CN112101112B - A visual recognition method and system for watch time - Google Patents

A visual recognition method and system for watch time Download PDF

Info

Publication number
CN112101112B
CN112101112B CN202010815672.3A CN202010815672A CN112101112B CN 112101112 B CN112101112 B CN 112101112B CN 202010815672 A CN202010815672 A CN 202010815672A CN 112101112 B CN112101112 B CN 112101112B
Authority
CN
China
Prior art keywords
watch
hand
tray
time
module
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.)
Active
Application number
CN202010815672.3A
Other languages
Chinese (zh)
Other versions
CN112101112A (en
Inventor
荆江波
王子焘
刘宏
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.)
Shenzhen Feiyada Precision Technology Co ltd
Feiyada Precision Technology Co ltd
Original Assignee
Shenzhen Feiyada Precision Technology Co ltd
Feiyada Precision Technology Co 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 Shenzhen Feiyada Precision Technology Co ltd, Feiyada Precision Technology Co ltd filed Critical Shenzhen Feiyada Precision Technology Co ltd
Priority to CN202010815672.3A priority Critical patent/CN112101112B/en
Publication of CN112101112A publication Critical patent/CN112101112A/en
Application granted granted Critical
Publication of CN112101112B publication Critical patent/CN112101112B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/70Determining position or orientation of objects or cameras
    • G06T7/73Determining position or orientation of objects or cameras using feature-based methods
    • G06T7/74Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/44Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Electromechanical Clocks (AREA)
  • Electric Clocks (AREA)

Abstract

一种手表时间的视觉识别方法及系统。所述视觉识别方法包括如下步骤:步骤S1、在用于放置手表的由透光材料制成的托盘上固定分别代表X轴和Y轴的第一定位条和第二定位条,所述第一定位条和所述第二定位条垂直连接;步骤S2、将手表以表盘朝上的方式放置在所述托盘上,并使所述第一对位部和所述第二对位部分别贴合所述第一定位条和所述第二定位条;步骤S3、布置在托盘正上方的摄像模块获取手表的正面图像,并将所述正面图像发送至与所述摄像模块信号连接的处理模块;步骤S4、所述处理模块识别所述正面图像中的时针、分针、秒针以及时针、分针、秒针的位置,从而识别所述手表的时间。所述视觉识别方法具有基准稳定、识别率高、兼容性好的优点。

A visual recognition method and system for watch time. The visual recognition method includes the following steps: Step S1, fixing a first positioning bar and a second positioning bar representing the X-axis and the Y-axis respectively on a tray made of a light-transmitting material for placing a watch, and the first positioning bar and the second positioning bar are vertically connected; Step S2, placing the watch on the tray with the dial facing upward, and making the first alignment part and the second alignment part respectively fit the first positioning bar and the second positioning bar; Step S3, a camera module arranged directly above the tray acquires a front image of the watch, and sends the front image to a processing module connected to the camera module signal; Step S4, the processing module identifies the hour hand, minute hand, second hand and the positions of the hour hand, minute hand and second hand in the front image, thereby identifying the time of the watch. The visual recognition method has the advantages of stable reference, high recognition rate and good compatibility.

