is determined.
  • the oral cavity detection method further comprises: adjusting the contrast of the oral cavity picture.
  • the tooth color is determined by:
  • the tooth color is determined based on the comparison results.
  • the standard color includes the following six standard color values:
  • RGBColor0 sRGBColor(255,255,255);
  • RGBColor1 sRGBColor(164,192,239)
  • RGBColor2 sRGBColor(131,172,217);
  • RGBColor3 sRGBColor(124,149,205);
  • RGBColor4 sRGBColor(21, 46, 110);
  • RGBColor5 sRGBColor(255, 255, 0).
  • determining the tooth color according to the comparison result further comprises:
  • the tooth color is determined from a weighted summation of the weights of each standard color value.
  • the dental calculus comparison threshold includes at least two sets of threshold intervals including a high threshold and a low threshold, or the gingivitis comparison threshold includes at least two sets of a high threshold and a low threshold, respectively The threshold interval for the threshold.
  • the low threshold is lower than the high threshold
  • the low threshold and the high threshold of the gingivitis comparison threshold are selected from the following interval: np.array([ 0,80,12]) to np.array([40,235,210]), or the low threshold and the high threshold of the calculus comparison threshold are selected from the following interval: np.array([0,30,10] ) to np.array([190,255,70]).
  • a second aspect of the present disclosure provides an oral detection device, the oral detection device comprising:
  • a camera device configured to obtain a picture of the oral cavity
  • a picture processing device configured to perform median filtering, grayscale conversion and adaptive threshold segmentation operations on the picture to obtain a first intermediate picture and convert the first intermediate picture from the RGB color space to HSV color space to get the second intermediate picture;
  • a threshold determination device configured to determine a comparison threshold based on tooth color
  • a pixel ratio determination device configured to determine the ratio of the pixel points located within the comparison threshold to the pixel points of the second intermediate picture based on the second intermediate picture and the comparison threshold.
  • the first intermediate picture includes an area of teeth in the picture and the comparison threshold includes a calculus comparison threshold, and wherein based on the second intermediate picture and the Determining the ratio of the pixels within the comparison threshold to the pixels in the second intermediate picture by comparing the threshold further includes:
  • the ratio of the pixel points located within the dental calculus comparison threshold to the pixel points of the second intermediate picture is determined.
  • the first intermediate picture includes a gingival area in the picture and the comparison threshold includes a gingivitis comparison threshold, and wherein based on the second intermediate picture and the Determining the ratio of the pixels within the comparison threshold to the pixels in the second intermediate picture by comparing the threshold further includes:
  • the proportion of the pixels located within the gingivitis comparison threshold to the pixels of the second intermediate picture is determined.
  • the image processing device is configured to adjust the contrast of the oral cavity image.
  • the tooth color is determined by:
  • the tooth color is determined based on the comparison results.
  • the standard color includes the following six standard color values:
  • RGBColor0 sRGBColor(255,255,255);
  • RGBColor1 sRGBColor(164,192,239)
  • RGBColor2 sRGBColor(131,172,217);
  • RGBColor3 sRGBColor(124,149,205);
  • RGBColor4 sRGBColor(21, 46, 110);
  • RGBColor5 sRGBColor(255, 255, 0).
  • determining the tooth color according to the comparison further comprises:
  • the tooth color is determined from a weighted summation of the weights of each standard color value.
  • the dental calculus comparison threshold includes at least two sets of threshold intervals including a high threshold and a low threshold, or the gingivitis comparison threshold includes at least two sets of a high threshold and a low threshold, respectively The threshold interval for the threshold.
  • the low threshold is lower than the high threshold
  • the low threshold and the high threshold of the gingivitis comparison threshold are selected from the following interval: np.array([ 0,80,12]) to np.array([40,235,210]), or the low threshold and the high threshold of the calculus comparison threshold are selected from the following interval: np.array([0,30,10] ) to np.array([190,255,70]).
  • a third aspect of the present disclosure proposes a tangible computer-readable storage medium comprising instructions for performing an oral detection method, which, when executed, cause processing of the computer to be performed. at least for:
  • the ratio of the pixels located within the comparison threshold to the pixels of the second intermediate picture is determined.
  • the first intermediate picture includes an area of teeth in the picture and the comparison threshold includes a calculus comparison threshold, and wherein based on the second intermediate picture and the Determining the ratio of the pixels within the comparison threshold to the pixels in the second intermediate picture by comparing the threshold further includes:
  • the ratio of the pixel points located within the dental calculus comparison threshold to the pixel points of the second intermediate picture is determined.
  • the first intermediate picture includes a gingival area in the picture and the comparison threshold includes a gingivitis comparison threshold, and wherein based on the second intermediate picture and the Determining the ratio of the pixels within the comparison threshold to the pixels in the second intermediate picture by comparing the threshold further includes:
  • the proportion of the pixels located within the gingivitis comparison threshold to the pixels of the second intermediate picture is determined.
  • the processor of the computer when the instructions are executed, the processor of the computer is further caused to at least adjust the contrast of the oral cavity picture.
  • the tooth color is determined by:
  • the tooth color is determined based on the comparison results.
  • the standard color includes the following six standard color values:
  • RGBColor0 sRGBColor(255,255,255);
  • RGBColor1 sRGBColor(164,192,239)
  • RGBColor2 sRGBColor(131,172,217);
  • RGBColor3 sRGBColor(124,149,205);
  • RGBColor4 sRGBColor(21, 46, 110);
  • RGBColor5 sRGBColor(255, 255, 0).
  • determining the tooth color according to the comparison result further comprises:
  • the tooth color is determined from a weighted summation of the weights of each standard color value.
  • the dental calculus comparison threshold includes at least two sets of threshold intervals including a high threshold and a low threshold, or the gingivitis comparison threshold includes at least two sets of a high threshold and a low threshold, respectively The threshold interval for the threshold.
  • the low threshold is lower than the high threshold
  • the low threshold and the high threshold of the gingivitis comparison threshold are selected from the following interval: np.array([ 0,80,12]) to np.array([40,235,210]), or the low threshold and the high threshold of the calculus comparison threshold are selected from the following interval: np.array([0,30,10] ) to np.array([190,255,70]).
  • the oral detection method, the oral detection device and the corresponding computer-readable storage medium provided according to the three aspects of the present disclosure will set different comparison thresholds according to the subject's own tooth color, thereby Targeted detection that conforms to its own characteristics can be carried out for different subjects, so that the pixels determined based on the second intermediate picture and the comparison threshold and located within the comparison threshold account for the second intermediate picture.
  • the ratio of the pixel points is more accurate and effective than the ratio determined by the traditional method, which is beneficial to the subsequent oral health assessment.
  • FIG. 1 shows a flowchart of an oral detection method 100 according to an embodiment of the present disclosure
  • FIG. 2 shows a flowchart of an oral detection method 200 according to another embodiment of the present disclosure
  • FIG. 3 shows a schematic block diagram of an oral detection device 300 according to one embodiment of the present disclosure.
  • FIG. 4 shows a schematic block diagram of an oral detection device 400 according to another embodiment of the present disclosure.
  • median filtering in the present disclosure basically refers to a nonlinear signal processing technique based on sorting statistics theory that can effectively suppress noise.
  • the basic principle of median filtering is to convert a point in a digital image or a digital sequence The value is replaced by the median value of each point value in a neighborhood of the point, so that the surrounding pixel values are close to the true value, thereby eliminating isolated noise points.
  • the pixel points refer to the points that constitute the image in a unit area, and each pixel point may have a different color value. The more pixels per unit area and the higher the resolution, the better the image will look.
  • adaptive threshold segmentation in this disclosure basically refers to an image processing technique.
  • the purpose of image area segmentation is to divide the area of an object from the image, that is, to find those pixel sets corresponding to the object or the surface of the object, which appear as two-dimensional lumps, which is one of the basic shape characteristics of the area. .
  • the pictures that appear in the present disclosure include, but are not limited to, image data obtained after one or more operations of cropping, adjusting contrast, median filtering, adaptive threshold segmentation, etc. on the original picture, which can both For example, it is a JPEG picture in the traditional sense, and it can also be a picture in other formats, or it can be other types of image-processed pixels, as long as it can meet the technical solutions proposed in the present disclosure. purpose.
  • first intermediate picture in the present disclosure basically refers to an intermediate picture obtained after performing median filtering, grayscale transformation and adaptive threshold segmentation on the oral picture, and the intermediate picture will include gums and teeth in the detection area.
  • color space in this disclosure basically refers to a color model (also known as a color space or color system) whose purpose is to describe colors in a generally acceptable manner under certain standards.
  • RGB color space basically refers to the color space based on the three basic colors of R (Red), G (Green), and B (Blue). A wide range of colors, so commonly known as three primary color mode.
  • HSV color space basically refers to the color space proposed for better digital processing of colors.
  • HSX color spaces where X may be V or I, and X has different meanings depending on the specific use. H is hue, S is saturation, V is lightness, and I is intensity.
  • LAB color space basically means that it consists of three elements, one element is luminance (L), A and B are two color channels. a includes colors from dark green (low lightness value) to gray (medium lightness value) to bright pink (high lightness value); b is from light blue (low lightness value) to gray (medium lightness value) and then to yellow (high brightness value). Therefore, this color mixing will result in a color with a bright effect.
  • second intermediate picture in the present disclosure basically refers to an intermediate picture obtained by converting the first intermediate picture from the RGB color space to the HSV color space.
  • third intermediate picture in the present disclosure basically refers to an intermediate picture obtained by converting the first intermediate picture from the RGB color space to the LAB color space.
  • RGBColor0 sRGBColor(255,255,255)
  • RGBColor1 sRGBColor(164,192,239)
  • RGBColor2 sRGBColor(131,172,217)
  • RGBColor3 sRGBColor(124,149,205)
  • RGBColor4 sRGBColor(21,46,110)
  • RGBColor5 sRGBColor(255,
  • the term "comparison threshold” in this disclosure basically means to include at least two sets of threshold intervals including a high threshold and a low threshold, respectively, wherein the low threshold is lower than the high threshold and the low threshold and the low threshold
  • the upper threshold is selected from the following intervals: np.array([0,80,12]) to np.array([40,235,210]) or np.array([0,30,10]) to np.array([190,255,70] ]), specifically, the low threshold and the high threshold of the gingivitis comparison threshold are selected from the following interval: np.array([0,80,12]) to np.array([40,235,210]), Alternatively, the low threshold and the high threshold of the calculus comparison threshold are selected from the following interval: np.array([0,30,10]) to np.array([190,255,70]).
  • the applicant of the present disclosure would like to first introduce the hardware selection design of the oral detection device disclosed in the present disclosure, but the following description is only exemplary, not limiting As long as the intended design purpose can be achieved, other options are also feasible, that is to say, other options will also fall within the scope of protection required by the claims of the present disclosure.
  • the camera module uses, for example, an 8MP high-definition autofocus module, the model is KS8A17, the module size is 38mm x 38mm, the operating temperature is -20°C to 70°C, and the imaging distance is 3 cm to infinity. This module can shoot 3264 x 2448 resolution photos with excellent low-light responsiveness and high-speed transfer to the controller for processing.
  • the UV light module can be, for example, a UV lamp structure.
  • the UV lamp has a simple shape, including UV lamp electrodes, built-in UV lamp beads (for example, the central wavelength is 365 nm), a cone-shaped structure (which can realize the function of concentrating light), and a UV filter ( Interfering light can be filtered out, leaving only UV light to pass).
  • the module After the module is powered, it can be used as a UV light source in the process of oral image acquisition.
  • the UV lamp part can be composed of, for example, two UV lamps, which are located on the left and right sides of the camera respectively, and the distance from the camera is between 1 and 3 centimeters.
  • the non-ultraviolet light module can be, for example, a white light LED lamp structure, using a 3mm LED white light emitting diode.
  • the LED light part consists of, for example, 4 LED white lights, which are located at the four top corners of the oral detector, and are arranged in a rectangular shape around the camera, and the distance from the camera is between 1 and 5 cm. .
