CN111551350A - Optical lens surface scratch detection method based on U _ Net network - Google Patents
Optical lens surface scratch detection method based on U _ Net network Download PDFInfo
- Publication number
- CN111551350A CN111551350A CN202010422041.5A CN202010422041A CN111551350A CN 111551350 A CN111551350 A CN 111551350A CN 202010422041 A CN202010422041 A CN 202010422041A CN 111551350 A CN111551350 A CN 111551350A
- Authority
- CN
- China
- Prior art keywords
- scratch
- image
- scratches
- length
- algorithm
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M11/00—Testing of optical apparatus; Testing structures by optical methods not otherwise provided for
- G01M11/02—Testing optical properties
- G01M11/0242—Testing optical properties by measuring geometrical properties or aberrations
- G01M11/0278—Detecting defects of the object to be tested, e.g. scratches or dust
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method for detecting scratches on the surface of an optical lens based on a U _ Net network, relating to the technical field of optical lenses; the method comprises the following steps: the method comprises the following steps: the flow structure of the scratch detection system; step two: factor analysis influencing image acquisition quality; step three: the scratch image and other similar defects are differentiated and researched; step four: researching a scratch detection algorithm; the invention not only can accurately detect the form of the scratch, but also can realize the differentiation of similar defects of the scratch on the surface of the optical lens and realize the quantitative detection of the position and the length width of the scratch on the basis; the product cost is reduced, the production efficiency and the production quality are greatly improved, the assembly line can be optimized according to the detected information, the defects can be found, and the occurrence of scratch and fault can be reduced; for the country, the application of the machine vision detection technology improves the international competitiveness of the production in the industrial field of China and improves the detection efficiency in the production process of the lens.
Description
Technical Field
The invention belongs to the technical field of optical lenses, and particularly relates to a method for detecting scratches on the surface of an optical lens based on a U _ Net network.
Background
The traditional machine vision detection technology is difficult to obtain proper characteristics, and detection results are often unsatisfactory. The traditional machine vision detection technology work flow is that a series of set image preprocessing is used for extracting the characteristics of sample data and expressing the sample data in a vector form, a classifier is designed for classifying objects, and if the gray level difference between a scratch area and a background is used for realizing the extraction of scratches and the detection of the edge characteristics of scratches by adopting a gray level threshold segmentation method, the algorithm only can give the general positions of scratches, the accuracy is low, the algorithm is easily influenced by background clutter, and the false detection rate are high. In addition, the detection technology of this mode often requires that users have abundant professional knowledge, and the quality of feature extraction directly affects the detection effect.
Disclosure of Invention
In order to solve the existing problems; the invention aims to provide a method for detecting scratches on the surface of an optical lens based on a U _ Net network.
The invention relates to a method for detecting scratches on the surface of an optical lens based on a U _ Net network, which comprises the following steps:
the method comprises the following steps: the flow structure of the scratch detection system is as follows:
establishing a special image acquisition platform, researching an illumination unit based on a coaxial light source, transmitting the acquired image to an upper computer, manufacturing an image training set, obtaining a high-precision scratch characteristic image through U _ Net deep learning network training, distinguishing scratches from similar defects on the basis, and finally completing measurement of the position, the number and the length and the width of the scratches through a corresponding algorithm;
step two: analyzing factors influencing image acquisition quality:
the coaxial light source is defined as that the light source is diffused by the diffusion plate to irradiate the semi-transparent semi-reflective light splitting sheet, and the light splitting sheet reflects the light to an object and then reflects the light to the lens by the object; detecting bruises, scratches, cracks and foreign bodies on the flat and smooth surface of an object; the images collected by the illumination environments with different colors and intensities are compared under the control of a computer, and more complete and accurate image information is comprehensively obtained;
step three: the scratch image and other similar defects are distinguished and studied:
the method comprises the steps of segmenting a scratch image by adopting an RGB three-channel u _ net network, and realizing more accurate embodiment of scratch edges by respectively convolving three color channels; the optimal illumination condition is found through experiments, meanwhile, the resolution of the camera is improved as much as possible, the original characteristics of the image are guaranteed, high-precision samples are provided for subsequent deep learning training, and the detection precision is improved;
step four: scratch detection algorithm study:
detecting scratches mainly includes three aspects: area positioning, quantity statistics and length measurement;
4.1, area positioning and quantity statistics are realized by adopting a contour query method, firstly, contour extraction is carried out on a scratch image, after the contour image is obtained, four vertex coordinates A (x1, y1), B (x2, y2), C (x3, y3) and D (x4, y4) of pixels of the contour extraction are traversed to limit the scratch area, the length and the width of the scratch area are obtained through coordinate point difference, the coordinate position of the scratch area is output, and the quantity of scratches is counted;
4.2, measuring the length of the scratch by adopting a K3M algorithm, wherein the K3M skeleton extraction algorithm is a continuous iterative algorithm and consists of an iterative part of seven steps and a single terminal additional step, and after the scratch skeleton is obtained, counting the pixel points of the scratch skeleton to obtain the arc length of the scratch; the scratch arc length expression is shown in formula 1:
wherein, L is the arc length of the scratch area and is in mm, lp is the actual length corresponding to a single pixel and is in mm; g (x, y) represents connected domain pixel points of the scratch extracted by the K3M algorithm framework; and finally, converting the actual distance represented by the pixel according to the pixel and the real length.