Description

Visual identification method and system for watch time
Technical Field
The invention relates to the technical field of watch manufacturing, in particular to a watch time visual identification method and a watch time visual identification system.
Background
The composite watch integrates the advantages of a traditional mechanical watch and an emerging intelligent watch, namely, the intelligent watch is implanted into the mechanical watch, the mobile phone application App corresponding to the watch issues time information to the intelligent watch through Bluetooth, and the intelligent watch is intelligent by controlling the rotor to rotate through a motor so as to adjust the hour hand and the minute hand.
Because the composite watch needs to combine the mechanical watch and the intelligent module, the requirements on the aspects of movement, assembly and the like are very high, the situation that the time of the watch needle is inaccurate and the deviation is large often occurs after the assembly is completed, and in order to prevent the unqualified product from flowing into the market, the user experience is influenced and the time precision of the watch needs to be detected.
In the process of detecting the time precision of the watch, the current positions of the hour hand, the minute hand and the second hand of the watch need to be identified, the current mode is that the hour hand, the minute hand and the second hand are identified through the characteristics of the watch hand after the front picture of the watch is directly captured through a lens, and the center of the watch and the 12H-position reference (namely the position of 12 points in a dial) are determined through the appearance of the watch. The current problems are: 1) The distinction of the hour hand, the second hand and the minute hand is frequently wrong; 2) The compatibility of the watch with different styles is poor, and when the shape, the color and the like of the watch dial, the pointer and the like are changed, the recognition rate is greatly reduced or the watch cannot be recognized; 3) The positioning reference is unstable, the accuracy is low, and the consistency and the accuracy of the test result are low.
Disclosure of Invention
The invention aims to solve the technical problem of providing a visual recognition method for watch time, which has stable reference, high recognition rate and good compatibility.
Another technical problem to be solved by the invention is to provide a visual recognition system, through which the visual recognition method is realized, so as to accurately recognize the vision of the watches with different styles.
In order to solve the technical problems, the technical scheme adopted by the invention is to provide a visual recognition method of watch time, wherein the watch comprises a watch case and a dial plate arranged in the watch case, and the outer side of the watch case is provided with a first alignment part corresponding to the 12-time position of the dial plate and a second alignment part corresponding to the 3-time position of the dial plate; the visual recognition method comprises the following steps:
s1, fixing a first positioning strip and a second positioning strip which respectively represent an X axis and a Y axis on a tray made of a light-transmitting material and used for placing a watch, wherein the first positioning strip and the second positioning strip are vertically connected;
S2, placing the watch on the tray in a dial-up mode, and enabling the first alignment part and the second alignment part to be respectively attached to the first positioning strip and the second positioning strip;
S3, a camera module arranged right above the tray acquires a front image of the watch and sends the front image to a processing module in signal connection with the camera module;
Step S4, the processing module identifies the positions of the hour hand, the minute hand, the second hand and the hour hand, the minute hand and the second hand in the front image, so that the time of the watch is identified.
In the visual recognition method for watch time provided by the invention, the processing module is pre-stored with the appearance characteristic standard values of the hour hand, the minute hand and the second hand of the watch; the step S4 includes the steps of:
Step S41, identifying a pointer in the front image;
Step S43, drawing each pointer to obtain an appearance characteristic identification value of each pointer;
And S44, comparing the appearance characteristic identification value of each watch hand with appearance characteristic standard values of the hour hand, the minute hand and the second hand corresponding to the watch hands of the watch, wherein the watch hand with the appearance characteristic identification value matched with the appearance characteristic standard value of the hour hand is judged to be the hour hand of the watch, the watch hand with the appearance characteristic identification value matched with the appearance characteristic standard value of the minute hand is judged to be the minute hand of the watch, and the watch hand with the appearance characteristic identification value matched with the appearance characteristic standard value of the second hand is judged to be the second hand of the watch.