  • the power supply module used can be a UV lamp power supply module, which can supply power to two UV lamps respectively through two AA batteries with a voltage of 1.5V, and connect the battery and the UV lamp through a relay to realize control.
  • the power module can also include a module for powering the controller, which can be used as the power supply of the whole machine through a 5V1500mAh lithium battery, and the structure except the UV lamp is powered by this.
  • RGBColor0 sRGBColor(255,255,255)
  • RGBColor1 sRGBColor(164,192,239)
  • RGBColor2 sRGBColor(131,172,217)
  • RGBColor3 sRGBColor(124,149,205)
  • RGBColor4 sRGBColor(21,46,110)
  • RGBColor5 sRGBColor(255,255,0)
  • different colors have different weights in the score, and the weighted summation can finally get the subject's tooth color score.
  • a positive white light photo has 10,000 pixels, and then compare the pixel values of the 10,000 pixels with the above six standard colors, that is, classify the 10,000 pixels according to which standard color is close to, and count the The number of pixels that are close to each standard color, and then the weighted average can finally get the subject's tooth color score.
  • the tooth color does not have to be determined by the above method, but can also be determined qualitatively, for example, the tooth color is first divided into different grades (such as black, very yellow , yellow, white, very white, etc.), each level corresponds to a comparison threshold.
  • the determination of the comparison threshold can then also be carried out correspondingly according to the subject's selection, for example by a qualitative evaluation of the subject's own selection of the colour of his teeth.
  • FIG. 1 shows a flowchart of an oral detection method 100 according to an embodiment of the present disclosure.
  • the tooth color in the oral cavity detection method 100 is determined by the following methods: first, in method step 111, a picture of the oral cavity is obtained; then, in method step 112, in the execution of the picture The first intermediate picture is obtained by value filtering, grayscale conversion and adaptive threshold segmentation operations; then, in method step 113, the first intermediate picture is converted from the RGB color space to the LAB color space to obtain the third intermediate picture; Then, in method step 114, the pixels in the third intermediate picture are compared with the standard color; and finally, in method step 115, the tooth color is determined according to the comparison result.
  • determining the tooth color according to the comparison result further comprises: determining the tooth color according to a weighted summation of the weights of each standard color value.
  • a median filtering operation will be performed on the non-ultraviolet light image to eliminate noise points. For example, if a 3*3 pixel matrix is taken in the image, That is, there are 9 pixels in the pixel matrix, sort the 9 pixels, and finally assign the center point of the matrix as the median of the nine pixels. This operation is called a median filtering operation. Then convert it into a grayscale image.
  • the specific conversion method is to do this operation r*0.2126+g*0.7152+b*0.0722 for each pixel in the three-channel image of the three-color RGB, three-channel image, A grayscale image can be obtained by superimposing proportionally.
  • adaptive threshold adjustment and area segmentation are performed to segment the area of interest. Specifically, the actual value of each pixel is distributed between [0, 255] on the basis of the grayscale image, and then it needs to be further refined. Divide which pixels are the foreground and those pixels are the background.
  • the adaptation is to traverse 0 to 255 to determine whether a pixel value is a foreground pixel or a background pixel, and let the foreground pixel class and the background The correlation coefficient of the class of pixel-like points is maximized, so as to obtain an adaptive threshold, and then use the adaptive threshold to distinguish the pixels of the foreground and the background and perform a region segmentation operation, so as to obtain the region of interest, which is only the tooth region and the gingival area.
  • determining the first region including the tooth region and the gum region based on the non-ultraviolet light picture can further include adjusting the contrast of the non-ultraviolet light picture to enhance the contrast.
  • the pixels are superimposed proportionally to form a new image, and the difference between the front and back pixel values of the new image will become larger, that is, the image contrast will be enhanced, which is beneficial to the subsequent adaptive threshold segmentation operation.
  • the color of the subject's teeth can be determined, and then targeted oral examination can be performed for each subject according to the difference in the color of the teeth.
  • the color of the subject's teeth is not necessarily determined every time the oral cavity is detected, and the subject's own tooth color can also be input into a related device or instrument, for example.
  • the non-ultraviolet oral images here do not necessarily need to be captured by the camera in real time, and can also be downloaded from a network location via a communication interface, or extracted from other images, or preprocessed.
  • FIG. 2 shows a flowchart of an oral cavity detection method 200 according to an embodiment of the present disclosure.
  • the oral cavity shown in FIG. The detection method 200 includes at least the following steps: first, in the method step 220, a picture of the oral cavity is obtained, and the picture of the oral cavity obtained here can be the picture of the oral cavity used to determine the color of the teeth previously, or it can be other oral pictures, and Similar to before, the non-ultraviolet oral images here do not necessarily have to be captured by the camera in real time, but can also be downloaded from a network location via a communication interface, extracted from other images, or obtained through preprocessing. Oral pictures.
  • method step 230 perform median filtering, grayscale conversion and adaptive threshold segmentation operations on the picture to obtain a first intermediate picture; next, in method step 240, the first intermediate picture is The image is converted from the RGB color space to the HSV color space to obtain a second intermediate image; then, in method step 250, a comparison threshold is determined based on the tooth color; and finally in method step 260, based on the second intermediate image and the comparison threshold to determine the ratio of the pixels located within the comparison threshold to the pixels of the second intermediate picture.
  • the comparison threshold can be determined according to the tooth color of the subject, and then the oral cavity can be determined. Image acquisition and processing.
  • the operations of median filtering, grayscale conversion and adaptive threshold segmentation performed here are similar to those previously used in determining tooth color, and to save space, they will not be repeated here.
  • the oral detection method can be used, for example, to determine the assessment of the gingival condition of a subject, and at this time, the oral detection method is used for gingivitis detection and scoring.
  • the contrast of the picture is optionally adjusted first, and then the median filtering, grayscale conversion and adaptive threshold segmentation operations are performed successively.
  • the tooth area is removed to obtain the detection image; it is also necessary to convert the detection image from the original RGB color space to the HSV color space, and then adjust the Threshold constraint, the pixels within the threshold can be determined as the gingival infection area, and finally the final score is obtained by the ratio of the pixels in the infected area to the number of pixels in the entire area.
  • the first intermediate picture in the oral cavity detection method 200 at this time includes the gingival area in the picture and the comparison threshold includes a gingivitis comparison threshold, and wherein method step 260 is based on the first intermediate picture.
  • Determining the ratio of the pixels located within the comparison threshold to the pixel points of the second intermediate picture in the second intermediate picture and the comparison threshold further includes: determining, based on the second intermediate picture and the gingivitis comparison threshold, located within the comparison threshold. The ratio of the pixels within the gingivitis comparison threshold to the pixels of the second intermediate picture.
  • the comparison threshold includes at least two sets of threshold intervals including a high threshold and a low threshold, respectively.
  • the low-order threshold is lower than the high-order threshold and the low-order threshold and the high-order threshold are selected from the interval: np.array([0,80,12]) to np.array([40, 235, 210]).
  • each interval there are respectively three intervals, in each interval the lower threshold is lower than the upper threshold and the lower threshold and the upper threshold are selected from the following intervals: np.array([0,80,12]) to np .array([40,235,210]) or np.array([0,30,10]) to np.array([190,255,70]), where np.array([0,80,12]) to np.array
  • the interval ([40,235,210]) is mainly used for the selection of gingivitis comparison threshold, while the interval from np.array([0,30,10]) to np.array([190,255,70]) is mainly used for dental calculus Choice of comparison thresholds.
  • the low threshold is np.array([0,170,60]) and the high threshold is np.array([10,215,70]); or the low threshold is np.array([0,170,35]) and the high threshold is np.array([10,225,50]); or the low threshold is np.array([20,130,130]) and the high threshold is np.array([26,200,200]).
  • a comparison threshold with a low threshold of np.array([20, 130, 130]) and a high threshold of np.array([26, 200, 200]) ;
  • the previous tooth color score is above 60 and below 80
  • select the low threshold as np.array([0,170,35]) and the high threshold as np.array([10,225, 50]);
  • the subject's teeth are very white, such as the previous tooth color score is above 80
  • the low threshold is np.array([0,170,60]) and the high threshold is np.array ([10, 215, 70]) comparison threshold.
  • the selection of the high threshold value and the low threshold value is only exemplary, but not restrictive, and those skilled in the art can also select other values within the above range.
  • the comparison threshold when each subject performs oral detection, the comparison threshold will be dynamically selected or set according to the subject's tooth color, and then the pixels above the low threshold and below the high threshold are set to 0, The pixels in between are the suspected gingivitis areas. The gingivitis pixels are counted, and the ratio is calculated with the total number of pixels in the detection area. The final gingivitis detection score is 10-99.9*10*ratio.
  • the oral cavity detection method can also be used, for example, to determine the evaluation of the subject's dental calculus, and in this case, the oral cavity detection method is used to detect the subject's dental calculus condition.
  • the first intermediate picture includes areas of teeth in the picture and the comparison threshold includes a calculus comparison threshold, and wherein method step 260 is based on the second intermediate picture and the comparison threshold Determining the ratio of the pixels located within the comparison threshold to the pixels of the second intermediate picture further includes: determining the pixels located within the calculus comparison threshold based on the second intermediate picture and the calculus comparison threshold The ratio of the dots to the pixel dots of the second intermediate picture.
  • the oral cavity detection method will optionally adjust the contrast of the oral cavity, such as a positive white light picture, and perform median filtering; then convert the grayscale image and perform adaptation such as detection area clipping. Threshold segmentation, get the detected part of the picture, and then convert it from the RGB color space to the HSV color space; then set the threshold, remove the non-detected part, get the pixels of the dental calculus, use these detected pixels and the total detection area pixels The ratio of the points to get the calculus detection score.
  • a picture of the oral cavity such as a positive white light picture, and then preferably adjust the contrast of the picture.
  • the threshold of suspected dental calculus converts the original RGB color space image to HSV color space image, set the threshold of suspected dental calculus, respectively set the low threshold to such as np.array([18,90,22]), and set the high threshold to such as np .array([30,225,60]), then set the pixels above the low threshold and below the high threshold to 0, and the pixels in between are the suspected calculus areas, count the calculus pixels, and then compare with The total number of pixels in the detection area is used to calculate the ratio, and the final calculus detection score is 10-99.9*10*ratio.
  • the selection of the low threshold value and the high threshold value is only exemplary and not restrictive, and those skilled in the art can certainly select other threshold values according to the color of the subject's teeth.
  • the calculus comparison threshold can be determined based on tooth color. For example, when the subject's teeth are yellow, such as the previous tooth color score is below 60, select the low threshold as np.array([150,50,18]) and the high threshold as np.array([180,130, 30]); when the subject's teeth are whiter, for example, the previous tooth color score is above 60 points and below 80 points, select the low threshold as np.array([2, 240, 10]) and the high threshold as np .array([20,255,25]) comparison threshold; and when the subject's teeth are very white, such as the previous tooth color score above 80 points, the lower threshold is selected as np.array([18,90,22] ) and the comparison threshold with the upper threshold as np.array([30, 225, 60]).
  • the gingivitis comparison threshold and the calculus comparison threshold can also be dynamically determined by, for example, the color of the gums during specific implementation.
  • the detection of one or several dimensions can be superimposed.
  • the results of tooth or gum color can be used as the basic parameters of other detection dimensions to obtain an adaptive algorithm based on tooth color, so that other The detection of dimensions such as dental calculus is more accurate.
  • the oral detection method according to the present disclosure will set different comparison thresholds according to the subject's own tooth color or gingival color, so as to carry out a targeted measurement that conforms to its own characteristics for different subjects. detection, so that the ratio of the pixels located within the comparison threshold to the pixels of the second intermediate picture determined based on the second intermediate picture and the comparison threshold is more accurate and effective than the ratio determined by the traditional method, This facilitates subsequent oral health assessments.
