CN109059867B - Monocular machine vision method for judging positive and negative postures of watch shell workpiece - Google Patents

Monocular machine vision method for judging positive and negative postures of watch shell workpiece Download PDF

Info

Publication number
CN109059867B
CN109059867B CN201810612412.9A CN201810612412A CN109059867B CN 109059867 B CN109059867 B CN 109059867B CN 201810612412 A CN201810612412 A CN 201810612412A CN 109059867 B CN109059867 B CN 109059867B
Authority
CN
China
Prior art keywords
workpiece
positive
watch case
image
gray
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.)
Expired - Fee Related
Application number
CN201810612412.9A
Other languages
Chinese (zh)
Other versions
CN109059867A (en
Inventor
李梦如
吴轩全
陈哲
卜王辉
陈茂林
奚鹰
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.)
Tongji University
Original Assignee
Tongji University
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 Tongji University filed Critical Tongji University
Priority to CN201810612412.9A priority Critical patent/CN109059867B/en
Publication of CN109059867A publication Critical patent/CN109059867A/en
Application granted granted Critical
Publication of CN109059867B publication Critical patent/CN109059867B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
    • G01C11/04—Interpretation of pictures

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Image Processing (AREA)

Abstract

The invention relates to a monocular machine vision method for judging the positive and negative postures of a watch shell workpiece. The photographing angle of the visual system is a top view of a workpiece, and the positive and negative postures of the watch shell are judged by utilizing the library function based on the OpenCV. The method has strong anti-interference performance, low requirement on hardware equipment and high judgment accuracy. The visual system is applied to a production line with the task of judging the positive and negative postures of the watch case workpiece, so that the working efficiency of the production line can be obviously improved, and the robot replaces human eyes to recognize, thereby realizing production automation.

