JPH0367261A - Cutout mask creation system - Google Patents

Abstract

PURPOSE:To efficiently execute clipping processing and to obtain a clipping line whose quality is excellent by executing clipping with the aid of ocmbining two kinds of automatic and manual clipping means and selecting a processing means according to the state of a contour line. CONSTITUTION:A prescribed automatic ally clipping area A including the contour of a pattern, for example, a rectangle or a polygon,is specified on an image 2. The program processing by the classification of density considering the changing axis of the density is executed for the inside of the area, for example. Then, the automatic clipping is executed. Besides, a stripe area B including the contour of the objective iamge 2 is specified while tracing it by a spot-like brush which is shown by a code C and the program processing is executed for it in real time. Then, the full-automatic clipping is executed. Besides, the contour of the objective image 2 is specified by an operator with the aid of using the brush, for example, and the manual clipping is executed along the specified contour line. Then, the manual clipping is executed by specifying with the aid of one segment (l). By combining both means in such a manner, the clipping processing is efficiently executed. Besides, since the proper processing method can be selected according to the state of the contour line, the clipped image having the excellent quality is obtained.

Description

[Detailed description of the invention]

[Field of Industrial Application] The present invention relates to an improvement in a cutout mask creation system for creating a printing plate film by extracting a background part from a color image. [Prior art] When cutting out and using only the necessary part from a photographic manuscript, for example, trimming a square photographic manuscript into a heart shape and using it, or extracting only the object from the photographic manuscript. ,
When a photo is to be combined with other photo originals and used, a cutting process is generally performed. In other words, you can use a tracing machine to trace the outline of the required image on layout paper and specify the cutout, or cover the photo manuscript with tracing paper, draw the outline of the necessary part, and then cross out the unnecessary part with diagonal lines. to specify the crop,
According to such clipping specifications, a clipping mask or the like is created and composition is executed. However, printed matter does not only consist of a single color area as mentioned above, but also includes gradual color changes, negative and positive films for color photographs, etc. When creating a film version by extracting only a specific object, such as a person or furniture, the area to be cut out overlaps with areas with different brightness, saturation, and hue, so the above method cannot produce a faithful image. Film version cannot be created automatically. In the case of a color film original, the operator creates a mask corresponding to the cutout area by projecting the film image, and then overlaps the mask with the film original to create the film version of the desired color original ( Y, M,
, C, Bk plates), the complexity of the film original image significantly reduces the efficiency of film plate creation and significantly increases the number of days required for the printing process. There was a case. Conventionally, a film image is converted into an image signal, projected onto a display, and an operator accurately specifies the outline of the image to be cropped using a pointing tool such as a mouse or cursor, thereby creating a cropping line (for example, a cropping vector). ) is known. However, there is a problem in that it takes an extremely long time for the operator to designate the entire outline of the image to be cropped using a cursor or the like, which places a heavy burden on the operator. To solve this problem, there are methods that allow the operator to automatically extract cutout lines by specifying the area to be masked, such as the color elements that make up the background in the image, using a cursor, A method has been considered in which an operator specifies a part of the area that is considered to be a background area, finds the density change axis of the background part, and automatically extracts a cutout line by density classification that takes the density change axis into consideration. However, when the target image is an object, there are frayed hairs, cases where the substance part has the same color elements as the background part, cases where the outline of the substance part is blurred by shadows, etc.
Depending on the nature of the image, there may be objects that cannot be cut out effectively with fully automatic cropping, and if you try to crop these types of objects fully automatically, the calculation area will be enormous, the processing time will be extremely long, and the cropping performance will be limited. However, this method has a problem in that the contour line is unstable and the contour line cannot always be extracted accurately. OBJECTS OF THE INVENTION The present invention has been made to solve the above-mentioned conventional problems, and it is possible to quickly create cutout lines, and
The purpose of the present invention is to provide a cutout mask creation system capable of extracting contour lines more accurately than in a fully automatic system.