  • FIG. 3 shows an oral cavity detection device 300 proposed according to the present disclosure.
  • the oral cavity detection device 300 includes: a camera device 310, and the camera device 310 is configured to acquire pictures of the oral cavity; the picture processing device 320, the The picture processing device 320 is configured to perform median filtering, grayscale conversion and adaptive threshold segmentation operations on the picture to obtain a first intermediate picture and convert the first intermediate picture from the RGB color space to the HSV color space obtaining a second intermediate picture; threshold determining means 430 configured to determine a comparison threshold based on tooth color; and pixel ratio determining means 440 configured to determine a comparison threshold based on the first The second intermediate picture and the comparison threshold determine the ratio of the pixels located within the comparison threshold to the pixels of the second intermediate picture.
  • the first intermediate picture includes an area of teeth in the picture and the comparison threshold includes a calculus comparison threshold, and wherein based on the second intermediate picture and the Determining the ratio of the pixel points within the comparison threshold to the pixel points of the second intermediate picture by comparing the threshold value further includes: determining, based on the second intermediate picture and the dental calculus comparison threshold, that the pixel points are located within the dental calculus comparison threshold The ratio of the pixel points of the second intermediate picture to the pixel points of the second intermediate picture.
  • the first intermediate picture includes a gingival area in the picture and the comparison threshold includes a gingivitis comparison threshold, and wherein based on the second intermediate picture and the Determining the ratio of the pixel points within the comparison threshold to the pixel points of the second intermediate picture by comparing the threshold further includes: determining, based on the second intermediate picture and the gingivitis comparison threshold, that the pixel points are within the gingivitis comparison threshold The ratio of the pixel points of the second intermediate picture to the pixel points of the second intermediate picture.
  • the tooth color is determined by the following methods: acquiring a picture of the oral cavity; performing median filtering, grayscale conversion and adaptive threshold segmentation operations on the picture to obtain a first intermediate picture; Convert the first intermediate picture from the RGB color space to the LAB color space to obtain a third intermediate picture; compare the pixels in the third intermediate picture with the standard color; and determine the tooth color according to the comparison result.
  • determining the tooth color according to the comparison result further comprises: determining the tooth color according to a weighted summation of the weights of each standard color value.
  • the dental calculus comparison threshold includes at least two sets of threshold intervals including a high threshold and a low threshold, or the gingivitis comparison threshold includes at least two sets of a high threshold and a low threshold, respectively The threshold interval for the threshold.
  • the low threshold is lower than the high threshold
  • the low threshold and the high threshold of the gingivitis comparison threshold are selected from the following interval: np.array([ 0,80,12]) to np.array([40,235,210]), or the low threshold and the high threshold of the calculus comparison threshold are selected from the following interval: np.array([0,30,10] ) to np.array([190,255,70]).
  • an embodiment of the present disclosure also provides a tangible computer-readable storage medium, the storage medium includes instructions for executing the oral cavity detection method, when the instructions are executed, the computer's
  • the processor is used for at least:
  • the ratio of the pixels located within the comparison threshold to the pixels of the second intermediate picture is determined.
  • the first intermediate picture includes an area of teeth in the picture and the comparison threshold includes a calculus comparison threshold, and wherein based on the second intermediate picture and the Determining the ratio of the pixels within the comparison threshold to the pixels in the second intermediate picture by comparing the threshold further includes:
  • the ratio of the pixel points located within the dental calculus comparison threshold to the pixel points of the second intermediate picture is determined.
  • the first intermediate picture includes a gingival area in the picture and the comparison threshold includes a gingivitis comparison threshold, and wherein based on the second intermediate picture and the Determining the ratio of the pixels within the comparison threshold to the pixels in the second intermediate picture by comparing the threshold further includes:
  • the proportion of the pixels located within the gingivitis comparison threshold to the pixels of the second intermediate picture is determined.
  • the tooth color is determined by:
  • the tooth color is determined based on the comparison results.
  • the standard color includes the following six standard color values:
  • RGBColor0 sRGBColor(255,255,255);
  • RGBColor1 sRGBColor(164,192,239)
  • RGBColor2 sRGBColor(131,172,217);
  • RGBColor3 sRGBColor(124,149,205);
  • RGBColor4 sRGBColor(21, 46, 110);
  • RGBColor5 sRGBColor(255, 255, 0).
  • determining the tooth color according to the comparison result further comprises:
  • the tooth color is determined from a weighted summation of the weights of each standard color value.
  • the dental calculus comparison threshold includes at least two sets of threshold intervals including a high threshold and a low threshold, or the gingivitis comparison threshold includes at least two sets of a high threshold and a low threshold, respectively The threshold interval for the threshold.
  • the low threshold is lower than the high threshold
  • the low threshold and the high threshold of the gingivitis comparison threshold are selected from the following interval: np.array([ 0,80,12]) to np.array([40,235,210]), or the low threshold and the high threshold of the calculus comparison threshold are selected from the following interval: np.array([0,30,10] ) to np.array([190,255,70]).
  • the oral detection method, the oral detection device, and the corresponding computer-readable storage medium will set different comparison thresholds according to the color of the subject's own teeth, thereby Targeted detection that conforms to its own characteristics can be carried out for different subjects, so that the pixels determined based on the second intermediate picture and the comparison threshold and located within the comparison threshold account for the second intermediate picture.
  • the ratio of the pixel points is more accurate and effective than the ratio determined by the traditional method, which is beneficial to the subsequent oral health assessment.
  • the above-described method can be implemented by a computer program product, ie a computer-readable storage medium.
  • the computer program product may include a computer-readable storage medium having computer-readable program instructions loaded thereon for carrying out various aspects of the present disclosure.
  • a computer-readable storage medium may be a tangible device that can hold and store instructions for use by the instruction execution device.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
  • Non-exhaustive list of computer readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM) or flash memory), static random access memory (SRAM), portable compact disk read only memory (CD-ROM), digital versatile disk (DVD), memory sticks, floppy disks, mechanically coded devices, such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above.
  • RAM random access memory
  • ROM read only memory
  • EPROM erasable programmable read only memory
  • flash memory static random access memory
  • SRAM static random access memory
  • CD-ROM compact disk read only memory
  • DVD digital versatile disk
  • memory sticks floppy disks
  • mechanically coded devices such as printers with instructions stored thereon Hole cards or raised structures in grooves, and any suitable combination of the above.
  • Computer-readable storage media are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (eg, light pulses through fiber optic cables), or through electrical wires transmitted electrical signals.
  • FIG. 4 shows a schematic block diagram of an oral detection device 400 proposed according to an embodiment of the present disclosure.
  • the oral cavity detection device 400 may be implemented to implement the functions of the oral cavity detection method 100 in FIG. 1 or the oral cavity detection method 200 in FIG. 2 .
  • the oral detection device 400 includes a central processing unit (CPU) 401 (eg, a processor) that can be loaded into a random access device according to computer program instructions stored in a read only memory (ROM) 402 or from a storage unit 408
  • Computer program instructions in memory (RAM) 403 are accessed to perform various appropriate actions and processes.
  • the RAM 403 various programs and data required for the operation of the oral cavity detection device 400 can also be stored.
  • the CPU 401, the ROM 402, and the RAM 403 are connected to each other through a bus 404.
  • An input/output (I/O) interface 405 is also connected to bus 404 .
  • a number of components in the oral detection device 400 are connected to the I/O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, CD-ROM, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, and the like.
  • the communication unit 409 allows the apparatus 400 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.
  • a third aspect of the present disclosure provides a tangible computer-readable storage medium comprising instructions for performing an oral detection method that, when executed, cause the computer's
  • the processor is at least configured to perform functions according to the oral cavity detection method 100 in FIG. 1 or the oral cavity detection method 200 in FIG. 2 .
  • oral inspection method 100 or oral inspection method 200 may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 408 .
  • part or all of the computer program may be loaded and/or installed on the oral detection device 400 via the ROM 402 and/or the communication unit 409.
  • processor CPU 401 When the computer program is loaded into RAM 403 and executed by processor CPU 401, one or more actions or steps in oral cavity detection method 100 or oral cavity detection method 200 described above may be performed.
  • the various example embodiments of the present disclosure may be implemented in hardware or special purpose circuits, software, firmware, logic, or any combination thereof. Certain aspects may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor or other computing device. While aspects of the embodiments of the present disclosure are illustrated or described as block diagrams, flowcharts, or using some other graphical representation, it is to be understood that the blocks, apparatus, systems, techniques, or methods described herein may be taken as non-limiting Examples of are implemented in hardware, software, firmware, special purpose circuits or logic, general purpose hardware or controllers or other computing devices, or some combination thereof.
  • the above-described data processing device for blockchain can be implemented in both hardware and software.
  • a technical improvement could easily be a hardware improvement (for example, an improvement in the circuit structure of diodes, transistors, switches, etc.) or a software improvement (for example, for method flow improvements).
  • a technical improvement could easily be a hardware improvement (for example, an improvement in the circuit structure of diodes, transistors, switches, etc.) or a software improvement (for example, for method flow improvements).
  • a technical improvement could easily be a hardware improvement (for example, an improvement in the circuit structure of diodes, transistors, switches, etc.) or a software improvement (for example, for method flow improvements).
  • the improvement of many methods and procedures today can almost be realized by programming the improved method procedures into the hardware circuit.
  • the corresponding hardware is obtained.
  • the circuit structure realizes the change of the hardware circuit structure, so the improvement of the method flow can also be regarded as a direct improvement of the hardware circuit structure.
  • a Programmable Logic Device (such as a Field Programmable Gate Array (FPGA)) is an integrated circuit whose logic function is determined by user programming of the device. It is programmed by the designer to "integrate" a digital system on a piece of programmable logic device, without the need for a chip manufacturer to design and manufacture a dedicated integrated circuit chip.
  • PLD Programmable Logic Device
  • FPGA Field Programmable Gate Array
  • HDL Hardware Description Language
  • ABEL Advanced Boolean Expression Language
  • AHDL Altera Hardware Description Language
  • HDCal JHDL
  • Lava Lava
  • Lola MyHDL
  • PALASM RHDL
  • VHDL Very-High-Speed Integrated Circuit Hardware Description Language
  • Verilog Verilog
  • Computer readable program instructions or computer program products for executing various aspects of the present disclosure can also be stored in the cloud, and when invoked, users can access the data stored in the cloud for execution through the mobile Internet, fixed network or other network.
  • the computer-readable program instructions of an aspect of the present disclosure thereby implement the technical solutions disclosed in accordance with various aspects of the present disclosure.
  • the oral detection method, the oral detection device and the corresponding computer-readable storage medium provided according to the three aspects of the present disclosure will set different comparison thresholds according to the subject's own tooth color, thereby Targeted detection that conforms to its own characteristics can be carried out for different subjects, so that the pixels determined based on the second intermediate picture and the comparison threshold and located within the comparison threshold account for the second intermediate picture.
  • the ratio of the pixel points is more accurate and effective than the ratio determined by the traditional method, which is beneficial to the subsequent oral health assessment.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Quality & Reliability (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Epidemiology (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Dental Tools And Instruments Or Auxiliary Dental Instruments (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