Description

Monocular machine vision method for judging positive and negative postures of watch shell workpiece
Technical Field
The invention relates to a monocular machine vision method for judging the positive and negative postures of a watch shell workpiece.
Background
Paul Hough proposed a Hough transform in 1959 machine analysis of bubble chamber photographs, and obtained U.S. Pat. No. 2 in 196, named Method and Means for recogning complete Patterns. In this patent, the straight-line parametric equation takes the form of a diagonal intercept, but since the slope may be infinite, this may result in an infinite transform space.
The Hough transform used in this patent was invented in 1972 by Richard Duda and Peter Hart under the name "generalized Hough transform [ GHT ]", and its patent name is "Use of the Hough Transformation to detect Lines and cultures in Pictures, 1972". Then in 1981, an article entitled general transform to detect architectural shapes appeared in the computer vision community, and the Hough transform technique was further generalized.
In addition, digital image processing techniques must be applied in machine vision systems. Digital image processing techniques were developed and integrated into books by professor jossajous and his team. More typically digital image histogram analysis. Digital image histogram analysis introduces probability and statistical techniques into the digital image signal. The basis is histogram analysis in probability and statistics. By analyzing the histogram of the digital image signal, the gray distribution characteristics of the image can be obtained, so that the characteristics of the image under different conditions can be found out.
Currently, there is very little research directed to the introduction of machine vision technology into the field of watch case manufacturing. Because the positive and negative recognition task of wrist-watch shell is comparatively ordinary, most enterprises still adopt manual mode to carry out positive and negative discernment of watchcase at present. A few enterprises begin to adopt mechanical structures to distinguish between the front and the back of the watch case. Although the task of identifying the front and the back of the watch shell is very simple and can be easily finished manually, the watch shell is easily tired after being identified by human eyes for a long time due to the fact that the watch shell is large in number on a production line for processing and manufacturing the watch shell, and the identification error rate can rise along with the increase of working time. From an economic perspective, the cost of using manual identification is higher than that of mechanical identification on a mass production basis. In addition, the watch shell posture is distinguished by using a pure mechanical structure, and the watch shell posture distinguishing device has limitations. On one hand, the mechanical structure is more complex, and the design and manufacturing cost is higher; on the other hand, the complexity of the mechanical structure directly affects its service life and maintenance costs. Therefore, the machine vision technology is introduced into the field, the problems of fatigue of human eyes and high labor cost can be solved, vision can be given to a production line, the complexity of a mechanical structure is greatly simplified, the maintenance cost is reduced, and meanwhile, the production efficiency and the production quality are also improved.
Disclosure of Invention
The invention aims to provide a monocular machine vision method for judging the positive and negative postures of a watch shell workpiece. The invention provides a monocular machine vision method for judging the positive and negative postures of a watch shell workpiece, which comprises the following specific steps:
(1) building machine vision hardware system
The machine vision hardware system consists of a black box, a camera, an annular light source, a watch case and a carrying disc, wherein the black box is of a hollow structure in the middle part; the shooting angle of the machine vision hardware system for the watch case workpiece is a top view capable of completely showing the outline of the workpiece, and in addition, the main body color of the workpiece is obviously distinguished from the background color; wherein: the black box is a shading part, so that the influence of the external environment on the photographing environment can be reduced, the photographing environment independently provides a light source as a lighting part to ensure the brightness of a workpiece, the annular light source is a light source system to create a specified photographing environment for a camera to acquire images, and image information acquired by the camera is input into image processing equipment to be processed and analyzed so as to obtain a required result;
(2) feature analysis of positive and negative postures of workpiece
Theoretically, the camera can photograph at a position approximately right above the watch case, and the light emitted by the light source is approximately parallel light perpendicular to the stage, so that the outline of the watch case obtained by the camera is not different from the outline of the watch case in a top view. In order to obtain a more versatile top view of the watch case, we have analyzed from the outline of the outermost periphery of the watch case. It can be seen that the four support feet of the case are not flat but have curved surfaces with a curvature, which are convex when the case is right side up and concave when the case is reverse side up. This feature is applicable to most watch cases.
By utilizing the common property of the watchcase, the optical knowledge shows that because the light projected by the light source is approximately parallel light, when the watchcase is positive, the curved surfaces of the four corners are convex upwards, so that part of the light is reflected outwards, and only a few light rays can be captured by the camera. When the watchcase is inverted, most of light rays are reflected inwards due to the concave surfaces of the four corners, and most of light rays can be captured by the camera. The effect of this phenomenon, which is ultimately presented on the image, is that when the case is positive, the four corners are darker; and when the watchcase is reversed, the four corners are brighter.
The four supporting feet of the watch case are not plane and are curved surfaces with certain radian; furthermore, the curved surface is convex when the case is right side up and concave when the case is reverse side up;
by utilizing the commonality of the watch case, the light projected by the light source is approximate to parallel light, so when the watch case is positive, part of light rays are reflected outwards due to the fact that the curved surfaces of the four corners are protruded upwards, and only a few light rays can be captured by the camera; when the watch shell is reversed, most of light rays are reflected inwards due to the concave surfaces of the four corners, and the camera can capture most of light rays; the effect of this phenomenon being eventually presented on the image is that when the watch case is positive, the four corners are darker; when the watch shell is reversed, the four corners are brighter;
(3) gray level histogram analysis of images
Firstly, two initial input images with positive postures and negative postures are shot, and then the initial input images are grayed to respectively obtain Igray_zAnd Igray_f. Histogram analysis is carried out on the two gray level images, and the gray level interval (gray) occupied by the four supporting legs when the posture of the watch case is positive can be judgedz1，grayz2]And the gray scale interval (gray) occupied by four supporting legs when the posture of the watch case is reversef1，grayf2](ii) a The interval resulting from the watch case being positive and the watch case being negative being clearly differentiated and faulted, i.e. grayz2＜＜grayf1；
(4) Geometric center (x) of workpiece imagec，yc) Is determined
(i) When the top view of the workpiece does not have obvious regular geometric features, graying the workpiece image with positive attitude, then performing histogram analysis, finding out a threshold value for distinguishing the workpiece from the background, and performing binarization on the image by using the threshold value so as to distinguish the workpiece from the background and obtain a binary image I of the original imagebinaryAnd the center of the workpiece is obtained by utilizing the binary image;
(ii) when the top view of the workpiece has obvious regular geometric characteristics, if the geometric center of the workpiece is superposed with the center of a part of circle of the workpiece, or the geometric center is superposed with the intersection point of a certain diagonal, the special standard graphs can be extracted, so that the geometric center can be obtained more accurately;
(5) binarization of images from histogram analysis
Selecting a gray value as a threshold value according to the formula 1, and binarizing the image of the front side and the back side of the workpiece to be judged to obtain Ibinary；
Figure GDA0002518021770000031
By the geometric centre (x) of the workpiecec，yc) As the origin, a judgment ring having an appropriate radius and width is set. The radius of the ring is selected so that it is exactly the same size as the four legs of the watch case but not the body of the watch case. For image IbinaryScanning pixel points in the set judgment ring area, and judging that the posture of the watchcase corresponding to the image is positive if gray values of all the pixel points in the ring are 0 (namely all the pixel points in the ring are black); otherwise, the posture is reversed.
In the invention, the camera is a common camera and has no special requirement.
The invention is suitable for various common watch shell workpieces, and has the common characteristic of comprising an inner circle and four supporting legs for mounting a watchband. In the present invention, it is specified that the posture of the watch case is positive when the face for displaying time is facing upward, and vice versa.
The invention has the beneficial effects that:
1. the invention has low requirements on the camera equipment used in the machine vision system, and the camera pixels are only required to be more than 100 thousands;
2. the positive and negative posture recognition accuracy and recognition rate of the watchcase are high, and the watch case can completely replace human eyes to complete recognition tasks;
3. according to the invention, the light source system (including the black box part) is built, so that a stable condition is created for shooting the watch shell, and the influence of the external condition on the system for judging the posture of the watch shell is small.
Drawings
FIG. 1 is a schematic structural diagram of a machine vision hardware system constructed according to the present invention.
FIG. 2 is a flow chart of the method of the present invention.
Figure 3 shows the positive position of the watch case from the side profile of the case.
Figure 4 shows the inverted position of the watch case from the side profile of the case.
Fig. 5 is a photograph of the watch case in a positive attitude.
Fig. 6 is a photographed image of the watch case in a reversed posture.
Fig. 7 is a histogram of a grayscale image with a positive attitude of the watch case.
Fig. 8 is a histogram of a grayscale image with the posture of the watch case reversed.
FIG. 9 is a diagram of the effects of the workpiece positioning algorithm.
Fig. 10 is an optical path diagram of the light source system when the posture of the wristwatch case is positive.
FIG. 11 is a light path diagram of the light source system when the watch case is in a reverse attitude.
FIG. 12 is an image and judgment ring with positive gesture of the watch case after binarization.
FIG. 13 is an image and judgment ring with the posture of the watch case inverted after binarization.
FIGS. 14.1 to 14.100 are graphs showing the results of the detection of the method of the present invention in practical applications.
Reference numbers in the figures: 1 is a black box, 2 is a camera, 3 is an annular light source, 4 is a watch shell, and 5 is a carrying disc.
Detailed Description
The invention will be further illustrated by the following example of a project produced by a watch case, with reference to the accompanying drawings.
Example 1:
the schematic diagram of a machine vision hardware system built by the project is shown in FIG. 1. Wherein (a) in fig. 1 shows an illumination schematic diagram of a light source system, and as can be seen from the diagram, a vision hardware system mainly comprises a black box, a camera, a light source and a shot workpiece. The image taken by the designed system is a top view of the workpiece. Wherein the distance of the light source and the camera from the workpiece should be adjustable. Fig. 1 (b) is a cross-sectional view of a three-dimensional model of a built visual system, in which the top cover of the black box has been hidden for the convenience of showing the internal structure. In order to reduce the influence of the external environment on the image acquisition process, a black box is designed in the project. The workpiece enters the black box to be photographed, so that the workpiece is isolated from the external environment. The flow chart of the positive and negative posture judging method of the watch case workpiece is shown in figure 2.
Figures 3 and 4 illustrate the watch case in a front-back position, respectively, from the side profile of the watch case. Wherein the posture of the watch case of figure 3 is positive and the posture of the watch case of figure 4 is negative.
And carrying out characteristic analysis on the watch shell workpiece. The four supporting feet of the watch case are not plane but have curved surfaces with certain radian, and in addition, the curved surfaces are upwards convex when the watch case is frontally upward and concave when the watch case is frontally upward. This feature is applicable to most watch cases. By utilizing the common characteristics of the watchcase and combining the knowledge of the structure and the optics of the light source system, because the light projected by the light source is approximately parallel light, when the watchcase is in a positive state, the curved surfaces of the four corners are convex upwards, so that part of the light is reflected outwards, and only a few light rays can be captured by the camera. When the watchcase is inverted, most of light rays are reflected inwards due to the concave surfaces of the four corners, and most of light rays can be captured by the camera. The effect of this phenomenon, which is ultimately presented on the image, is that when the case is positive, the four corners are darker; and when the watchcase is reversed, the four corners are brighter.
And respectively photographing the watch shell with the positive posture and the watch shell with the negative posture in a black box of the built machine vision system to obtain two basic images (see fig. 5 and 6) for completing the preparation work before judging the positive posture and the negative posture. Then, the two basic images are grayed, and then the grayscale image histograms thereof are drawn (see fig. 7 and 8), and analyzed. Analysis of the histogram shows that the histogram has three peaks. The first peak represents a black background portion. The second peak represents the case support foot portion. The third peak represents the annular part of the watch case. It can be seen that the average gray value corresponding to the second peak of the image of the watch case in the positive posture is smaller than that of the image of the watch case in the negative posture. Taking the average gray value corresponding to the second peak of the watchcase image with positive attitude as gray190, the average gray value corresponding to the second peak of the watchcase image with the reversed posture is gray2＝160。
The appearance characteristics of the watch shell workpiece are analyzed, and the geometric center of the workpiece top view is the same as the circle center of the inner circle of the workpiece circular ring. Therefore, in the project, the circle outline is identified by using the Hough circle detection method, so that the center of the circle in the circular ring is extracted, and further, the center of the circle in the circular ring is extractedObtaining the geometric center (x) of the workpiecec，yc). Such as the white point center in fig. 9.
Fig. 10 and 11 are light path diagrams of watch cases with front and back postures irradiated by a light source in a built vision system. As can be seen from the optical path diagram, the watchcase with the positive posture reflects light outward at the curved surface of the supporting leg, and the watchcase with the negative posture reflects light inward at the curved surface of the supporting leg. Thus, in the image, the watchcase leg in the positive posture appears darker, while the watchcase leg in the negative posture appears brighter. Performing histogram analysis, taking the threshold value as g, and binarizing the watchcase image to obtain IbinaryThe meter case supporting foot with the meter case posture of the reverse direction is reserved by utilizing a binarization mode, and the meter case supporting foot part with the meter case posture of the positive direction is filtered by a threshold value g. Wherein:
Figure GDA0002518021770000061
by the geometric centre (x) of the workpiecec，yc) For the origin, a judgment ring of a proper radius and width is set, the radius of which is just larger than the outer circle radius of the ring in the watch case and is smaller than the distance between the farthest points of the four supporting legs (the judgment ring is shown in fig. 12 and 13 in the manner of a white ring). The resulting images for both positive and negative poses are shown in fig. 12 and 13. For image IbinaryScanning pixel points in the set judgment ring area, and judging that the posture of the watchcase corresponding to the image is positive if gray values of all the pixel points in the ring are 0 (namely all the pixel points in the ring are black); otherwise, the posture is reversed.
Through the above steps, the method of the present invention is detected on 100 images. The detection results are shown in FIGS. 14.1-14.100. In the figure, a circle is drawn at the center of the watchcase to indicate that the image processing system judges the watchcase to be positive; on the contrary, the cross at the center of the watchcase indicates that the image processing system judges the watchcase to be reverse. According to the detection result, the accuracy rate of judging the positive and negative postures of the watch shell is almost 100%.

Claims (1)

1. The monocular machine vision method for judging the positive and negative postures of the watch case workpiece is characterized in that: the method comprises the following specific steps:
(1) building machine vision hardware system
The machine vision hardware system consists of a black box, a camera, an annular light source, a watch case and a carrying disc, wherein the black box is of a hollow structure in the middle part; the shooting angle of the machine vision hardware system for the watch case workpiece is a top view capable of completely showing the outline of the workpiece, and in addition, the main body color of the workpiece is obviously distinguished from the background color; wherein: the black box is a shading part, so that the influence of the external environment on the photographing environment can be reduced, the photographing environment independently provides a light source as a lighting part to ensure the brightness of a workpiece, the annular light source is a light source system to create a specified photographing environment for a camera to acquire images, and image information acquired by the camera is input into image processing equipment to be processed and analyzed so as to obtain a required result;
(2) feature analysis of positive and negative postures of workpiece
The four supporting feet of the watch case are not plane and are curved surfaces with certain radian; furthermore, the curved surface is convex when the case is right side up and concave when the case is reverse side up;
by utilizing the commonality of the watch case, the light projected by the light source is approximate to parallel light, so when the watch case is in positive time, because the curved surfaces of the four corners are protruded upwards, partial light is scattered towards the outer side direction of the watch case and cannot be reflected to the position of the camera lens, and only a few light can be reflected to the position of the camera lens and captured by the camera; when the watch shell is reversed, most of light rays are reflected to the inner side of the watch shell due to the fact that the curved surfaces of the four corners are concave, and the light rays are focused on the position of a camera lens, so that most of light rays can be captured by the camera; the effect of this phenomenon being eventually presented on the image is that when the watch case is positive, the four corners are darker; when the watch shell is reversed, the four corners are brighter;
(3) gray level histogram analysis of images
Firstly, two initial input images with positive postures and negative postures are shot, and then the initial input images are grayed to respectively obtain Igray_zAnd Igray_f(ii) a Histogram analysis is carried out on the two gray level images, and the gray level interval (gray) occupied by the four supporting legs when the posture of the watch case is positive can be judgedz1，grayz2]And the gray scale interval (gray) occupied by four supporting legs when the posture of the watch case is reversef1，grayf2](ii) a The interval resulting from the watch case being positive and the watch case being negative being clearly differentiated and faulted, i.e. grayz2＜＜grayf1；
(4) Geometric center (x) of workpiece imagec，yc) Is determined
(i) When the top view of the workpiece does not have obvious regular geometric features, graying the workpiece image with positive attitude, then performing histogram analysis, finding out a threshold value for distinguishing the workpiece from the background, and performing binarization on the image by using the threshold value so as to distinguish the workpiece from the background and obtain a binary image I of the original imagebinaryAnd the center of the workpiece is obtained by utilizing the binary image;
(ii) when the top view of the workpiece has obvious regular geometric characteristics, if the geometric center of the workpiece is superposed with the center of a part of circle of the workpiece, or the geometric center is superposed with the intersection point of a certain diagonal, the special standard graphs can be extracted, so that the geometric center can be obtained more accurately;
(5) binarization of images from histogram analysis
Selecting a gray value as a threshold value according to the formula 1, and binarizing the image of the front side and the back side of the workpiece to be judged to obtain Ibinary；
Figure FDA0002518021760000021
By the geometric centre (x) of the workpiecec，yc) Setting a judgment ring with proper radius and width as an origin; the radius of the ring is selectedThe principle is that the size of the bracket is just intersected with the four supporting legs of the watch case but not intersected with the watch case body; for image IbinaryScanning pixel points in the set judgment ring area, and judging that the posture of the watchcase corresponding to the image is positive if gray values of all the pixel points in the ring are 0 (namely all the pixel points in the ring are black); otherwise, the posture is reversed.
CN201810612412.9A 2018-06-14 2018-06-14 Monocular machine vision method for judging positive and negative postures of watch shell workpiece Expired - Fee Related CN109059867B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810612412.9A CN109059867B (en) 2018-06-14 2018-06-14 Monocular machine vision method for judging positive and negative postures of watch shell workpiece

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810612412.9A CN109059867B (en) 2018-06-14 2018-06-14 Monocular machine vision method for judging positive and negative postures of watch shell workpiece

Publications (2)

Publication Number Publication Date
CN109059867A CN109059867A (en) 2018-12-21
CN109059867B true CN109059867B (en) 2020-10-30

Family

ID=64820892

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810612412.9A Expired - Fee Related CN109059867B (en) 2018-06-14 2018-06-14 Monocular machine vision method for judging positive and negative postures of watch shell workpiece

Country Status (1)

Country Link
CN (1) CN109059867B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109916339B (en) * 2019-03-21 2020-11-06 浙江理工大学 Method and device for measuring fiber angle based on illumination stereoscopic system

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070125863A1 (en) * 2005-12-05 2007-06-07 Jakoboski Timothy A System and method for employing infrared illumination for machine vision
JP6179680B1 (en) * 2016-04-08 2017-08-16 新日鐵住金株式会社 Surface condition monitoring apparatus and surface condition monitoring method
CN105806845A (en) * 2016-06-07 2016-07-27 西南大学 In-car ceiling handle surface defect detecting device based on machine vision
CN106814084A (en) * 2016-06-08 2017-06-09 北京壹格科技有限公司 A kind of new panel surface defect detecting system
CN107589124A (en) * 2017-02-13 2018-01-16 上海佑生源环境工程有限公司 Online wood-based plate surface defects detection based on machine vision is graded system and method
CN106908444B (en) * 2017-03-20 2023-10-10 辽宁科技大学 Tapered roller bearing end face recognition system and method based on image processing
CN107876425A (en) * 2017-11-10 2018-04-06 华东交通大学 A kind of bearing defect detecting system device of view-based access control model
CN108037135A (en) * 2018-01-15 2018-05-15 佛山职业技术学院 A kind of magnet ring surface defect detection apparatus and method

Also Published As

Publication number Publication date
CN109059867A (en) 2018-12-21

Similar Documents

Publication Publication Date Title
US11869139B2 (en) System and method for three-dimensional scanning and for capturing a bidirectional reflectance distribution function
CN103810478B (en) A kind of sitting posture detecting method and device
CN105138965B (en) A kind of near-to-eye sight tracing and its system
WO2016158856A1 (en) Imaging system, imaging device, imaging method, and imaging program
CN111160136B (en) Standardized 3D information acquisition and measurement method and system
CN102855626A (en) Methods and devices for light source direction calibration and human information three-dimensional collection
CN106297492B (en) A kind of Educational toy external member and the method using color and outline identification programming module
CN111627008B (en) Object surface detection method and system based on image fusion and storage medium
CN110514665A (en) A kind of detection method of electronic product plastic shell scratch defects
US9204130B2 (en) Method and system for creating a three dimensional representation of an object
CN109059867B (en) Monocular machine vision method for judging positive and negative postures of watch shell workpiece
CN103413318B (en) Target ball mirror surface center positioning method
CN108510544A (en) A kind of striation localization method of feature based cluster
CN110012287B (en) The dirty self checking method of digital camera image sensor based on retina perception
CN107680035A (en) A kind of parameter calibration method and device, server and readable storage medium storing program for executing
JP2003271932A (en) Sight line direction detector
JP2007017364A (en) Device and method for extracting silhouette, and device and method for generating three-dimensional shape data
Shieh et al. Fast facial detection by depth map analysis
Li et al. Vision-based target detection and positioning approach for underwater robots
US20240013437A1 (en) Method for providing calibration data for calibrating a camera, method for calibrating a camera, method for producing at least one predefined point-symmetric region, and device
CN109741302A (en) SD card form recognition system and method based on machine vision
CN115184362A (en) Rapid defect detection method based on structured light projection
KR100593606B1 (en) Object Recognition Apparatus by Pattern Image Projection and Applied Image Processing Method
JP2019101974A (en) Image processing device
CN114354607B (en) Luminosity three-dimensional flaw detection method based on spiral phase contrast filtering algorithm

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
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20201030

CF01 Termination of patent right due to non-payment of annual fee