In the visual recognition method for watch time provided by the invention, the appearance characteristic standard value comprises a gauge needle length standard value, a gauge needle width standard value and a gauge needle contour standard value; the appearance characteristic identification value comprises a pointer length identification value, a pointer width identification value and a pointer profile identification value; and the processing module recognizes the outline of the pointer in a multipoint curve fitting mode to obtain pointer outline recognition values of the pointers.
In the method for visually identifying watch time provided by the invention, the step S4 further comprises the following steps:
S42, analyzing the number of the identified hands; if the number of hands is three, go to step S42; if the number of the gauge pins is not three, the identification is judged to be failed, and the step S41 is skipped.
In the method for visually identifying watch time provided by the invention, the step S4 further comprises the following steps:
step S45, analyzing whether the length of the identified hour hand is the shortest one of the three hands and whether the width of the identified second hand is the narrowest one of the three hands; if yes, confirming that the identification is correct; if not, judging that the identification is wrong, and jumping to the step S41.
In the method for visually identifying watch time provided by the invention, the step S4 further comprises the following steps:
step S46, identifying the 3-time position of the dial in the front image, and respectively confirming the positions of the three identified hands by taking the 3-time position of the dial as a reference.
In the visual recognition method of watch time provided by the invention, the visual recognition method further comprises a step SA implemented between the step S2 and the step S3;
Step SA, the upper light emitting module arranged above the tray and the lower light emitting module arranged below the tray radiate light towards the watch on the tray.
In order to solve the other technical problem, the technical scheme adopted by the invention provides a visual recognition system of watch time, wherein the watch comprises a watch case and a dial plate arranged in the watch case, and the outer side of the watch case is provided with a first alignment part corresponding to the 12-time position of the dial plate and a second alignment part corresponding to the 3-time position of the dial plate; the visual recognition system includes:
The watch comprises a tray made of a light-transmitting material and used for placing a watch, wherein a first positioning strip and a second positioning strip which respectively represent an X axis and a Y axis are fixed on the tray, and the first positioning strip is vertically connected with the second positioning strip;
a camera module arranged right above the tray;
the processing module is in signal connection with the camera module;
the camera module is used for acquiring a front image of the watch placed on the tray and sending the front image to the processing module;
The processing module is used for identifying the positions of the hour hand, the minute hand, the second hand and the hour hand, the minute hand and the second hand in the front image, so as to identify the time of the watch.
In the watch time visual recognition system provided by the invention, the visual recognition system further comprises an upper light-emitting module and a lower light-emitting module; the upper light emitting module is arranged between the camera module and the tray; the lower light emitting module is arranged below the tray; the upper light-emitting module and the lower light-emitting module are both used for irradiating light rays towards the watch on the tray.
In the watch time visual recognition system provided by the invention, the middle part of the upper light-emitting module is provided with the through hole, and the camera shooting module is aligned with the through hole of the upper light-emitting module.
In the watch time visual recognition system provided by the invention, the camera module is a high-definition camera, and the processing module is a computer.
The implementation of the invention can achieve the following beneficial effects:
1. In the visual identification method, when the watch is placed on the tray, the first positioning strip and the second positioning strip which respectively represent the X axis and the Y axis are used for positioning, the watch is placed on the tray in a way that the dial faces upwards, and the first alignment part and the second alignment part are respectively attached to the first positioning strip and the second positioning strip, so that the position and the angle of the watch are positioned, the identification difficulty of the watch needle and the position of the watch needle is reduced, and meanwhile, the improvement of the identification accuracy is facilitated.
2. In the visual identification method, the processing module identifies the outline of the pointer in a multipoint curve fitting mode to obtain the pointer outline identification value of each pointer, so that the visual identification method can perform time identification on watches with arc-shaped and special-shaped outline of the pointer, namely, the visual identification method has high compatibility.