一种口腔检测方法，包括：图片获取口腔图片；对图片执行中值滤波和区域分割操作得到第一中间图片；将第一中间图片由RGB颜色空间转换至HSV颜色空间得到第二中间图片；基于牙齿颜色确定比较阈值；以及基于第二中间图片和比较阈值确定位于比较阈值内的像素点占所述第二中间图片的像素点的比例。该口腔检测方法会根据受试者自身的牙齿颜色来设定不同的比较阈值，从而能够针对不同的受试者进行符合其自身特点的有针对性的检测，使得基于所述第二中间图片和所述比较阈值所确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例比传统方法所确定的比例更为精确有效，进而有利于后续的口腔健康状况评估。

Description

口腔检测方法、口腔检测装置以及计算机可读存储介质 技术领域
本公开内容涉及口腔检测领域，更为具体地涉及一种口腔检测方法、一种口腔检测装置以及一种用于执行上述口腔检测方法的计算机可读存储介质。
背景技术
US2019/0167115 A1公开了一种用于处理口腔图像的系统，该用于处理口腔图像的系统包括：图像捕获装置；被配置为附接到图像捕获设备并且将图像捕获设备相对于用户的嘴安装在固定位置的口腔附件；显示器以及处理单元，其中，处理单元被配置为：从图像捕获设备接收口腔图像数据；以及在图像数据中识别与牙齿和牙龈相对应的分析区域；从图像数据的分析区域中提取一组图像属性特征；使图像属性特征通过条件分类器，条件分类器被配置为将提取的图像属性特征的值与预设参数进行比较，以识别指示口腔健康状况的分析区域的子区域；并将与所识别的子区域相对应的结果数据发送到显示器。
发明内容
如前所述，现有技术中存在以下技术问题，即现有的口腔图像处理系统并不会针对不同的受试者进行符合其自身特点的有针对性的检测。
本公开内容所旨在实现的目的在于针对不同的受试者进行符合其自身特点的有针对性的检测。针对上述技术问题，本公开内容的发明人基于不同的受试者有着不同的自身特性的思考，本公开内容的第一方面提出了一种口腔检测方法，所述口腔检测方法包括：
获取口腔图片；
对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；
将所述第一中间图片由RGB颜色空间转换至HSV颜色空间得到第二中间图片；
基于牙齿颜色确定比较阈值；以及
基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例。
依据本公开内容的口腔检测方法会根据受试者自身的牙齿颜色来设定不同的比较阈值，从而能够针对不同的受试者进行符合其自身特点的有针对性的检测，使得基于所述第二中间图片和所述比较阈值所确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例。比传统方法所确定的比例更为精确有效，进而有利于后续的口腔健康状况评估。
在依据本公开内容的一个实施例之中，所述第一中间图片包括所述图片中的牙齿区域并且所述比较阈值包括牙结石比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
基于所述第二中间图片和所述牙结石比较阈值确定位于所述牙结石比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，所述第一中间图片包括所述图片中的牙龈区域并且所述比较阈值包括牙龈炎比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
基于所述第二中间图片和所述牙龈炎比较阈值确定位于所述牙龈炎比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，所述口腔检测方法还包括：调整所述口腔图片的对比度。
在依据本公开内容的一个实施例之中，所述牙齿颜色通过以下方法确定：
获取口腔图片；
对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；
将所述第一中间图片由RGB颜色空间转换至LAB颜色空间得到第三中间图片；
将所述第三中间图片中的像素点和标准颜色进行比较；以及
根据比较结果确定所述牙齿颜色。
在依据本公开内容的一个实施例之中，所述标准颜色包括以下六个标准颜色值：
RGBColor0＝sRGBColor(255,255,255)；
RGBColor1＝sRGBColor(164,192,239)；
RGBColor2＝sRGBColor(131,172,217)；
RGBColor3＝sRGBColor(124,149,205)；
RGBColor4＝sRGBColor(21,46,110)；以及
RGBColor5＝sRGBColor(255,255,0)。
在依据本公开内容的一个实施例之中，根据比较结果确定所述牙齿颜色进一步包括：
根据每个标准颜色值的权重加权求和来确定所述牙齿颜色。
在依据本公开内容的一个实施例之中，所述牙结石比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间，或者所述牙龈炎比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间。
在依据本公开内容的一个实施例之中，所述低位阈值低于所述高位阈值，并且所述牙龈炎比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,80,12])至np.array([40,235,210])，或者所述牙结石比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,30,10])至np.array([190,255,70])。
此外，本公开内容的第二方面提出了一种口腔检测装置，所述口腔检测装置包括：
摄像装置，所述摄像装置被配置用于获取口腔图片；
图片处理装置，所述图片处理装置被配置用于对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片并且将所述第一中间图片由RGB颜色空间转换至HSV颜色空间得到第二中间图片；
阈值确定装置，所述阈值确定装置被配置用于基于牙齿颜色确定比较阈值；以及
像素比例确定装置，所述像素比例确定装置被配置用于基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，所述第一中间图片包括所述图 片中的牙齿区域并且所述比较阈值包括牙结石比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
基于所述第二中间图片和所述牙结石比较阈值确定位于所述牙结石比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，所述第一中间图片包括所述图片中的牙龈区域并且所述比较阈值包括牙龈炎比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
基于所述第二中间图片和所述牙龈炎比较阈值确定位于所述牙龈炎比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，所述图片处理装置被配置用于调整所述口腔图片的对比度。
在依据本公开内容的一个实施例之中，所述牙齿颜色通过以下方法确定：
获取口腔图片；
对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；
将所述第一中间图片由RGB颜色空间转换至LAB颜色空间得到第三中间图片；
将所述第三中间图片中的像素点和标准颜色进行比较；以及
根据比较结果确定所述牙齿颜色。
在依据本公开内容的一个实施例之中，所述标准颜色包括以下六个标准颜色值：
RGBColor0＝sRGBColor(255,255,255)；
RGBColor1＝sRGBColor(164,192,239)；
RGBColor2＝sRGBColor(131,172,217)；
RGBColor3＝sRGBColor(124,149,205)；
RGBColor4＝sRGBColor(21,46,110)；以及
RGBColor5＝sRGBColor(255,255,0)。
在依据本公开内容的一个实施例之中，根据比较结果确定所述牙齿颜 色进一步包括：
根据每个标准颜色值的权重加权求和来确定所述牙齿颜色。
在依据本公开内容的一个实施例之中，所述牙结石比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间，或者所述牙龈炎比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间。
在依据本公开内容的一个实施例之中，所述低位阈值低于所述高位阈值，并且所述牙龈炎比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,80,12])至np.array([40,235,210])，或者所述牙结石比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,30,10])至np.array([190,255,70])。
再者，本公开内容的第三方面提出了一种有形的计算机可读存储介质，所述存储介质包括用于执行口腔检测方法的指令，当所述指令被执行时，使得所述计算机的处理器至少用于：
获取口腔图片；
对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；
将所述第一中间图片由RGB颜色空间转换至HSV颜色空间得到第二中间图片；
基于牙齿颜色确定比较阈值；以及
基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，所述第一中间图片包括所述图片中的牙齿区域并且所述比较阈值包括牙结石比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
基于所述第二中间图片和所述牙结石比较阈值确定位于所述牙结石比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，所述第一中间图片包括所述图片中的牙龈区域并且所述比较阈值包括牙龈炎比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
基于所述第二中间图片和所述牙龈炎比较阈值确定位于所述牙龈炎比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，当所述指令被执行时，还使得所述计算机的处理器至少用于：调整所述口腔图片的对比度。
在依据本公开内容的一个实施例之中，所述牙齿颜色通过以下方法确定：
获取口腔图片；
对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；
将所述第一中间图片由RGB颜色空间转换至LAB颜色空间得到第三中间图片；
将所述第三中间图片中的像素点和标准颜色进行比较；以及
根据比较结果确定所述牙齿颜色。
在依据本公开内容的一个实施例之中，所述标准颜色包括以下六个标准颜色值：
RGBColor0＝sRGBColor(255,255,255)；
RGBColor1＝sRGBColor(164,192,239)；
RGBColor2＝sRGBColor(131,172,217)；
RGBColor3＝sRGBColor(124,149,205)；
RGBColor4＝sRGBColor(21,46,110)；以及
RGBColor5＝sRGBColor(255,255,0)。
在依据本公开内容的一个实施例之中，根据比较结果确定所述牙齿颜色进一步包括：
根据每个标准颜色值的权重加权求和来确定所述牙齿颜色。
在依据本公开内容的一个实施例之中，所述牙结石比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间，或者所述牙龈炎比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间。
在依据本公开内容的一个实施例之中，所述低位阈值低于所述高位阈值，并且所述牙龈炎比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,80,12])至np.array([40,235,210])，或者所述牙结石比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,30,10]) 至np.array([190,255,70])。
综上所述，通过依据本公开内容的三个方面所提供的口腔检测方法、口腔检测装置以及相应地计算机可读存储介质会根据受试者自身的牙齿颜色来设定不同的比较阈值，从而能够针对不同的受试者进行符合其自身特点的有针对性的检测，使得基于所述第二中间图片和所述比较阈值所确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例比传统方法所确定的比例更为精确有效，进而有利于后续的口腔健康状况评估。本公开内容的其他优势将在下文中进一步说明。
附图说明
结合附图并参考以下详细说明，本公开内容的各实施例的特征、优点及其他方面将变得更加明显，在此以示例性而非限制性的方式示出了本公开内容的若干实施例，在附图中：
图1示出了根据本公开内容的一个实施例的口腔检测方法100的流程图；
图2示出了根据本公开内容的另一个实施例的口腔检测方法200的流程图；
图3示出了根据本公开内容的一个实施例的口腔检测装置300的示意方框图；以及
图4示出了根据本公开内容的另一个实施例的口腔检测装置400的示意方框图。
具体实施方式
以下参考附图详细描述本公开内容的各个示例性实施例。虽然以下所描述的示例性方法、装置包括在其它组件当中的硬件上执行的软件和/或固件，但是应当注意，这些示例仅仅是说明性的，而不应看作是限制性的。例如，考虑在硬件中独占地、在软件中独占地、或在硬件和软件的任何组合中可以实施任何或所有硬件、软件和固件组件。因此，虽然以下已经描述了示例性的方法和装置，但是本领域的技术人员应容易理解，所提供的示例并不用于限制用于实现这些方法和装置的方式。
此外，附图中的流程图和框图示出了根据本公开内容的各种实施例的方法和系统的可能实现的体系架构、功能和操作。应当注意，方框中所标注的功能也可以按照不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，或者它们有时也可以按照相反的顺序执行，这取决于所涉及的功能。同样应当注意的是，流程图和/或框图中的每个方框、以及流程图和/或框图中的方框的组合，可以使用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以使用专用硬件与计算机指令的组合来实现。
本公开内容之中的术语“中值滤波”基本上是指基于排序统计理论的一种能有效抑制噪声的非线性信号处理技术，中值滤波的基本原理是把数字图像或数字序列中一点的值用该点的一个邻域中各点值的中值代替，让周围的像素值接近的真实值，从而消除孤立的噪声点。其中像素点是指单位面积中构成图像的点，其中，每个像素点可能都有不同的颜色值。单位面积内的像素越多，分辨率越高，图像的效果就越好。
本公开内容之中的术语“自适应阈值分割”基本上是指一种图像处理技术。图像区域分割的目的是从图像中划分出某个物体的区域，即找出那些对应于物体或物体表面的像元集合，它们表现为二维的团块状，这是区域基本形状特点之一。
本公开内容之中的所出现的图片包括但不限于对原始图片进行裁剪、调整对比度、中值滤波、自适应阈值分割等操作中的一个或者多个操作之后所得到的图像数据，其既能够是传统意义上的例如JPEG图片，也能够是其他格式的图片，或者说其能够是其他类型的经过图像处理的像素点，只要其能够满足本公开内容所提出的技术方案所旨在实现的技术目的即可。
本公开内容之中的术语“第一中间图片”基本上是指将口腔图片执行了中值滤波、转灰度图和自适应阈值分割操作之后得到的中间图片，该中间图片将包括牙龈和牙齿所在的检测区域。