Compared with the prior art, the invention has the beneficial effects that:
firstly, the form of the scratch can be accurately detected, the similar defect distinguishing of the scratch on the surface of the optical lens can be realized, and the quantitative detection of the scratch position and the length width can be realized on the basis;
secondly, the product cost is reduced, the production efficiency and the production quality are greatly improved, the assembly line can be optimized according to the detected information, the defects can be found, and the occurrence of scratch and fault can be reduced; for the country, the application of the machine vision detection technology improves the international competitiveness of the production in the industrial field of China and improves the detection efficiency in the production process of the lens.
Drawings
For ease of illustration, the invention is described in detail by the following detailed description and the accompanying drawings.
FIG. 1 is a basic flowchart of the scratch detection according to the present invention;
FIG. 2 is a schematic view of a lens image acquired by the imaging system of the present invention;
FIG. 3 is an optical schematic diagram of the imaging of scratches and near defects in the present invention;
FIG. 4 is a schematic diagram of a scratch image after binarization in the invention;
fig. 5 is a schematic view of a scratch image after edge extraction in the present invention.
Detailed Description
In order that the objects, aspects and advantages of the invention will become more apparent, the invention will be described by way of example only, and in connection with the accompanying drawings. It is to be understood that such description is merely illustrative and not intended to limit the scope of the present invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
It should be noted that, in order to avoid obscuring the present invention with unnecessary details, only the structures and/or processing steps closely related to the scheme according to the present invention are shown in the drawings, and other details not so relevant to the present invention are omitted.
The specific implementation mode adopts the following technical scheme: the method comprises the following steps:
as shown in fig. 1, a flow structure of the scratch detection system:
the scratch detection system of the optical lens is the basis for machine vision realization; the scratch on the surface of the lens is accurately positioned, the number of the scratches is counted, the length and the width of the scratch are measured, and the difference between the number of pixels of a scratch image and the number of pixels of a background is large, and the gray scale contrast is small, so that the acquisition of a high-resolution image is the key for realizing the scratch; establishing a special image acquisition platform aiming at the problems, researching an illumination unit based on a coaxial light source, transmitting the acquired image to an upper computer, manufacturing an image training set, obtaining a high-precision scratch characteristic image through U _ Net deep learning network training, distinguishing scratches from similar defects on the basis, and finally completing measurement aiming at the positions, the number and the length and the width of scratches through a corresponding algorithm;
secondly, analyzing factors influencing image acquisition quality:
the accurate measurement of scratches is needed, so that the whole research premise is met when a lens image with high quality and high definition is acquired, the image with good imaging quality plays a crucial role in the manufacture of a subsequent data set and the stable operation of a feature extraction algorithm.
As shown in fig. 2, when a camera of a mobile phone is used to take a picture, the taken picture is not suitable for visual processing due to a lot of reflection and shading, so an illumination unit based on a coaxial light source is adopted, the coaxial light is defined as that the light source is diffused by a diffusion plate to strike a semi-transparent semi-reflective beam splitter, and the beam splitter reflects the light to an object and then the object is reflected to a lens. Since the light reflected by the object is on the same axis as the camera, the light source in this manner is called coaxial light. Coaxial light sources (diffuse coaxial lamps, metal plane diffuse reflective illumination sources) provide more uniform illumination than conventional light sources, thus improving the accuracy and reproducibility of machine vision. The coaxial light source shown in fig. 3 can highlight the unevenness of the surface of an object, overcome the interference caused by surface reflection, and is mainly used for detecting the bruise, scratch, crack and foreign matter of the flat and smooth surface of the object. The images collected by the illumination environments with different colors and intensities are compared under the control of a computer, and more complete and accurate image information is comprehensively obtained.