3. In the visual recognition method, the features of the narrowest second hand and the shortest hour hand are combined to distinguish the hour hand, the minute hand and the second hand, so that the accuracy of time recognition of the watch is improved.
Drawings
For a clearer description of an embodiment of the invention or of a technical solution in the prior art, the drawings that are required to be used in the description of the embodiment or of the prior art will be briefly described, it being obvious that the drawings in the description below are only embodiments of the invention, and that other drawings can be obtained, without inventive effort, by a person skilled in the art from the drawings provided:
fig. 1 is a flowchart illustrating steps of a visual recognition method according to a first embodiment of the present invention;
Fig. 2 is a schematic structural diagram of a visual recognition system according to a second embodiment of the present invention;
Fig. 3 is a schematic view of a wristwatch suitable for use with the present invention.
Reference numerals in the detailed description indicate:
Image pickup module 1 Tray for holding food 3
Processing module 6 Upper light-emitting module 2
Lower light emitting module 5 Support frame 7
Watch with a watch body 8 First positioning strip 41
Second positioning strip 42 A first alignment part 82
A second alignment part 83
Detailed Description
In order that the invention may be understood more fully, the invention will be described with reference to the accompanying drawings. Exemplary embodiments of the invention are illustrated in the accompanying drawings. The invention may, however, be embodied in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.
The terms including ordinal numbers such as "first", "second", and the like used in the present specification may be used to describe various constituent elements, but these constituent elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, a first component may be termed a second component, and, similarly, a second component may be termed a first component, without departing from the scope of the present invention.
Example 1
The implementation provides the visual recognition method for the time of the watch 8, which has stable reference, high recognition rate and good compatibility.
First, the wristwatch 8 according to the present invention includes a case and a dial placed inside the case, and the case has a first alignment portion 82 corresponding to the 12-time position of the dial and a second alignment portion 83 corresponding to the 3-time position of the dial on the outside.
In this embodiment, the first alignment part 82 is a pair of block-shaped lugs (see fig. 3) connected to the outer sides of the watch case, and the 12-time position of the dial is located exactly in the middle of the pair of lugs, that is, the line connecting the 12-time position of the dial and the centers of the pair of lugs is perpendicular to the X-axis. The second alignment part 83 is a crown connected to the outside of the watch case (see fig. 3), and the 3-time position of the dial is exactly aligned with the crown, that is, the line connecting the 3-time position of the dial and the crown is perpendicular to the Y axis.
In some other embodiments, the first alignment portion 82 may be an elongated ear connected to the outside of the case, and a line connecting the center of the ear to the position of the dial 12, i.e., the position of the dial 12 and the center of the ear is perpendicular to the X axis.
In this embodiment, the visual recognition method includes the following steps:
Step S1, fixing a first positioning strip 41 and a second positioning strip 42 which respectively represent an X axis and a Y axis on a tray 3 which is made of a light-transmitting material and is used for placing a watch 8, wherein the first positioning strip 41 and the second positioning strip 42 are vertically connected;
Step S2, placing the wristwatch 8 on the tray 3 with the dial facing upward, and attaching the first positioning portion 82 and the second positioning portion 83 to the first positioning bar 41 and the second positioning bar 42, respectively;
step S3, the camera module 1 arranged right above the tray 3 acquires a front image of the watch 8 and sends the front image to the processing module 6 in signal connection with the camera module 1;
Step S4, the processing module 6 identifies the position of the hour hand, minute hand, second hand, and hour hand, minute hand, second hand in the front image, thereby identifying the time of the wristwatch 8.
In the step S2, when the wristwatch 8 is placed on the tray 3, the first positioning bar 41 and the second positioning bar 42, which respectively represent the X axis and the Y axis, are used to perform positioning, that is, the wristwatch 8 is placed on the tray 3 with the dial facing upward, and the first positioning portion 82 and the second positioning portion 83 are attached to the first positioning bar 41 and the second positioning bar 42, respectively. At this time, the line connecting the 12-time position of the dial with the center of the first alignment part 82 is perpendicular to the first positioning bar 41, and the line connecting the 3-time position of the dial with the second alignment part 83 is perpendicular to the second positioning bar 42. Therefore, the watch 8 is positioned in position and angle, the recognition difficulty of the watch hand and the position is reduced, and meanwhile, the improvement of the recognition accuracy is facilitated.