本公开内容之中的术语“颜色空间”基本上是指彩色模型(又称彩色空间或彩色系统)，它的用途是在某些标准下用通常可接受的方式对彩色加以说明。其中，术语“RGB颜色空间”基本上是指R(Red红)、G(Green绿)、B(Blue蓝)三种基本色为基础的颜色空间，对他们进行不同程度的叠加，产 生丰富而广泛的颜色，所以俗称三基色模式。而术语“HSV颜色空间”基本上是指为了更好的数字化处理颜色而提出来的颜色空间。有许多种HSX颜色空间，其中的X可能是V，也可能是I，依据具体使用而X含义不同。H是色调，S是饱和度，V是明度，I是强度。而术语“LAB颜色空间”基本上是指由三个要素组成，一个要素是亮度(L)，A和B是两个颜色通道。a包括的颜色是从深绿色(低亮度值)到灰色(中亮度值)再到亮粉红色(高亮度值)；b是从亮蓝色(低亮度值)到灰色(中亮度值)再到黄色(高亮度值)。因此，这种颜色混合后将产生具有明亮效果的色彩。
本公开内容之中的术语“第二中间图片”基本上是指将第一中间图片由RGB颜色空间转换到HSV颜色空间所得到的中间图片。相应地，本公开内容之中的术语“第三中间图片”基本上是指将第一中间图片由RGB颜色空间转换到LAB颜色空间所得到的中间图片。
本公开内容之中的术语“标准颜色”基本上是指从整个色域中所选取的几个作为标准的比对颜色值，其在本申请之中例如能够为以下六个标准颜色，即：RGBColor0＝sRGBColor(255,255,255)、RGBColor1＝sRGBColor(164,192,239)、RGBColor2＝sRGBColor(131,172,217)、RGBColor3＝sRGBColor(124,149,205)、RGBColor4＝sRGBColor(21,46,110)以及RGBColor5＝sRGBColor(255,255,0)。当然，本领域的技术人员应当了解，这样的选择仅仅是示例性的而非限制性的。
本公开内容之中的术语“比较阈值”基本上是指包括至少两组分别包括高位阈值和低位阈值的阈值区间，其中，所述低位阈值低于所述高位阈值并且所述低位阈值和所述高位阈值从以下区间选择：np.array([0,80,12])至np.array([40,235,210])或者np.array([0,30,10])至np.array([190,255,70])，具体而言，所述牙龈炎比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,80,12])至np.array([40,235,210])，或者所述牙结石比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,30,10])至np.array([190,255,70])。
在开始介绍本公开内容所提出的口腔检测方法之前，本公开内容的申请人希望首先介绍本公开内容所公开的口腔检测装置的硬件选型设计，但是以下说明仅仅是示例性的，而非限制性的，只要能够实现所旨在设计的目的，其他选型也是可行的，也就是说其他选型也将落入本公开内容的权 利要求书所要求保护的范围之内。
硬件方面，通过如下特别设计的结构，拍摄到高质量的口腔例如白光的非紫外光照片与紫外光照片，在此，紫外光照片并不是必须的，而是可选的。其中摄像头模块例如采用的是800万高清自动对焦模组，型号为KS8A17，模组尺寸为38mm x 38mm，工作温度为-20℃到70℃，成像距离3厘米至无穷远，该模块能够拍出3264 x 2448分辨率的照片，有着优异的低照度环境响应能力并且能够高速传输到控制器进行处理。而紫外光模块例如能够是UV灯结构，该UV灯外形简洁，包括UV灯电极、内置UV灯珠(中心波长例如为365nm)、圆锥状结构(可实现聚光功能)以及UV滤光片(可以滤掉干扰光，仅保留UV光通过)。该模块供电后可作为口腔图像采集过程中的UV光源。至于UV灯的排布而言，UV灯部分例如能够由2个UV灯组成，分别位于摄像头左右两边，距离摄像头在1至3厘米之间。
此外，非紫外光模块例如能够是白光LED灯结构，采用的是3mm LED白色发光二极管。至于LED灯的排布而言，LED灯部分例如由4个LED白灯组成，分别位于口腔检测仪内部4个顶角的位置，围绕摄像头呈矩形排布，距离摄像头在1至5厘米之间。
再者，所使用的电源模块能够为UV灯供电模块，可通过两节五号电池分别给两个UV灯供电，电压均为1.5V，通过继电器连接电池和UV灯，实现控制。此外，该电源模块也能够包括为控制器供电的模块，可通过5V1500mAh锂电池作为整机的供电电源，除UV灯外的结构都由此供电。
而在算法方面，基于硬件采集到的高质量的口腔诸如白光照片的非紫外光照片与紫外光照片，进行如下口腔问题的分析：
首先介绍牙齿颜色分析的过程以及相应的评分过程。在该过程中，基于口腔图片，诸如正白光图片的非紫外光照片，经过中值滤波、转灰度图和自适应阈值分割，由原来的RGB颜色空间，转为LAB颜色空间；然后和标准颜色对比，这六个标准颜色例如分别是RGBColor0＝sRGBColor(255,255,255)、RGBColor1＝sRGBColor(164,192,239)、RGBColor2＝sRGBColor(131,172,217)、RGBColor3＝sRGBColor(124,149,205)、RGBColor4＝sRGBColor(21,46,110)、RGBColor5＝sRGBColor(255,255,0)，最后不同颜色在得分上有不同的权重占比，加权求和，即可最终得到受试 者的牙齿颜色得分。例如，正白光照片得到一万个像素点，然后将这一万个像素点的像素值与上述的六个标准色做比较，即将这一万个像素点按照和哪个标准色接近进行分类，统计离各个标准色接近的像素点的个数，然后加权平均即可最终得到受试者的牙齿颜色得分。
此为通过图像处理的技术获取牙齿颜色的数值的技术方案，然后牙齿颜色并非必须通过上述方式确定，也能够定性地确定牙齿颜色，例如，将牙齿颜色先分成不同的档(例如黑，非常黄，黄，白，非常白等)，每一档对应一个比较阈值。然后也可以例如通过受试者自己选择自己牙齿颜色的定性评价，根据受试者的选择相应地进行比较阈值的确定。
在定量地确定牙齿颜色的技术方案之中，图1示出了根据本公开内容的一个实施例的口腔检测方法100的流程图。从图1之中可以看出，口腔检测方法100中的牙齿颜色通过以下方法确定：首先，在方法步骤111之中，获取口腔图片；然后，在方法步骤112之中，对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；接着，在方法步骤113之中，将所述第一中间图片由RGB颜色空间转换至LAB颜色空间得到第三中间图片；再然后，在方法步骤114之中，将所述第三中间图片中的像素点和标准颜色进行比较；以及最后在方法步骤115之中，根据比较结果确定所述牙齿颜色。在依据本公开内容的一个实施例之中，如前所述，所述标准颜色包括以下六个标准颜色值：RGBColor0＝sRGBColor(255,255,255)；RGBColor1＝sRGBColor(164,192,239)；RGBColor2＝sRGBColor(131,172,217)；RGBColor3＝sRGBColor(124,149,205)；RGBColor4＝sRGBColor(21,46,110)；以及RGBColor5＝sRGBColor(255,255,0)。在依据本公开内容的一个实施例之中，根据比较结果确定所述牙齿颜色进一步包括：根据每个标准颜色值的权重加权求和来确定所述牙齿颜色。
也就是说，在得到诸如正白光的非紫外光的口腔图片之后，将会对该非紫外光图片执行中值滤波操作，从而消除噪声点，例如如果在图像中取3*3的像素矩阵，即该像素矩阵里面有9个像素点，将9个像素进行排序，最后将这个矩阵的中心点赋值为这九个像素的中值，该操作即称为中值滤波操作。然后将其转换为灰度图，具体转换方法为将按照RGB三个颜色的三通道图片中的每个像素点做这个操作r*0.2126+g*0.7152+b*0.0722，三个 通道的图，按比例叠加，就可以得到灰度图。接下来进行自适应阈值调整和区域分割，以将所关心的区域分割出来，具体而言，在灰度图的基础上每个像素点的实际值分布在[0,255]之间，然后需要进一步细分那些像素点是前景，那些像素点是背景，这里自适应就是遍历0到255，确定一个像素值是前景类的像素点还是后景类的像素点，让前景类像素点的类和后景类像素点的类的相关系数最大化，从而得到自适应阈值，进而利用该自适应阈值来区分前后景的像素并执行区域分割操作，从而得到所关心的区域，在此为仅仅是牙齿区域和牙龈区域。可选地，基于所述非紫外光图片确定包括牙齿区域和牙龈区域在内的第一区域还能够包括调整所述非紫外光图片的对比度，以增强对比度，简单说例如能够利用原图和一张黑色的图，像素点按比例叠加形成一幅新图，新图的前后景像素值差值会变大，也就是增强了图像对比度，从而有利于后续的自适应阈值分割操作。
通过图1所示的方法能够确定受试者牙齿的颜色，然后，便能够根据牙齿颜色的不同对每个受试者进行有针对性的口腔检测了。当然，受试者的牙齿颜色也不一定在每次口腔检测时进行确定，也能够例如由受试者将自己的牙齿颜色输入至相关设备或者仪器之中。而且此处的非紫外光的口腔图片也并非必须由摄像头实时拍摄的，也能够例如经由通信接口从网络位置下载、通过其他图片抽取的口腔图片或者是经过预处理而获得的口腔图片。
在确定了牙齿颜色之后，图2示出了依据本公开内容的一个实施例的口腔检测方法200的流程图，从图2中可以看出，图2所示出的依据本公开内容所述口腔检测方法200至少包括以下几个步骤：首先，在方法步骤220之中，获取口腔图片，此处所获取的口腔图片既可以是先前确定牙齿颜色所使用的口腔图片，也能够是其他口腔图片，而且与之前相类似地，此处的非紫外光的口腔图片也并非必须由摄像头实时拍摄的，也能够例如经由通信接口从网络位置下载、通过其他图片抽取的口腔图片或者是经过预处理而获得的口腔图片。然后，在方法步骤230之中，对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；接下来，在方法步骤240之中，将所述第一中间图片由RGB颜色空间转换至HSV颜色空间得到第二中间图片；再接下来，在方法步骤250之中，基于牙齿颜色确定比较阈值；以及最后在方法步骤260之中，基于所述第二中间图片 和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例。在此，本领域的技术人员应当了解，此处的方法执行步骤的顺序并非必须如图2所示出的那样，也能够例如先根据受试者的牙齿颜色来确定比较阈值，然后再进行口腔图片的获取以及处理。本领域的技术人员应当了解，此处执行的中值滤波、转灰度图和自适应阈值分割操作与先前在确定牙齿颜色中所使用的技术手段相似，为了节省篇幅，在此不再赘述。
具体而言，该口腔检测方法例如能够用于确定受试者的牙龈状况的评估，此时，该口腔检测方法用于牙龈炎检测与评分。在此过程之中，基于口腔例如正白光图片的图片，可选地先调整图片对比度，然后相继地进行中值滤波、转灰度图和自适应阈值分割操作。对于牙齿炎症的确定过程来说，主要查看牙龈，所以通过自适应阈值分割剪裁之后，去除牙齿区域，得到检测图片；同样需要将检测图片由原来的RGB颜色空间，转换为HSV颜色空间，然后调整阈值约束，阈值以内的像素点即可被判定为牙龈感染区域，最后通过感染区域像素点与整个区域像素点数的比值得到最终分数。概括地将，此时口腔检测方法200之中的所述第一中间图片包括所述图片中的牙龈区域并且所述比较阈值包括牙龈炎比较阈值，并且其中，方法步骤260，即基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：基于所述第二中间图片和所述牙龈炎比较阈值确定位于所述牙龈炎比较阈值内的像素点占所述第二中间图片的像素点的比例。
举例来说，首先输入口腔诸如正白光图片的图片，接着可选地调整图片对比度，这里需要用的两个参数例如分别是alpha＝0.7、beta＝20，将原图与一张同尺寸的全黑图片混合叠加，降低原图片像素值。再对此图片进行中值滤波，除去噪声像素点。然后再将图片转为灰度图，利用自适应阈值分割，得到检测区域。紧接着将原来的RGB颜色空间图片转为HSV颜色空间图片，设置疑似牙龈炎阈值。在依据本公开内容的一个实施例之中，所述比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间。在依据本公开内容的一个实施例之中，所述低位阈值低于所述高位阈值并且所述低位阈值和所述高位阈值从以下区间选择：np.array([0,80,12])至np.array([40,235,210])。
这里例如分别有三个区间范围，每个区间范围中低位阈值低于所述高位阈值并且所述低位阈值和所述高位阈值从以下区间选择：np.array([0,80,12])至np.array([40,235,210])或者np.array([0,30,10])至np.array([190,255,70])，其中，np.array([0,80,12])至np.array([40,235,210])这一区间主要用于牙龈炎比较阈值的选择，而np.array([0,30,10])至np.array([190,255,70])这一区间主要用于牙结石比较阈值的选择。
具体而言，例如低位阈值为np.array([0,170,60])以及高位阈值为np.array([10,215,70])；或者低位阈值为np.array([0,170,35])以及高位阈值为np.array([10,225,50])；或者低位阈值为np.array([20,130,130])以及高位阈值为np.array([26,200,200])。例如，当受试者的牙齿较黄，例如之前的牙齿颜色得分在60分以下时，选择低位阈值为np.array([20,130,130])以及高位阈值为np.array([26,200,200])的比较阈值；当受试者的牙齿较白，例如之前的牙齿颜色得分在60分以上80分以下时，选择低位阈值为np.array([0,170,35])以及高位阈值为np.array([10,225,50])的比较阈值；而当受试者的牙齿非常白，例如之前的牙齿颜色得分在80分以上时，选择低位阈值为np.array([0,170,60])以及高位阈值为np.array([10,215,70])的比较阈值。
在此，高位阈值和低位阈值的选择仅仅是示例性的，而非限制性的，本领域的技术人员也可以在上述区间范围内进行其他数值的选择。
具体到每个受试者进行口腔检测时来说，将根据受试者的牙齿颜色进行比较阈值的动态选择或者设定，然后将高于低位阈值并且低于高位阈值的像素点设置为0，在此之间的像素点也就是疑似牙龈炎区域，统计牙龈炎像素点，然后与总共检测区域像数点数求比值ratio，最终牙龈炎检测分数为10-99.9*10*ratio。
此外，该口腔检测方法例如也能够用于确定受试者的牙结石的评估，此时，该口腔检测方法用于检测受试者的牙结石状况。在此过程之中，所述第一中间图片包括所述图片中的牙齿区域并且所述比较阈值包括牙结石比较阈值，并且其中，方法步骤260即基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：基于所述第二中间图片和所述牙结石比较阈值确定位于所述牙结石比较阈值内的像素点占所述第二中间图片的像素点的比例。换句话说，此时依据本公开内容的口腔检测方法会基于口腔诸如正白光图片的 图片，可选地调整图片对比度，经过中值滤波；然后转灰度图并进行诸如检测区域剪裁的自适应阈值分割，得到检测部分图片，在对其进行由RGB颜色空间转换到HSV颜色空间；然后设置阈值，除去非检测部分，得到牙结石的像素点，利用这些检测到的像素点与总共检测区域像素点数的比值，得到牙结石检测得分。
举例来说，首先输入口腔的诸如正白光图片的图片，接着优选地调整图片对比度，这里需要用的两个参数例如分别是alpha＝0.5、beta＝-30，将原图与一张同尺寸的全黑图片混合叠加，降低原图片像素值。再对此图片进行中值滤波，除去噪声像素点。然后再将图片转为灰度图，利用自适应阈值进行区域分割，得到检测区域。紧接着将原来的RGB颜色空间图片转为HSV颜色空间图片，设置疑似牙结石阈值，分别为低位阈值设定为诸如np.array([18,90,22])，高位阈值设定为诸如np.array([30,225,60])，然后将高于低位阈值并且低于高位阈值的像素点设置为0，在此之间的像素点也就是疑似牙结石区域，统计牙结石像素点，然后与总共检测区域像数点数求比值ratio，最终牙结石检测分数为10-99.9*10*ratio。在此，低位阈值和高位阈值的选择仅仅是示例性的，而非限制性的，本领域的技术人员当然也能够根据受试者的牙齿颜色选择其他的阈值。