[Means to achieve the task]

The present invention provides a cutout mask creation system for extracting a predetermined portion from an input image, in which a predetermined area including the outline of the image to be cut out can be specified for the input image, and the inside of the specified area is automatically A means for program-processing and cutting out along the contour; and a means for specifying a band-shaped area including the contour of the target image, and automatically program-processing the inside of the designated area and cutting out along the contour. means for specifying an arbitrary contour and cutting out along the contour; and means for specifying an arbitrary contour as a line segment and cutting out along the contour. By doing so, the above-mentioned problem has been achieved. [Operation] The present invention was made by focusing on the fact that even if the target image is the same, there are areas where automatic cropping is possible and areas where automatic cropping is difficult. In the present invention, for example, as shown in FIG.
2, a predetermined rectangular or polygonal automatic clipping area A including the outline of the picture is designated, and the inside of the area is automatically cropped by program processing based on density classification taking into consideration the axis of density change, for example. The automatic clipping area mA can be specified, for example, by setting the reference point of the area A to the upper left corner in advance,
This can be done by specifying the position of the reference point P on the picture @2 with a cursor. Further, as shown in FIG. 1 (8), for example, a band-shaped region B including the outline of the target image 2 is specified by tracing it with a spot-shaped brush indicated by the symbol C, and program processing is performed in real time to perform fully automatic cutting. Depending on the condition of the contour line, it may not be possible to obtain good results with automatic cropping, so the operator may specify the contour of the target image 2 with a brush, for example, as shown in FIG. 1(C).
Cutting (manual cutting) is performed along the specified contour line. By using a brush to specify the contour, the operator can precisely designate the contour of the target image to be cropped, regardless of which curve the contour is. In addition, in FIG. 1(C), the state in which the outline is traced with a brush with a circular tip is shown by reference numerals. The cutout line can be on the background side or on the picture side along the envelope of the circle at the tip of the brush. In addition, the outline of the target image is specified by at least one line segment (as shown in Fig. 1(D)) and cutout (manual cutout) is performed.
You can easily and accurately cut out straight lines. In the present invention, as described above, since the cutting can be performed using two automatic cutting means and two manual cutting means, the cutting process can be performed efficiently by combining each means. Furthermore, since an appropriate processing method can be selected depending on the condition of the contour line, a high-quality cutout image can be obtained. Further, noises generated by automatic clipping can be easily corrected by manual clipping. Therefore, it is possible to quickly create a cutout image, and moreover, the cutout image can be cut out more accurately than in the case of a fully automatic method. [Examples] Examples of the present invention will be described in detail below with reference to the drawings. This embodiment is a cutout mask creation system configured as shown in FIG. In FIG. 2, reference numeral 1 denotes a layout table, on which a color original 2 (with a uniform background) such as a color film, for example, is placed. A color scanner 3 optically reads the image of the color original 2, converts the RGB signals into Y, M, C, and 8 signals and stores them in the image memory 4. Reference numeral 5 denotes an image processing controller section composed of a computer or the like, which includes principal component calculation means 5a, one-degree average/covariance calculation means 5b, discriminant function calculation means 5C1, dorsal part extraction means 5d,
It is composed of a smoothing processing means 5e, a high resolution processing means 5, etc., and is activated based on a clipping processing program stored in a program memory 10. The principal component calculating means 5a calculates image data (C, M, Y) of a training area 11a in a uniform background part of a preset automatic clipping area, for example, the upper left corner of the automatic clipping area 11 (see FIG. 3). is sampled and its principal components are calculated to obtain the axis of density change (principal component axis) as shown in Fig. Even when the shadow of the real part is captured, changes in the density distribution can be predicted. Of course, it is also possible to set the training area at other locations within the background part. From the second and third principal component values of each pixel obtained by the component analysis, the density average value and covariance value of the training area 11a are determined in order to perform density clustering by the maximum likelihood method.The discriminant function calculation means 5C is , a discrimination function for clustering the entire target image into a background part and a substance part (a part other than the background part) by substituting the density average value and covariance value calculated by the density average/covariance calculating means 5b into a normal distribution function. Then, the color image data stored in the image memory 4 is read out and substituted into the discrimination function to calculate the density distance data with respect to the training area. This is because it is assumed that when an image is uniform, it follows a normal distribution. If the density distance data is within a predetermined value, the background face image data is determined from the color image data stored in the image memory 4. The smoothing processing means 5e extracts the background part extraction means 5.
The background face image data extracted in step d is smoothed as described below. The high-resolution processing means 5f pseudo-increases the resolution of the raster data background image data smoothed by the smoothing processing means 5e by interpolating between pixels, thereby creating a high-quality image. It is used for processing. That is, this high resolution processing means 5f includes:
A run-length processing unit 50g that converts the background image data into run-length data, an enlargement processing unit 50h that enlarges the run-length data, and a connection relationship search unit 501 that searches for connection relationships between the enlarged run-length data. , and a subdivision processing unit 50j that subdivides a predetermined number of edges of a contour connecting arbitrary two points based on the relationship of the retrieved enlarged run length data. In FIG. 2, 6 is a display for the operator to designate an automatic cropping area, check/correct the automatically extracted cropping mask, manually crop, etc., and 7 is an input section that allows the operator to move the keyboard 7a and the cursor on the display 6. It is composed of a pointing device 7b for movement, and inputs instructions to the image processing controller section 5, such as command position data necessary for cropping processing and execution of painting within a closed area. 8 is a layout scanner serving as a film output means;