In this embodiment, the camera module 1 is a high-definition camera.
In some other embodiments, the camera module 1 may also be a smart device with photographing and signal transmission functions, for example, a smart phone, a tablet computer, etc.
In this embodiment, the processing module 6 is a computer.
In this embodiment, the processing module 6 stores therein the standard values of the external characteristics of the hour hand, minute hand and second hand of the wristwatch 8 in advance. The appearance characteristic standard value comprises a gauge needle length standard value, a gauge needle width standard value and a gauge needle profile standard value.
In some other embodiments, the appearance characteristic standard values may also include gauge needle color standard values, and so forth.
In this embodiment, the step S4 includes the following steps:
Step S41, identifying a pointer in the front image;
Step S43, drawing each pointer to obtain an appearance characteristic identification value of each pointer;
Step S44, comparing the appearance characteristic recognition value of each hand with the appearance characteristic standard value of the hour hand, minute hand, and second hand corresponding to the hand of the watch 8, determining the hand having the appearance characteristic recognition value matching with the appearance characteristic standard value of the hour hand as the hour hand of the watch 8, determining the hand having the appearance characteristic recognition value matching with the appearance characteristic standard value of the minute hand as the minute hand of the watch 8, and determining the hand having the appearance characteristic recognition value matching with the appearance characteristic standard value of the second hand as the second hand of the watch 8.
It should be understood that the appearance characteristic identification values include a gauge needle length identification value, a gauge needle width identification value, and a gauge needle profile identification value. Here, the processing module 6 identifies the contour of the pointer by means of multi-point curve fitting to obtain the pointer contour identification value of each pointer, so that the visual identification method can perform time identification on the watch 8 with the contour of the pointer in an arc-shaped and special-shaped manner, that is, the compatibility of the visual identification method is high.
In this embodiment, the step S4 further includes the following steps:
S42, analyzing the number of the identified hands; if the number of hands is three, go to step S42; if the number of the gauge pins is not three, the identification is judged to be failed, and the step S41 is skipped. That is, in the process of identifying the gauge pins, if the number of the identified gauge pins is more than or less than 3 (for example, the overlapping situation easily causes the number of the identified gauge pins to be less than 3), the test is determined to be invalid, that is, the identification is failed at this time, and the previous step is returned to perform the gauge pin identification again so as to ensure that the valid identification data can be obtained.
In this embodiment, the step S4 further includes the following steps:
Step S45, analyzing whether the length of the identified hour hand is the shortest one of the three hands and whether the width of the identified second hand is the narrowest one of the three hands; if yes, confirming that the identification is correct; if not, judging that the identification is wrong, and jumping to the step S41. In this way, the hour hand, minute hand and second hand are distinguished by combining the features of the narrowest second hand and the shortest hour hand, and the accuracy of time identification of the wristwatch 8 is improved.
In this embodiment, the step S4 further includes the following steps:
Step S46, identifying the 3-time position of the dial in the front image, and respectively confirming the positions of the three identified hands by taking the 3-time position of the dial as a reference. Here, the positions and angles of the second hand, minute hand, and hour hand are confirmed by analyzing the relative positional relationship between the recognized 3-hour positions of the second hand, minute hand, and hour hand and the dial, and the time of the wristwatch 8 is confirmed.
Further, the visual recognition method further includes a step SA implemented between the step S2 and the step S3;
Step SA, the upper light emitting module 2 arranged above the tray 3 and the lower light emitting module 5 arranged below the tray 3 radiate light towards the watch 8 on said tray 3.
In this embodiment, led lamps may be used for both the upper light emitting module 2 and the lower light emitting module 5. The upper light-emitting module 2 and the lower light-emitting module 5 are used for compensating light for the camera module 1, so that the camera module 1 can collect clear front images of the watch 8.