如前所述，可以根据牙齿颜色来确定牙结石比较阈值。例如，当受试者的牙齿较黄，例如之前的牙齿颜色得分在60分以下时，选择低位阈值为np.array([150,50,18])以及高位阈值为np.array([180,130,30])的比较阈值；当受试者的牙齿较白，例如之前的牙齿颜色得分在60分以上80分以下时，选择低位阈值为np.array([2,240,10])以及高位阈值为np.array([20,255,25])的比较阈值；而当受试者的牙齿非常白，例如之前的牙齿颜色得分在80分以上时，选择低位阈值为np.array([18,90,22])以及高位阈值为np.array([30,225,60])的比较阈值。
上述的通过牙齿颜色来动态确定牙龈炎比较阈值和牙结石比较阈值的实施例仅仅是一种示例，其对于本公开内容的权利要求书的保护范围并不会起到限定作用，本领域的技术人员应当了解，在具体实施时例如也能够通过牙龈颜色来动态确定牙龈炎比较阈值和牙结石比较阈值。换句话说，上述检测维度中，一种或几种维度的检测可以进行叠加，如牙齿或者牙龈颜色的结果可以作为其他检测维度的基本参数，以基于牙齿颜色得到自适 应的算法，从而使得其他维度如牙结石的检测更加准确。换句话说，依据本公开内容的口腔检测方法会根据受试者自身的牙齿颜色或者牙龈颜色来设定不同的比较阈值，从而能够针对不同的受试者进行符合其自身特点的有针对性的检测，使得基于所述第二中间图片和所述比较阈值所确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例比传统方法所确定的比例更为精确有效，进而有利于后续的口腔健康状况评估。
图3示出了依据本公开内容所提出的一种口腔检测装置300，所述口腔检测装置300包括：摄像装置310，所述摄像装置310被配置用于获取口腔图片；图片处理装置320，所述图片处理装置320被配置用于对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片并且将所述第一中间图片由RGB颜色空间转换至HSV颜色空间得到第二中间图片；阈值确定装置430，所述阈值确定装置430被配置用于基于牙齿颜色确定比较阈值；以及像素比例确定装置440，所述像素比例确定装置440被配置用于基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，所述第一中间图片包括所述图片中的牙齿区域并且所述比较阈值包括牙结石比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：基于所述第二中间图片和所述牙结石比较阈值确定位于所述牙结石比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，所述第一中间图片包括所述图片中的牙龈区域并且所述比较阈值包括牙龈炎比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：基于所述第二中间图片和所述牙龈炎比较阈值确定位于所述牙龈炎比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，所述牙齿颜色通过以下方法确定：获取口腔图片；对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；将所述第一中间图片由RGB颜色空间转换至LAB颜色空间得到第三中间图片；将所述第三中间图片中的像素点和标准 颜色进行比较；以及根据比较结果确定所述牙齿颜色。
在依据本公开内容的一个实施例之中，所述标准颜色包括以下六个标准颜色值：RGBColor0＝sRGBColor(255,255,255)；RGBColor1＝sRGBColor(164,192,239)；RGBColor2＝sRGBColor(131,172,217)；RGBColor3＝sRGBColor(124,149,205)；RGBColor4＝sRGBColor(21,46,110)；以及RGBColor5＝sRGBColor(255,255,0)。
在依据本公开内容的一个实施例之中，根据比较结果确定所述牙齿颜色进一步包括：根据每个标准颜色值的权重加权求和来确定所述牙齿颜色。
在依据本公开内容的一个实施例之中，所述牙结石比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间，或者所述牙龈炎比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间。
在依据本公开内容的一个实施例之中，所述低位阈值低于所述高位阈值，并且所述牙龈炎比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,80,12])至np.array([40,235,210])，或者所述牙结石比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,30,10])至np.array([190,255,70])。
再者，本公开内容的一个实施例还提出了一种有形的计算机可读存储介质，所述存储介质包括用于执行口腔检测方法的指令，当所述指令被执行时，使得所述计算机的处理器至少用于：
获取口腔图片；
对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；
将所述第一中间图片由RGB颜色空间转换至HSV颜色空间得到第二中间图片；
基于牙齿颜色确定比较阈值；以及
基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，所述第一中间图片包括所述图片中的牙齿区域并且所述比较阈值包括牙结石比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
基于所述第二中间图片和所述牙结石比较阈值确定位于所述牙结石比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，所述第一中间图片包括所述图片中的牙龈区域并且所述比较阈值包括牙龈炎比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
基于所述第二中间图片和所述牙龈炎比较阈值确定位于所述牙龈炎比较阈值内的像素点占所述第二中间图片的像素点的比例。
在依据本公开内容的一个实施例之中，所述牙齿颜色通过以下方法确定：
获取口腔图片；
对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；
将所述第一中间图片由RGB颜色空间转换至LAB颜色空间得到第三中间图片；
将所述第三中间图片中的像素点和标准颜色进行比较；以及
根据比较结果确定所述牙齿颜色。
在依据本公开内容的一个实施例之中，所述标准颜色包括以下六个标准颜色值：
RGBColor0＝sRGBColor(255,255,255)；
RGBColor1＝sRGBColor(164,192,239)；
RGBColor2＝sRGBColor(131,172,217)；
RGBColor3＝sRGBColor(124,149,205)；
RGBColor4＝sRGBColor(21,46,110)；以及
RGBColor5＝sRGBColor(255,255,0)。
在依据本公开内容的一个实施例之中，根据比较结果确定所述牙齿颜色进一步包括：
根据每个标准颜色值的权重加权求和来确定所述牙齿颜色。
在依据本公开内容的一个实施例之中，所述牙结石比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间，或者所述牙龈炎比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间。
在依据本公开内容的一个实施例之中，所述低位阈值低于所述高位阈值，并且所述牙龈炎比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,80,12])至np.array([40,235,210])，或者所述牙结石比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,30,10])至np.array([190,255,70])。
综上所述，通过依据本公开内容的一个实施例所提供的口腔检测方法、口腔检测装置以及相应地计算机可读存储介质会根据受试者自身的牙齿颜色来设定不同的比较阈值，从而能够针对不同的受试者进行符合其自身特点的有针对性的检测，使得基于所述第二中间图片和所述比较阈值所确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例比传统方法所确定的比例更为精确有效，进而有利于后续的口腔健康状况评估。本公开内容的其他优势将在下文中进一步说明。
此外，替代地，上述方法能够通过计算机程序产品，即计算机可读存储介质来实现。计算机程序产品可以包括计算机可读存储介质，其上载有用于执行本公开内容的各个方面的计算机可读程序指令。计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备。计算机可读存储介质例如可以是但不限于电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
图4示出了依据本公开内容的一个实施例所提出的口腔检测装置400的示意性框图。应当理解，口腔检测装置400可以被实现为实现图1的口腔检测方法100或者图2中的口腔检测方法200的功能。从图4中可以看出口腔检测装置400包括中央处理单元(CPU)401(例如处理器)，其可 以根据存储在只读存储器(ROM)402中的计算机程序指令或者从存储单元408加载到随机访问存储器(RAM)403中的计算机程序指令，来执行各种适当的动作和处理。在RAM 403中，还可存储该口腔检测装置400操作所需的各种程序和数据。CPU 401、ROM 402以及RAM 403通过总线404彼此相连。输入/输出(I/O)接口405也连接至总线404。
口腔检测装置400中的多个部件连接至I/O接口405，包括：输入单元406，例如键盘、鼠标等；输出单元407，例如各种类型的显示器、扬声器等；存储单元408，例如磁盘、光盘等；以及通信单元409，例如网卡、调制解调器、无线通信收发机等。通信单元409允许该装置400通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据。
概括地将，本公开内容的第三方面提供了一种有形的计算机可读存储介质，所述存储介质包括用于执行口腔检测方法的指令，当所述指令被执行时，使得所述计算机的处理器至少用于执行依据图1的口腔检测方法100或者图2中的口腔检测方法200的功能。
上文所描述的各种方法，例如口腔检测方法100或者口腔检测方法200可由处理单元401执行。例如，在一些实施例中，口腔检测方法100或者口腔检测方法200可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元408。在一些实施例中，计算机程序的部分或者全部可以经由ROM 402和/或通信单元409而被载入和/或安装到口腔检测装置400上。当计算机程序被加载到RAM 403并由处理器CPU 401执行时，可以执行上文描述的口腔检测方法100或者口腔检测方法200中的一个或多个动作或步骤。
一般而言，本公开内容的各种示例实施例可以在硬件或专用电路、软件、固件、逻辑，或其任何组合中实施。某些方面可以在硬件中实施，而其他方面可以在可以由控制器、微处理器或其他计算设备执行的固件或软件中实施。当本公开内容的实施例的各方面被图示或描述为框图、流程图或使用某些其他图形表示时，将理解此处描述的方框、装置、系统、技术或方法可以作为非限制性的示例在硬件、软件、固件、专用电路或逻辑、通用硬件或控制器或其他计算设备，或其某些组合中实施。
虽然上面描述了本公开内容的各种示例实施例可以在硬件或专用电路中实现，但是上述用于区块链的数据处理设备既可以以硬件的形式来实现， 也可以通过软件的形式来实现，这是因为：在20世纪90年代，一个技术改进能够很容易地对该改进属于硬件上的改进(例如，对二极管、晶体管、开关等电路结构的改进)还是属于软件上的改进(例如对于方法流程的改进)。然而，随着技术的持续发展，如今的很多方法流程的改进几乎都能够通过将改进的方法流程编程到硬件电路中来实现，换句话说，通过对于硬件电路编程不同的程序从而得到相应的硬件电路结构，即实现了硬件电路结构的改变，故这样的方法流程的改进也可以被视为硬件电路结构的直接改进。因此，不能说一个方法流程的改进就不能用硬件实体模块来实现。例如，可编程逻辑器件(Programmable Logic Device：PLD)(例如现场可编程门阵列(Field Programmable Gate Array：FPGA))就是这样一种集成电路，其逻辑功能由用户对器件编程来确定。由设计人员自行编程来把一个数字系统“集成”在一片可编程逻辑器件上，而不需要请芯片制造厂商来设计和制作专用的集成电路芯片。而且，如今取代手工地制作集成电路芯片，这种编程也多半改用“逻辑编译器(logic compi1er)”软件来实现，它与程序开发撰写时所用的软件编译器相类似，而要编译之前的原始代码也得用特定的编程语言来撰写，此称之为硬件描述语言(Hardware Description Language：HDL)，而HDL也并非仅有—种，而是有许多种，如ABEL(Advanced Boolean Expression Language)、AHDL(Altera Hardware Description Language)、Confluence、CUPL(Cornell University Programming Language)、HDCal、JHDL(Java Hardware Description Language)、Lava、Lola、MyHDL、PALASM、RHDL(Ruby Hardware Description Language)等，目前最普遍使用的是VHDL(Very-High-Speed Integrated Circuit Hardware Description Language)与Verilog。本领域技术人员也应该清楚，只需要将方法流程用上述几种硬件描述语言稍作逻辑编程并编程到集成电路中，就可以很容易得到实现该逻辑方法流程的硬件电路。
用于执行本公开内容的各个方面的计算机可读程序指令或者计算机程序产品也能够存储在云端，在需要调用时，用户能够通过移动互联网、固网或者其他网络访问存储在云端上的用于执行本公开内容的一方面的计算机可读程序指令，从而实施依据本公开内容的各个方面所公开的技术方案。
综上所述，通过依据本公开内容的三个方面所提供的口腔检测方法、口腔检测装置以及相应地计算机可读存储介质会根据受试者自身的牙齿颜 色来设定不同的比较阈值，从而能够针对不同的受试者进行符合其自身特点的有针对性的检测，使得基于所述第二中间图片和所述比较阈值所确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例比传统方法所确定的比例更为精确有效，进而有利于后续的口腔健康状况评估。
以上所述仅为本公开内容的实施例可选实施例，并不用于限制本公开内容的实施例，对于本领域的技术人员来说，本公开内容的实施例可以有各种更改和变化。凡在本公开内容的实施例的精神和原则之内，所作的任何修改、等效替换、改进等，均应包含在本公开内容的实施例的保护范围之内。
虽然已经参考若干具体实施例描述了本公开内容的实施例，但是应当理解，本公开内容的实施例并不限于所公开的具体实施例。本公开内容的实施例旨在涵盖在所附权利要求的精神和范围内所包括的各种修改和等同布置。权利要求的范围符合最宽泛的解释，从而包含所有这样的修改及等同结构和功能。