While referring to the background cutout mask data outputted from the noise removing means 5h, the color image data other than the background portion is read out for each plate color from the color image data stored in the image memory 4, and is transferred to the printing film plate 9. Cut out and output. FIG. 3 is a state transition diagram illustrating automatic clipping processing. In FIG. 3, reference numeral 11 indicates an automatic clipping area, and 11a indicates its training area. Further, 12 indicates background extracted image data, which corresponds to the background extracted image data extracted by the background extracting means 5d shown in FIG. In FIG. 3, N+ and N2 are noise components, which correspond to data extracted as non-uniform density regions generated by image processing calculations. 13 is smoothing data, smoothing processor FI
! 5e is the noise component N1. N2 corresponds to, for example, removing adjacent pixel data using predetermined matrix data. Reference numeral 14 indicates high-resolution data, in which the high-resolution processing means 5t performs run-length processing on the smoothing data to increase the resolution in a pseudo manner. Reference numeral 17 denotes an automatically cut out image, which is combined with the manually cut out image and exposed onto the printing film plate 9 shown in FIG. When inputting the color original 2 is instructed by the pointing device 7b, the color scanner 3 starts reading the color original 2, and stores the read color image data in the image memory for each plate color (yellow, magenta, cyan, black). 4 in sequence. When this writing is completed, the color image data read out from the image memory 4 is displayed on the display 6. The training area 11a is formed by automatically cutting out the area 11 in advance.
is set at a predetermined position in the background portion of the image, for example, at the upper left corner of the automatic cropping area 11. Furthermore, this training area 1
1a can be changed using the pointing device 7b. The principal component calculation means 5a operates in this training area 11a.
Sample the image data (C, M, Y) of the part,
As shown in FIG. 4, this image data is subjected to principal component analysis in order to determine the direction of change in density. This allows cases where the background part of the image data has a gradation,
Changes in density distribution can be predicted even when the shadow of the real body part is captured. When extracting the background part, the second and third principal component values of each pixel obtained by this principal component analysis are passed to the maximum likelihood method. In the maximum likelihood method, first, the concentration average/covariance calculation means 5b
is the second of each pixel in the training area 11a,
The concentration average value and covariance value are calculated from the third principal component value. Next, the discriminant function calculating means 5C substitutes the density average value and covariance value of the training area 11a into a normal distribution function, and determines a discriminant function for clustering the automatically cut out region into a background part and a real part. Furthermore, the discriminant function calculation means 5C substitutes each pixel into this discriminant function and computes density distance data with respect to the training area. Next, the background extracting means 5d extracts background extracted image data 12 by determining whether the calculated density distance data is smaller than pre-stored determination distance data. Since the maximum likelihood method statistically processes the --like parts of the image in this way, the background part can be extracted stably. The background contour portion of the extracted background image data 12 is smoothed by the smoothing processing means 5e, and smoothed data 13 is generated. Next, high resolution processing means 5r1. : The generated smoothing data 13 is compressed to create run-length data, and the run-length data is expanded and subdivided and subjected to high-resolution processing to generate high-resolution data 14. For example, the procedure proposed by the applicant in Japanese Patent Laid-Open No. 63-64179 can be used to create the run length data. Next, the operator confirms and corrects the automatically extracted and high-resolution automatically cutout area on the display 6, and combines it with the manual cutout line to determine a background cutout mask. The determined background section cutout mask data (high resolution data 16) is output to the layout scanner 8, and according to this, the layout scanner 8 refers to the background section cutout mask data and scans the color image data stored in the image memory 4. Color image data corresponding to the outside of the background area (
The cutout images 15) are read out, and cut out and exposed for each plate on the printing film plate 9. Next, with reference to FIGS. 5 to 8, a smoothing process based on fat expansion and contraction by the smoothing process means 5e shown in FIG. 3 will be described. FIG. 5 is a schematic diagram illustrating expansion of contour pixels by the smoothing processing means 5e shown in FIG. 1. In the figure, 21 is a judgment pixel pattern, for example, a target pixel 21a
8 neighboring pixels adjacent to the target pixel 21a are searched, and the target pixel 21a is
1" (black pixel) and "O" (white pixel). 2
2 is a fat swelling treatment pattern, and if even one of the 8 neighboring pixels of the judgment pixel pattern 21 is "1", the target pixel 21a is "1".
1'' (indicated by diagonal lines), corresponding to the inflated state. FIG. 6 is a schematic diagram illustrating contraction of contour pixels by the smoothing processing means 5e shown in FIG. In the figure, 31 is a judgment pixel pattern, for example, a target pixel 31a
1. :Search the 8 neighboring pixels and select the target pixel 31.
Determine rlJ rOJ of a. 32 is a contraction processing pattern, which corresponds to a contracted state in which the target pixel 31a is formed into rOJ when even one of the eight neighboring pixels of the determination pixel pattern 31 is rOJ. For example, when line drawing image data 41a in which the outline of the line drawing includes a convex notch as shown in FIG. 7 is retrieved, the judgment pixel pattern 31 shown in FIG. To perform a contraction scan to generate contraction image data 41b, and to perform expansion processing on this contraction image data 41b, based on the smoothing processing program, after the smoothing processing means 5e is set to the determination pixel shown in FIG. Expansion scanning is performed using pattern 21 to generate notch-removed image data 41G. On the other hand, when line drawing image data 42a in which the outline of the line drawing includes a concave notch as shown in FIG. 8 is retrieved, the judgment pixel pattern 21 shown in FIG. In order to perform an expansion scan to generate the expanded image data 42b and perform a contraction process on the expanded image data 42b, the smoothing processing means 5e performs the determination shown in FIG. 6 based on the smoothing processing program. Contraction scanning is performed using the pixel pattern 31 to generate notch-removed image data 42c. In addition,