Example two
The present embodiment provides a visual recognition system by which the visual recognition method described in the first embodiment can be implemented to accurately recognize the vision of different styles of watches 8.
Similarly, the wristwatch 8 applied to the present embodiment includes a case and a dial built in the case, and the case has a first alignment portion 82 corresponding to the 12-time position of the dial and a second alignment portion 83 corresponding to the 3-time position of the dial on the outside. The first alignment part 82 is a pair of block-shaped lugs (see fig. 3) connected to the outer side of the watch case, and the 12-time position of the dial is located right in the middle of the pair of lugs, that is, the line connecting the 12-time position of the dial and the centers of the pair of lugs is perpendicular to the X axis. The second alignment part 83 is a crown connected to the outside of the watch case (see fig. 3), and the 3-time position of the dial is exactly aligned with the crown, that is, the line connecting the 3-time position of the dial and the crown is perpendicular to the Y axis.
The visual recognition system comprises a camera module 1, a tray 3, a processing module 6, an upper light-emitting module 2 and a lower light-emitting module 5. Wherein, draw together camera module 1, go up light emitting module 2, tray 3, lower light emitting module 5 from top to bottom install on support 7. The tray 3 is made of a light-transmitting material (e.g. glass) for placing the watch 8. The tray 3 is fixed with a first positioning bar 41 and a second positioning bar 42 which respectively represent an X axis and a Y axis, and the first positioning bar 41 is vertically connected with the second positioning bar 42. The camera module 1 is arranged directly above the tray 3. The camera module 1 is in signal connection with the processing module 6. The camera module 1 is used for acquiring a front image of the watch 8 placed on the tray 3 and sending the front image to the processing module 6; the processing module 6 is configured to identify the position of the hour hand, minute hand, second hand and hour hand, minute hand, second hand in the front image, thereby identifying the time of the watch 8. The upper light emitting module 2 is arranged between the camera module 1 and the tray 3; the lower light emitting module 5 is arranged below the tray 3; the upper light emitting module 2 and the lower light emitting module 5 are both used to radiate light toward the wristwatch 8 on the tray 3.
In this embodiment, a through hole is formed in the middle of the upper light emitting module 2, and the camera module 1 is aligned with the through hole of the upper light emitting module 2. Specifically, the upper light emitting module 2 includes a frame and led lamps disposed on the frame, the frame is connected with the bracket 7, and the middle of the frame is provided with the through hole.
In this embodiment, the camera module 1 is a high-definition camera.
In some other embodiments, the camera module 1 may also be a smart device with photographing and signal transmission functions, for example, a smart phone, a tablet computer, etc.
In this embodiment, the processing module 6 is a computer.
The method for using the visual recognition system provided in this embodiment is referred to in the first embodiment, and will not be described herein.
In summary, the implementation of the invention can achieve the following beneficial effects:
1. In the visual recognition method of the present invention, when the watch 8 is placed on the tray 3, the first positioning bar 41 and the second positioning bar 42 respectively representing the X axis and the Y axis are used for positioning, the watch 8 is placed on the tray 3 in a dial-up manner, and the first alignment part 82 and the second alignment part 83 are respectively attached to the first positioning bar 41 and the second positioning bar 42, so that the position and the angle of the watch 8 are positioned, the difficulty in recognizing the watch hand and the position thereof is reduced, and the improvement of the recognition accuracy is facilitated.
2. In the visual identification method of the invention, the processing module 6 identifies the outline of the pointer in a multipoint curve fitting mode to obtain the pointer outline identification value of each pointer, so that the visual identification method can perform time identification on the watch 8 with the outline of the pointer in an arc-shaped and special-shaped style, namely, the compatibility of the visual identification method is high.
3. In the visual recognition method of the present invention, the features of the narrowest second hand and the shortest hour hand are combined to distinguish the hour hand, the minute hand and the second hand, thereby improving the accuracy of time recognition of the wristwatch 8.
The embodiments of the invention have been described above with reference to the accompanying drawings, but the invention is not limited to the embodiments described above, which are merely illustrative and not restrictive, and many forms may be made by those of ordinary skill in the art without departing from the spirit of the invention and the scope of the claims, which fall within the protection of the invention.