Claims (27)

  1. 一种口腔检测方法，其特征在于，所述口腔检测方法包括：
    获取口腔图片；
    对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；
    将所述第一中间图片由RGB颜色空间转换至HSV颜色空间得到第二中间图片；
    基于牙齿颜色确定比较阈值；以及
    基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例。
  2. 根据权利要求1所述的口腔检测方法，其特征在于，所述第一中间图片包括所述图片中的牙齿区域并且所述比较阈值包括牙结石比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
    基于所述第二中间图片和所述牙结石比较阈值确定位于所述牙结石比较阈值内的像素点占所述第二中间图片的像素点的比例。
  3. 根据权利要求1所述的口腔检测方法，其特征在于，所述第一中间图片包括所述图片中的牙龈区域并且所述比较阈值包括牙龈炎比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
    基于所述第二中间图片和所述牙龈炎比较阈值确定位于所述牙龈炎比较阈值内的像素点占所述第二中间图片的像素点的比例。
  4. 根据权利要求1所述的口腔检测方法，其特征在于，所述口腔检测方法还包括：
    调整所述口腔图片的对比度。
  5. 根据权利要求1至4中任一项所述的口腔检测方法，其特征在于，所述牙齿颜色通过以下方法确定：
    获取口腔图片；
    对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；
    将所述第一中间图片由RGB颜色空间转换至LAB颜色空间得到第三中间图片；
    将所述第三中间图片中的像素点和标准颜色进行比较；以及
    根据比较结果确定所述牙齿颜色。
  6. 根据权利要求5所述的口腔检测方法，其特征在于，所述标准颜色包括以下六个标准颜色值：
    RGBColor0＝sRGBColor(255,255,255)；
    RGBColor1＝sRGBColor(164,192,239)；
    RGBColor2＝sRGBColor(131,172,217)；
    RGBColor3＝sRGBColor(124,149,205)；
    RGBColor4＝sRGBColor(21,46,110)；以及
    RGBColor5＝sRGBColor(255,255,0)。
  7. 根据权利要求6所述的口腔检测方法，其特征在于，根据比较结果确定所述牙齿颜色进一步包括：
    根据每个标准颜色值的权重加权求和来确定所述牙齿颜色。
  8. 根据权利要求2或3所述的口腔检测方法，其特征在于，所述牙结石比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间，或者所述牙龈炎比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间。
  9. 根据权利要求8所述的口腔检测方法，其特征在于，所述低位阈值低于所述高位阈值，并且所述牙龈炎比较阈值的所述低位阈值和所述高位 阈值从以下区间选择：np.array([0,80,12])至np.array([40,235,210])，或者所述牙结石比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,30,10])至np.array([190,255,70])。
  10. 一种口腔检测装置，所述口腔检测装置包括：
    摄像装置，所述摄像装置被配置用于获取口腔图片；
    图片处理装置，所述图片处理装置被配置用于对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片并且将所述第一中间图片由RGB颜色空间转换至HSV颜色空间得到第二中间图片；
    阈值确定装置，所述阈值确定装置被配置用于基于牙齿颜色确定比较阈值；以及
    像素比例确定装置，所述像素比例确定装置被配置用于基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例。
  11. 根据权利要求10所述的口腔检测装置，其特征在于，所述第一中间图片包括所述图片中的牙齿区域并且所述比较阈值包括牙结石比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
    基于所述第二中间图片和所述牙结石比较阈值确定位于所述牙结石比较阈值内的像素点占所述第二中间图片的像素点的比例。
  12. 根据权利要求10所述的口腔检测装置，其特征在于，所述第一中间图片包括所述图片中的牙龈区域并且所述比较阈值包括牙龈炎比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
    基于所述第二中间图片和所述牙龈炎比较阈值确定位于所述牙龈炎比较阈值内的像素点占所述第二中间图片的像素点的比例。
  13. 根据权利要求10所述的口腔检测装置，其特征在于，所述图片处理装置被配置用于调整所述口腔图片的对比度。
  14. 根据权利要求10至13中任一项所述的口腔检测装置，其特征在于，所述牙齿颜色通过以下方法确定：
    获取口腔图片；
    对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；
    将所述第一中间图片由RGB颜色空间转换至LAB颜色空间得到第三中间图片；
    将所述第三中间图片中的像素点和标准颜色进行比较；以及
    根据比较结果确定所述牙齿颜色。
  15. 根据权利要求14所述的口腔检测装置，其特征在于，所述标准颜色包括以下六个标准颜色值：
    RGBColor0＝sRGBColor(255,255,255)；
    RGBColor1＝sRGBColor(164,192,239)；
    RGBColor2＝sRGBColor(131,172,217)；
    RGBColor3＝sRGBColor(124,149,205)；
    RGBColor4＝sRGBColor(21,46,110)；以及
    RGBColor5＝sRGBColor(255,255,0)。
  16. 根据权利要求15所述的口腔检测装置，其特征在于，根据比较结果确定所述牙齿颜色进一步包括：
    根据每个标准颜色值的权重加权求和来确定所述牙齿颜色。
  17. 根据权利要求11或12所述的口腔检测装置，其特征在于，所述牙结石比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间，或者所述牙龈炎比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间。
  18. 根据权利要求17所述的口腔检测装置，其特征在于，所述低位阈值低于所述高位阈值，并且所述牙龈炎比较阈值的所述低位阈值和所述高 位阈值从以下区间选择：np.array([0,80,12])至np.array([40,235,210])，或者所述牙结石比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,30,10])至np.array([190,255,70])。
  19. 一种有形的计算机可读存储介质，所述存储介质包括用于执行口腔检测方法的指令，当所述指令被执行时，使得所述计算机的处理器至少用于：
    获取口腔图片；
    对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；
    将所述第一中间图片由RGB颜色空间转换至HSV颜色空间得到第二中间图片；
    基于牙齿颜色确定比较阈值；以及
    基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例。
  20. 根据权利要求19所述的计算机可读存储介质，其特征在于，所述第一中间图片包括所述图片中的牙齿区域并且所述比较阈值包括牙结石比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
    基于所述第二中间图片和所述牙结石比较阈值确定位于所述牙结石比较阈值内的像素点占所述第二中间图片的像素点的比例。
  21. 根据权利要求19所述的计算机可读存储介质，其特征在于，所述第一中间图片包括所述图片中的牙龈区域并且所述比较阈值包括牙龈炎比较阈值，并且其中，基于所述第二中间图片和所述比较阈值确定位于所述比较阈值内的像素点占所述第二中间图片的像素点的比例进一步包括：
    基于所述第二中间图片和所述牙龈炎比较阈值确定位于所述牙龈炎比较阈值内的像素点占所述第二中间图片的像素点的比例。
  22. 根据权利要求19所述的计算机可读存储介质，其特征在于，当所 述指令被执行时，还使得所述计算机的处理器至少用于：
    调整所述口腔图片的对比度。
  23. 根据权利要求19至22中任一项所述的计算机可读存储介质，其特征在于，所述牙齿颜色通过以下方法确定：
    获取口腔图片；
    对所述图片执行中值滤波、转灰度图和自适应阈值分割操作得到第一中间图片；
    将所述第一中间图片由RGB颜色空间转换至LAB颜色空间得到第三中间图片；
    将所述第三中间图片中的像素点和标准颜色进行比较；以及
    根据比较结果确定所述牙齿颜色。
  24. 根据权利要求23所述的计算机可读存储介质，其特征在于，所述标准颜色包括以下六个标准颜色值：
    RGBColor0＝sRGBColor(255,255,255)；
    RGBColor1＝sRGBColor(164,192,239)；
    RGBColor2＝sRGBColor(131,172,217)；
    RGBColor3＝sRGBColor(124,149,205)；
    RGBColor4＝sRGBColor(21,46,110)；以及
    RGBColor5＝sRGBColor(255,255,0)。
  25. 根据权利要求24所述的计算机可读存储介质，其特征在于，根据比较结果确定所述牙齿颜色进一步包括：
    根据每个标准颜色值的权重加权求和来确定所述牙齿颜色。
  26. 根据权利要求20或21所述的计算机可读存储介质，其特征在于，所述牙结石比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间，或者所述牙龈炎比较阈值包括至少两组分别包括高位阈值和低位阈值的阈值区间。
  27. 根据权利要求26所述的计算机可读存储介质，其特征在于，所述低位阈值低于所述高位阈值，并且所述牙龈炎比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,80,12])至np.array([40,235,210])，或者所述牙结石比较阈值的所述低位阈值和所述高位阈值从以下区间选择：np.array([0,30,10])至np.array([190,255,70])。
PCT/CN2021/119036 2020-09-18 2021-09-17 口腔检测方法、口腔检测装置以及计算机可读存储介质 Ceased WO2022057890A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP21868712.7A EP4216151A4 (en) 2020-09-18 2021-09-17 ORAL DETECTION METHOD, ORAL DETECTION APPARATUS, AND COMPUTER-READABLE STORAGE MEDIUM
US18/026,982 US12511751B2 (en) 2020-09-18 2021-09-17 Oral cavity examination method, oral cavity examination device and computer-readable storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010989252.7 2020-09-18
CN202010989252.7A CN114283107A (zh) 2020-09-18 2020-09-18 口腔检测方法、口腔检测装置以及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2022057890A1 true WO2022057890A1 (zh) 2022-03-24