In this embodiment, this processing is performed on the entire image in the order of expansion and contraction. The high-resolution processing by the high-resolution processing means 5f will be explained with reference to the schematic diagram of FIG. 9. In Figure 9 (A>), 43 is the run length date,
The number is the column number.
) is shown. 43a is a run length value, which represents the run length data 43 by a column number. Reference numeral 44 in FIG. 9(B) is enlarged run-length data, which is data obtained by enlarging the run-length data 43, for example, twice in the vertical and horizontal directions. 44a is a run length value, which represents the enlarged run length data 44 by a column number. 45 in FIG. 9(C) is the enlarged run length data 4.
The run length data obtained by subdividing 4 is shown. 45a is a run length value that represents the segmented run length data 45 using column numbers. As shown in FIGS. 9(A) to 9(C), the run length processing unit 500 generates run length data 43,
A run length value 43a is obtained. For these data, the enlargement processing unit 50h converts the data 43 into two
Enlargement processing is performed to generate enlarged run length data 44. This results in a run length value of 44ah<m. Next, the connection relationship search means 50i determines the run length value 4.
A connection relation search is performed for 4a to generate prescribed data. This specified data includes line elements (for example, 13-13-11...
). Once these specified data are obtained, the specified data is subdivided and corrected by the subdivision processing unit 50j to generate subdivided run length data 45 and obtain its run length value 45a. In this way, a high resolution enlarged image is obtained. Next, the procedure of the clipping process according to the present invention will be explained with reference to FIG. In the cutting process according to the present invention, first, Obere, -
Yu instructs and starts image reading of the color image 2 using the pointing device 7b. When started,
In step 110, the color scanner 3 reads the color original 2 for each plate color, and inputs and registers the read color image data to the image memory 4 for each plate color. Next, in step 112, when an image display command is specified, the color image data read from the image memory 4 is displayed on the display 6. Next, in step 114, the operator selects an appropriate cutting method for each contour while viewing the display 6. Then, according to the selected approach, steps 116A-
Perform automatic and manual cropping with 116D. That is, when the region specified clipping of a predetermined range is selected, in step 116A, the operator cuts a predetermined, for example, rectangular or polygonal region near the outline of the target image, as shown in No. 16 (A) above. Specify the area and automatically cut out the background inside that area using program processing. If band-shaped region cutting is selected, in step 116B, the operator specifies a band-shaped region by tracing around the outline of the target image with, for example, a spot brush, as shown in FIG. 1 <8). This allows for automatic cropping in real time using program processing. After automatic cropping is performed in steps 116A and 1116B, the operator manually corrects the cropped image as necessary while monitoring the cropped image displayed on the display 6 in steps 118A and 118B. Also, if a brush cutout is selected, step 116
At C, the operator cuts out an arbitrary outline of the target image by instructing it with a brush. In this case, the area to be specified with the brush can be either outside (background area) or inside (image side) of the outline to be cut out.Also, the area to be specified with the brush can be cut along the envelope of the circle at the tip of the brush. If manual cropping using lines is selected, in step 116D, the operator specifies the portion of the image outline to be cut using at least one line segment, connects the line segments, and cuts the image. Cutting out by minutes allows you to easily and accurately cut out a straight line where you want to make a straight line.Next, in step 120, it is determined whether the entire contour has been cut out.If it is determined that the entire contour has been cut out, step In step 122, a background image mask is created based on the cutout lines. Next, in step 124, the background image mask is subjected to smoothing processing and high resolution processing. Next, in step 126, the layout scanner 8 creates a background image mask based on the processed background image. While referring to the mask, the color image data of the plate color gil stored in the image memory 4 is read out, and a color image other than the background part (cutout image) is exposed and output for each plate color onto the printing film plate 9. In the embodiment, the case where the color original 2 is input from the color scanner 3 has been explained, but even if the color document 2 is input from the input drum (not shown) of the layout scanner 8,
It is clear that similar processing can be performed. Furthermore, in the above embodiment, automatic clipping was performed based on density classification that took into account the axis of change in density, so even if the brightness and hue changed, it was possible to effectively extract background areas with gradations and shadows. However, the automatic clipping method is not limited to this. Furthermore, in the above embodiment, smoothing processing and high resolution processing are applied to the background mask area data, and this processing is performed as necessary, but if a cropped image of sufficient quality can be obtained, this processing is Processing can be omitted. Further, as a means for performing high resolution processing, a processing means 5t that uses run length processing is shown, but the means for performing the processing is not limited to this, and high resolution processing may be performed using other processing methods without performing run length processing. can be applied. [Advantageous Effects of the Invention 1] As explained above, according to the present invention, the cutting is performed automatically and manually by combining two types of cutting means, so that the cutting process can be performed efficiently. Furthermore, since the processing means can be selected depending on the state of the contour line, high-quality cutout lines can be obtained. Further, excellent effects such as noise generated by automatic clipping can be easily corrected by manual clipping can be obtained.

[Brief explanation of drawings]

FIG. 1 is a plan view for explaining automatic and manual cutting processes for explaining the present invention, and FIG. 2 shows the configuration of a cutting mask creation system according to an embodiment of the present invention. A block diagram, FIG. 3 is a state transition diagram explaining the automatic cropping process in the above embodiment, and FIG. 4 is a two-dimensional histogram of the training area and lines showing the principal component axes to explain the automatic cropping method. 5 is a schematic diagram illustrating engraving of contour pixels by the smoothing processing means of the embodiment shown in FIG. 2; FIG. 6 is a schematic diagram illustrating contraction of contour pixels; FIG. FIG. 8 is a schematic diagram illustrating the smoothing processing state; FIGS. 9(A) to (C) are schematic diagrams illustrating high resolution processing by the high resolution processing means of the embodiment; FIG. 1 is a flowchart showing a clipping processing procedure in the embodiment. 2... Color document, A, B, 11... Automatic clipping area, 3... Color scanner, 4... Image memory, 5... Image processing controller section, 5a... Principal component calculation means , 5b... Concentration average/covariance calculation means, 5C... Discrimination function calculation means, 5d... Background extraction means, 5f... High resolution processing means, 6... Display, 9... Printing film version, 10...Program memory, 11a...Training area, 12...Background part extracted image data.

Claims (1)

[Claims] (1) In a cropping mask creation system for extracting a predetermined part from an input image, it is possible to specify an area including the outline of the image to be cropped for the input image, and the inside of the specified area is automatically processed by a program. and a means for making it possible to specify a band-shaped area including the outline of the target image, automatically processing the inside of the specified area with a program, and cutting out the image along the outline. means for specifying an arbitrary contour of the target image and cropping it along the contour; and means for specifying an arbitrary contour of the target image as a line segment and cropping it along the contour. A cutout mask creation system comprising: means.