Claims (7)

1. The visual recognition method of watch time is characterized in that the watch comprises a watch case and a dial plate arranged in the watch case, wherein the outer side of the watch case is provided with a first alignment part corresponding to the 12-time position of the dial plate and a second alignment part corresponding to the 3-time position of the dial plate; the visual recognition method comprises the following steps:
s1, fixing a first positioning strip and a second positioning strip which respectively represent an X axis and a Y axis on a tray made of a light-transmitting material and used for placing a watch, wherein the first positioning strip and the second positioning strip are vertically connected;
S2, placing the watch on the tray in a dial-up mode, and enabling the first alignment part and the second alignment part to be respectively attached to the first positioning strip and the second positioning strip;
S3, a camera module arranged right above the tray acquires a front image of the watch and sends the front image to a processing module in signal connection with the camera module; the processing module is internally pre-stored with appearance characteristic standard values of an hour hand, a minute hand and a second hand of the watch;
Step S4, the processing module identifies the positions of the hour hand, the minute hand, the second hand and the hour hand, the minute hand and the second hand in the front image, so as to identify the time of the watch;
the step S4 includes the steps of:
Step S41, identifying a pointer in the front image;
Step S43, drawing each pointer to obtain an appearance characteristic identification value of each pointer;
Step S44, comparing the appearance characteristic identification value of each watch hand with appearance characteristic standard values of the hour hand, the minute hand and the second hand corresponding to the watch hands of the watch respectively, wherein the watch hand with the appearance characteristic identification value matched with the appearance characteristic standard value of the hour hand is judged to be the hour hand of the watch, the watch hand with the appearance characteristic identification value matched with the appearance characteristic standard value of the minute hand is judged to be the minute hand of the watch, and the watch hand with the appearance characteristic identification value matched with the appearance characteristic standard value of the second hand is judged to be the second hand of the watch;
The appearance characteristic standard value comprises a gauge needle length standard value, a gauge needle width standard value and a gauge needle profile standard value; the appearance characteristic identification value comprises a pointer length identification value, a pointer width identification value and a pointer profile identification value; the processing module recognizes the outline of the pointer in a multipoint curve fitting mode to obtain pointer outline recognition values of the pointers;
The step S4 further includes the steps of:
S42, analyzing the number of the identified hands; if the number of hands is three, go to step S42; if the number of the gauge pins is not three, judging that the identification fails, and jumping to the step S41;
step S45, analyzing whether the length of the identified hour hand is the shortest one of the three hands and whether the width of the identified second hand is the narrowest one of the three hands; if yes, confirming that the identification is correct; if not, judging that the identification is wrong, and jumping to the step S41.
2. The method for visually recognizing a time of a wristwatch according to claim 1, wherein the step S4 further comprises the steps of:
step S46, identifying the 3-time position of the dial in the front image, and respectively confirming the positions of the three identified hands by taking the 3-time position of the dial as a reference.
3. The method for visual recognition of a watch time according to claim 1, characterized in that it further comprises a step SA carried out between said step S2 and said step S3;
Step SA, the upper light emitting module arranged above the tray and the lower light emitting module arranged below the tray radiate light towards the watch on the tray.
4. A visual recognition system of watch time for implementing the visual recognition method of watch time according to any one of claims 1 to 3, characterized in that the watch comprises a case and a dial built in the case, the outside of the case has a first alignment part corresponding to the 12-hour position of the dial and a second alignment part corresponding to the 3-hour position of the dial; the visual recognition system includes:
The watch comprises a tray made of a light-transmitting material and used for placing a watch, wherein a first positioning strip and a second positioning strip which respectively represent an X axis and a Y axis are fixed on the tray, and the first positioning strip is vertically connected with the second positioning strip;
a camera module arranged right above the tray;
the processing module is in signal connection with the camera module;
the camera module is used for acquiring a front image of the watch placed on the tray and sending the front image to the processing module;
The processing module is used for identifying the positions of the hour hand, the minute hand, the second hand and the hour hand, the minute hand and the second hand in the front image, so as to identify the time of the watch.
5. The visual identification system of watch time of claim 4, further comprising an upper light module and a lower light module; the upper light emitting module is arranged between the camera module and the tray; the lower light emitting module is arranged below the tray; the upper light-emitting module and the lower light-emitting module are both used for irradiating light rays towards the watch on the tray.
6. The watch time visual recognition system of claim 4, wherein the middle portion of the upper light module has a through hole, and the camera module is aligned with the through hole of the upper light module.
7. The watch time visual recognition system of claim 4, wherein the camera module is a high-definition camera and the processing module is a computer.
CN202010815672.3A 2020-08-13 2020-08-13 A visual recognition method and system for watch time Active CN112101112B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010815672.3A CN112101112B (en) 2020-08-13 2020-08-13 A visual recognition method and system for watch time