Family

ID=80775922

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/119036 Ceased WO2022057890A1 (zh) 2020-09-18 2021-09-17 口腔检测方法、口腔检测装置以及计算机可读存储介质

Country Status (4)

Country Link
US (1) US12511751B2 (zh)
EP (1) EP4216151A4 (zh)
CN (1) CN114283107A (zh)
WO (1) WO2022057890A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110931132B (zh) * 2019-12-31 2022-09-30 天津市口腔医院 一种牙胚发育阶段的判断方法
CN116681780B (zh) * 2023-03-30 2025-11-18 南昌大学 基于可变分自编码器的牙齿比色方法、设备、介质和程序

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104346803A (zh) * 2013-08-05 2015-02-11 好来化工(中山)有限公司 用于对口腔组织进行分析的方法和装置以及牙科分析系统
US20190167115A1 (en) 2016-08-09 2019-06-06 Onaria Technologies Ltd. Method and system for processing an image of the teeth and gums
CN110742707A (zh) * 2018-07-23 2020-02-04 广达电脑股份有限公司 用以标示牙菌斑荧光反应区域的影像处理方法以及其电子系统
CN110751635A (zh) * 2019-10-12 2020-02-04 湖南师范大学 一种基于帧间差分和hsv颜色空间的口腔检测方法

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2006325015A (ja) * 2005-05-19 2006-11-30 Konica Minolta Photo Imaging Inc 画像処理方法、画像処理装置、撮像装置及び画像処理プログラム
CN103347436B (zh) * 2011-01-11 2016-06-22 爱德芳世株式会社 口腔内拍摄显示系统
US9870613B2 (en) * 2014-11-05 2018-01-16 Carestream Health, Inc. Detection of tooth condition using reflectance images with red and green fluorescence
DE102015208087A1 (de) * 2015-04-30 2016-11-03 Carl Zeiss Microscopy Gmbh Verfahren zum Generieren eines reflektionsreduzierten Kontrastbildes und diesbezügliche Vorrichtungen
CN105761260B (zh) * 2016-02-15 2018-09-28 天津大学 一种皮肤图像患处分割方法
CN108451501A (zh) * 2018-02-01 2018-08-28 福建师范大学 一种基于像素分析的鲜红斑痣颜色和面积评估方法
BR112020015757A2 (pt) * 2018-02-02 2020-12-08 University Health Network Dispositivos, sistemas, e métodos para visualização e remoção de tumor
CN109741336B (zh) * 2018-12-06 2021-06-01 东南大学 一种基于像素聚类与分割阈值的白癜风区域分割方法
CN110060239B (zh) * 2019-04-02 2021-05-07 广州大学 一种用于瓶子瓶口的缺陷检测方法
CN110070523B (zh) * 2019-04-02 2021-06-22 广州大学 一种用于瓶底的异物检测方法
CN110120056B (zh) * 2019-05-21 2021-08-10 闽江学院 基于自适应直方图阈值和轮廓检测的血液白细胞分割方法
CN110543837B (zh) * 2019-08-16 2022-03-15 北京航空航天大学 一种基于潜在目标点的可见光机场飞机检测方法
CN110689860B (zh) * 2019-09-29 2021-02-05 京东方科技集团股份有限公司 一种图像表示方法、装置和计算机存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104346803A (zh) * 2013-08-05 2015-02-11 好来化工(中山)有限公司 用于对口腔组织进行分析的方法和装置以及牙科分析系统
US20190167115A1 (en) 2016-08-09 2019-06-06 Onaria Technologies Ltd. Method and system for processing an image of the teeth and gums
CN110742707A (zh) * 2018-07-23 2020-02-04 广达电脑股份有限公司 用以标示牙菌斑荧光反应区域的影像处理方法以及其电子系统
CN110751635A (zh) * 2019-10-12 2020-02-04 湖南师范大学 一种基于帧间差分和hsv颜色空间的口腔检测方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4216151A4

Also Published As

Publication number Publication date
US12511751B2 (en) 2025-12-30
EP4216151A4 (en) 2024-09-25
EP4216151A1 (en) 2023-07-26
CN114283107A (zh) 2022-04-05
US20230342934A1 (en) 2023-10-26

Similar Documents

Publication Publication Date Title
CN107451969B (zh) 图像处理方法、装置、移动终端及计算机可读存储介质
CN107424198B (zh) 图像处理方法、装置、移动终端及计算机可读存储介质
CN100551081C (zh) 一种实现白平衡校正的方法及装置
CN107800966B (zh) 图像处理的方法、装置、计算机可读存储介质和电子设备
TWI696450B (zh) 資訊處理裝置、資訊處理系統、及資訊處理程式
CN110691226B (zh) 图像处理方法、装置、终端及计算机可读存储介质
CN105430361A (zh) 成像方法、图像传感器、成像装置及电子装置
WO2022057890A1 (zh) 口腔检测方法、口腔检测装置以及计算机可读存储介质
CN111311500A (zh) 一种对图像进行颜色还原的方法和装置
CN112215808B (zh) 一种生成人脸皮肤敏感图的方法及其相关装置
CN110365920A (zh) 图像处理
CN104954772A (zh) 一种应用于自动白平衡算法的图像近灰色像素选取算法
CN117132544A (zh) 一种基于深度学习和颜色空间变换的图像偏色检测方法
CN100477743C (zh) 摄像装置及其光源推断装置
CN107464225A (zh) 图像处理方法、装置、计算机可读存储介质和移动终端
CN115471571A (zh) 标定方法、图像处理方法、装置、存储介质与电子设备
CN101312494A (zh) 计算相机响应曲线及合成大动态范围图像的方法及其装置
JPH1166301A (ja) カラー画像分類方法及び装置及びこの方法を記録した記録媒体
CN113724235B (zh) 镜下环境改变条件时半自动化的Ki67/ER/PR阴性、阳性细胞计数系统及方法
CN106791744A (zh) 投影机画面高动态范围处理系统及其处理方法
CN110490861A (zh) 一种用于黄板上蚜虫的识别方法及系统
US20230363644A1 (en) Oral cavity detection method, oral cavity detection device, and computer-readable storage medium
CN109040598A (zh) 图像处理方法、装置、计算机可读存储介质和电子设备
HK40095953A (zh) 口腔检测方法、口腔检测装置以及电脑可读储存介质
KR101039404B1 (ko) 이미지 시그널 프로세서, 스마트폰 및 자동 노출 제어 방법

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21868712

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)
NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2021868712

Country of ref document: EP

Effective date: 20230418

WWG Wipo information: grant in national office

Ref document number: 18026982

Country of ref document: US