Thirdly, distinguishing and researching the scratch image and other similar defects:
due to the fact that the defects of the lens are various, the defects are most similar to scratches, namely the strip-shaped dirt and the internal flocks on the surface of the lens, the defects cannot be accurately distinguished according to the area, the gray value and the position of the defects, missing detection and false detection are often caused in manual detection of an assembly line, and therefore characteristic analysis needs to be carried out through the optical principle. As shown in fig. 3, when the CCD camera acquires a pattern, the dirt on the surface of the lens and the internal flock obstruct the parallel light rays, so that the image can generate defect images with uniform gray scale and different shapes. In contrast, the scratch is mostly a curve with little curvature variation, which forms a groove on the lens surface, which changes the traveling direction of light, and the edge is refracted so that there is a large variation in the gray image compared with its surrounding background.
As shown in fig. 4 and 5, most of the conventional detection methods are based on threshold segmentation and edge extraction, and although the scratch morphology can be approximately retained by this method, the optical characteristics of the scratch are completely changed due to the defect of the algorithm itself, and become approximately a solid line, so that the work of distinguishing the subsequent scratch from the similar defect cannot be realized at all.
Because the detected scratch target is close to the background gray value, and the brightness change of the scratch is required to be accurately detected to distinguish from other defects, the traditional single-channel gray image is difficult to realize. Aiming at the problems, an RGB three-channel u _ net network is adopted to segment the scratch image, and the three color channels are respectively convoluted to realize more accurate embodiment of the scratch edge; the optimal illumination condition is found through experiments, the resolution ratio of the camera is improved as much as possible, the original features of the image are guaranteed, high-precision samples are provided for subsequent deep learning training, and the detection precision is improved.
Fourthly, researching a scratch detection algorithm:
detecting scratches mainly includes three aspects: area positioning, quantity statistics and length measurement;
4.1, area positioning and quantity statistics are realized by adopting a contour query method, firstly, contour extraction is carried out on a scratch image, after the contour image is obtained, four vertex coordinates A (x1, y1), B (x2, y2), C (x3, y3) of contour pixels are extracted by traversing pixels, the scratch area is limited by D (x4, y4), the length and the width of the scratch area are obtained through coordinate point difference, the coordinate position of the scratch area is output, and the quantity of scratches is counted.
4.2, the scratch length measurement is supposed to adopt a K3M algorithm, a K3M skeleton extraction algorithm is a continuous iteration algorithm and comprises an iteration part of seven steps and a single terminal additional step, and after the scratch skeleton is obtained, the scratch skeleton pixel points are counted to obtain the arc length of the scratch. The scratch arc length expression is shown in formula 1
Wherein, L is the arc length of the scratch area and is in mm, lp is the actual length corresponding to a single pixel and is in mm; g (x, y) represents connected domain pixel points of the scratch extracted by the K3M algorithm framework. And finally, converting the actual distance represented by the pixel according to the pixel and the real length.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (1)
1. A method for detecting scratches on the surface of an optical lens based on a U _ Net network is characterized by comprising the following steps: the method comprises the following steps:
the method comprises the following steps: the flow structure of the scratch detection system is as follows:
establishing a special image acquisition platform, researching an illumination unit based on a coaxial light source, transmitting the acquired image to an upper computer, manufacturing an image training set, obtaining a high-precision scratch characteristic image through U _ Net deep learning network training, distinguishing scratches from similar defects on the basis, and finally completing measurement of the position, the number and the length and the width of the scratches through a corresponding algorithm;
step two: analyzing factors influencing image acquisition quality:
the coaxial light source is defined as that the light source is diffused by the diffusion plate to irradiate the semi-transparent semi-reflective light splitting sheet, and the light splitting sheet reflects the light to an object and then reflects the light to the lens by the object; detecting bruises, scratches, cracks and foreign bodies on the flat and smooth surface of an object; the images collected by the illumination environments with different colors and intensities are compared under the control of a computer, and more complete and accurate image information is comprehensively obtained;
step three: the scratch image and other similar defects are distinguished and studied:
the method comprises the steps of segmenting a scratch image by adopting an RGB three-channel u _ net network, and realizing more accurate embodiment of scratch edges by respectively convolving three color channels; the optimal illumination condition is found through experiments, meanwhile, the resolution of the camera is improved as much as possible, the original characteristics of the image are guaranteed, high-precision samples are provided for subsequent deep learning training, and the detection precision is improved;
step four: scratch detection algorithm study:
detecting scratches mainly includes three aspects: area positioning, quantity statistics and length measurement;
4.1, area positioning and quantity statistics are realized by adopting a contour query method, firstly, contour extraction is carried out on a scratch image, after the contour image is obtained, four vertex coordinates A (x1, y1), B (x2, y2), C (x3, y3) and D (x4, y4) of pixels of the contour extraction are traversed to limit the scratch area, the length and the width of the scratch area are obtained through coordinate point difference, the coordinate position of the scratch area is output, and the quantity of scratches is counted;
4.2, measuring the length of the scratch by adopting a K3M algorithm, wherein the K3M skeleton extraction algorithm is a continuous iterative algorithm and consists of an iterative part of seven steps and a single terminal additional step, and after the scratch skeleton is obtained, counting the pixel points of the scratch skeleton to obtain the arc length of the scratch; the scratch arc length expression is shown in formula 1:
wherein, L is the arc length of the scratch area and is in mm, lp is the actual length corresponding to a single pixel and is in mm; g (x, y) represents connected domain pixel points of the scratch extracted by the K3M algorithm framework; and finally, converting the actual distance represented by the pixel according to the pixel and the real length.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010422041.5A CN111551350A (en) | 2020-05-18 | 2020-05-18 | Optical lens surface scratch detection method based on U _ Net network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010422041.5A CN111551350A (en) | 2020-05-18 | 2020-05-18 | Optical lens surface scratch detection method based on U _ Net network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111551350A true CN111551350A (en) | 2020-08-18 |
Family
ID=72006464
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010422041.5A Pending CN111551350A (en) | 2020-05-18 | 2020-05-18 | Optical lens surface scratch detection method based on U _ Net network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111551350A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112903720A (en) * | 2021-02-07 | 2021-06-04 | 电子科技大学 | Quantitative detection method for surface defects of lens of satellite telescope |
CN113012103A (en) * | 2021-02-07 | 2021-06-22 | 电子科技大学 | Quantitative detection method for surface defects of large-aperture telescope lens |
CN114266768A (en) * | 2022-03-01 | 2022-04-01 | 聚时科技(江苏)有限公司 | Method for generating surface scratch defect image |
CN114486939A (en) * | 2022-04-08 | 2022-05-13 | 欧普康视科技股份有限公司 | Lens scratch detection system and method |
CN116342589A (en) * | 2023-05-23 | 2023-06-27 | 之江实验室 | Cross-field scratch defect continuity detection method and system |
EP4343302A1 (en) * | 2022-09-26 | 2024-03-27 | Essilor International | Computer-implemented method for determining a localization of at least one defect in a tested ophthalmic lens |
CN117893532A (en) * | 2024-03-14 | 2024-04-16 | 山东神力索具有限公司 | Die crack defect detection method for die forging rigging based on image processing |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102735695A (en) * | 2012-06-04 | 2012-10-17 | 华中科技大学 | Rapid lens flaw detection method and apparatus thereof |
CN108956462A (en) * | 2018-05-15 | 2018-12-07 | 武汉科技大学 | A kind of color camera RGB image fusion vision detection system and detection method |
CN109489591A (en) * | 2018-12-17 | 2019-03-19 | 吉林大学 | Plane scratch length non-contact measurement method based on machine vision |
CN110060251A (en) * | 2019-04-26 | 2019-07-26 | 福州大学 | A kind of building surface crack detecting method based on U-Net |
CN111060525A (en) * | 2018-10-16 | 2020-04-24 | 苏州微微视视觉科技有限公司 | Equipment for detecting surface defects of metal target based on picture processing |
-
2020
- 2020-05-18 CN CN202010422041.5A patent/CN111551350A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102735695A (en) * | 2012-06-04 | 2012-10-17 | 华中科技大学 | Rapid lens flaw detection method and apparatus thereof |
CN108956462A (en) * | 2018-05-15 | 2018-12-07 | 武汉科技大学 | A kind of color camera RGB image fusion vision detection system and detection method |
CN111060525A (en) * | 2018-10-16 | 2020-04-24 | 苏州微微视视觉科技有限公司 | Equipment for detecting surface defects of metal target based on picture processing |
CN109489591A (en) * | 2018-12-17 | 2019-03-19 | 吉林大学 | Plane scratch length non-contact measurement method based on machine vision |
CN110060251A (en) * | 2019-04-26 | 2019-07-26 | 福州大学 | A kind of building surface crack detecting method based on U-Net |
Non-Patent Citations (1)
Title |
---|
林文伟: "基于深度学习的机箱表面细微划痕检测方法研究", 《中国优秀博硕士学位论文全文数据库(硕士) 信息科技辑》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112903720A (en) * | 2021-02-07 | 2021-06-04 | 电子科技大学 | Quantitative detection method for surface defects of lens of satellite telescope |
CN113012103A (en) * | 2021-02-07 | 2021-06-22 | 电子科技大学 | Quantitative detection method for surface defects of large-aperture telescope lens |
CN113012103B (en) * | 2021-02-07 | 2022-09-06 | 电子科技大学 | Quantitative detection method for surface defects of large-caliber telescope lens |
CN114266768A (en) * | 2022-03-01 | 2022-04-01 | 聚时科技(江苏)有限公司 | Method for generating surface scratch defect image |
CN114486939A (en) * | 2022-04-08 | 2022-05-13 | 欧普康视科技股份有限公司 | Lens scratch detection system and method |
EP4343302A1 (en) * | 2022-09-26 | 2024-03-27 | Essilor International | Computer-implemented method for determining a localization of at least one defect in a tested ophthalmic lens |
CN116342589A (en) * | 2023-05-23 | 2023-06-27 | 之江实验室 | Cross-field scratch defect continuity detection method and system |
CN116342589B (en) * | 2023-05-23 | 2023-08-22 | 之江实验室 | Cross-field scratch defect continuity detection method and system |
CN117893532A (en) * | 2024-03-14 | 2024-04-16 | 山东神力索具有限公司 | Die crack defect detection method for die forging rigging based on image processing |
CN117893532B (en) * | 2024-03-14 | 2024-05-24 | 山东神力索具有限公司 | Die crack defect detection method for die forging rigging based on image processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111551350A (en) | Optical lens surface scratch detection method based on U _ Net network | |
CN108520274B (en) | High-reflectivity surface defect detection method based on image processing and neural network classification | |
CN109840889A (en) | High-precision vision measurement method, device and system based on bionic Algorithm | |
CN109900711A (en) | Workpiece, defect detection method based on machine vision | |
CN111612737B (en) | Artificial board surface flaw detection device and detection method | |
CN115760654B (en) | Industrial microscope image processing system | |
CN110570412B (en) | Part error vision judgment system | |
CN112651968A (en) | Wood board deformation and pit detection method based on depth information | |
CN115082451B (en) | Stainless steel soup ladle defect detection method based on image processing | |
CN110108715B (en) | Defect detection method for transparent parallel flat plate | |
CN106709529B (en) | Visual detection method for photovoltaic cell color difference classification | |
CN115526889B (en) | Nondestructive testing method of boiler pressure pipeline based on image processing | |
CN113177924A (en) | Industrial production line product flaw detection method | |
CN109584259B (en) | Quartz crucible bubble layered counting device and method | |
CN114280075B (en) | Online visual detection system and detection method for surface defects of pipe parts | |
CN111624203A (en) | Relay contact alignment non-contact measurement method based on machine vision | |
CN114252449A (en) | Aluminum alloy weld surface quality detection system and method based on line structured light | |
CN114494169A (en) | Industrial flexible object detection method based on machine vision | |
CN112326683B (en) | Method for correcting and detecting lens cleanliness by utilizing spectral difference flat field | |
CN117078608B (en) | Double-mask guide-based high-reflection leather surface defect detection method | |
CN111879791B (en) | Machine vision system and method for enhancing raised features on pattern surface | |
CN111192261A (en) | Method for identifying lens defect types | |
CN110579184A (en) | Product appearance online detection device and use method thereof | |
CN116245793A (en) | Color ring resistor resistance value detection method based on vision | |
CN115035071A (en) | Visual detection method for black spot defect of PAD light guide plate |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200818 |