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010815672.3A CN112101112B (en) 2020-08-13 2020-08-13 A visual recognition method and system for watch time

Publications (2)

Publication Number Publication Date
CN112101112A CN112101112A (en) 2020-12-18
CN112101112B true CN112101112B (en) 2024-11-15

Family

ID=73753738

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010815672.3A Active CN112101112B (en) 2020-08-13 2020-08-13 A visual recognition method and system for watch time

Country Status (1)

Country Link
CN (1) CN112101112B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105092904A (en) * 2014-05-04 2015-11-25 无锡华润上华半导体有限公司 MEMS silicon wafer fixing device, fixing method and testing method
CN109145753A (en) * 2018-07-23 2019-01-04 珠海格力电器股份有限公司 Watch hand identification method and device
CN110929710A (en) * 2019-10-29 2020-03-27 湖南大学 A vision-based automatic recognition method and system for meter pointer readings

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100578396C (en) * 2008-10-27 2010-01-06 深圳华为通信技术有限公司 A terminal and its time configuration method
EP2458458B1 (en) * 2010-11-26 2017-11-15 The Swatch Group Research and Development Ltd. Method for measuring the precision of a mechanical watch
CN105955011B (en) * 2016-04-21 2019-12-24 深圳欧德蒙科技有限公司 Intelligent timing method and device

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105092904A (en) * 2014-05-04 2015-11-25 无锡华润上华半导体有限公司 MEMS silicon wafer fixing device, fixing method and testing method
CN109145753A (en) * 2018-07-23 2019-01-04 珠海格力电器股份有限公司 Watch hand identification method and device
CN110929710A (en) * 2019-10-29 2020-03-27 湖南大学 A vision-based automatic recognition method and system for meter pointer readings

Also Published As

Publication number Publication date
CN112101112A (en) 2020-12-18

Similar Documents

Publication Publication Date Title
US10222634B2 (en) Optical measurement aid device
TWI307814B (en) Nonadjustable focusing type camera module
EP3088939B1 (en) Block device, eyeglass lens manufacturing method and program
EP3089001A1 (en) Screen assembly of mobile device and mobile device
KR20170105587A (en) Measurement device for eyeglasses-wearing parameter, measurement program for eyeglasses-wearing parameter, and position designation method
US12247826B2 (en) Spectacle lens shape measurement method
JP6016760B2 (en) Work confirmation system
KR20230066085A (en) Fitting mechanism and wearer anatomical adjustment of eyeglasses with visible display
CN112101112B (en) A visual recognition method and system for watch time
WO2022033016A1 (en) Visual test method and system for determining whether travel time precision of watch qualifies
US11140376B2 (en) Method for calibrating a binocular displaying device
JP2013142597A (en) Spectacle fitting parameter measurement system and spectacle fitting parameter measurement method
CN210605737U (en) face image acquisition device
US11531217B2 (en) Method for determining a parameter of an optical equipment
JP7121172B2 (en) lens meter
CN103890641A (en) Method for measuring pupil position and method for manufacturing bifocal lens
KR20190142187A (en) Electronic device with display
US20220142473A1 (en) Method and system for automatic pupil detection
CN103137218B (en) Method and device for adjusting pointer
CN216167379U (en) Liquid crystal intelligent interactive visual chart
CN104571138B (en) Method and apparatus for acquiring and calculating data from an ophthalmic subject
CN106572346B (en) 360 degree of monoscopic video data correcting methods of one kind and correction system
CN109990980A (en) A kind of visible-light detector visibility function modification method based on spectrometer
KR102299051B1 (en) Digital system providing 3D parameters for diagnosing the ophthalmic glasses
JP2574026B2 (en) Eyeglass lens processing data calculation method and apparatus

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant