CN110838149A - Camera light source automatic configuration method and system - Google Patents
Camera light source automatic configuration method and system Download PDFInfo
- Publication number
- CN110838149A CN110838149A CN201911162753.1A CN201911162753A CN110838149A CN 110838149 A CN110838149 A CN 110838149A CN 201911162753 A CN201911162753 A CN 201911162753A CN 110838149 A CN110838149 A CN 110838149A
- Authority
- CN
- China
- Prior art keywords
- camera
- image
- flaw
- contour
- area
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Geometry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
- Studio Devices (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a camera light source automatic configuration method and a system, comprising the following steps: generating a marker image template; establishing a camera configuration lookup table, wherein each element corresponds to different camera configuration parameters; placing the flaw area markers in flaw areas of the cloth, and controlling cameras to shoot according to the configuration parameters of the cameras to obtain a plurality of cloth images; matching the marker image template with each cloth image to obtain a flaw area image; marking the flaw outline of each flaw area image to obtain a real flaw outline; extracting the outline of each flaw area image by adopting an edge detection method to obtain a detected flaw outline; and calculating the intersection ratio of the overlapping areas between the real flaw outline and the detected flaw outline for each flaw area image, and taking the camera configuration parameter corresponding to the flaw area image with the largest intersection ratio of the overlapping areas as the camera light source configuration of the camera. The invention has simple operation and saves a large amount of labor cost; and errors caused by judgment by human experience are avoided.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a method and a system for automatically configuring a camera light source.
Background
Flaw detection is an important link in the cloth generation process. In this process, in order to ensure the quality of the cloth, various defects which may exist on the cloth, such as holes, dirt, silks, etc., need to be carefully checked. Some fully automatic detection schemes based on computer vision already exist on the market today. The principle is as follows: 1. and shooting the cloth by using a camera to obtain a cloth image. 2. The defect type in the image is identified by using a deep learning technology or a traditional image identification method.
In the full-automatic cloth flaw detection process, a professional camera and a light source are generally needed to obtain an ideal cloth image. Aiming at different cloth colors, materials and flaw types, different camera parameters (exposure time, color gain and the like) and light source brightness need to be set, and the optimal imaging effect is achieved. For example, light colored cloth typically requires relatively small camera exposure times and dark light sources; dark cloth usually requires a relatively large camera exposure time and a bright light source; the color gain also needs to be adjusted according to the circumstances. The precise camera and light source configuration scheme has the effect of achieving double results with little effort on improving the detection precision of the cloth flaws.
The traditional camera and light source configuration scheme needs workers to manually debug different parameters and make a decision by experience, has certain subjectivity, and is very complicated in process.
Disclosure of Invention
The present invention provides a method and a system for automatically configuring a camera light source to solve the above-mentioned technical problems.
In order to achieve the purpose, the invention adopts the following technical scheme:
the provided camera light source automatic configuration method is applied to a cloth flaw detection task and specifically comprises the following steps:
step S1, obtaining a marker image of a prefabricated flaw area marker, and generating a marker image template according to the marker image;
step S2, establishing a camera configuration lookup table, wherein each element in the camera configuration lookup table corresponds to different camera configuration parameters respectively;
step S3, placing the flaw area markers in the flaw areas of the cloth, and controlling a camera to shoot according to the camera configuration parameters in the camera configuration lookup table to obtain a plurality of cloth images;
each cloth image corresponds to one camera configuration parameter;
step S4, matching the marker image template with each cloth image respectively to obtain a flaw area image corresponding to each cloth image;
step S5, marking the flaw outline of each flaw area image to obtain a real flaw outline;
step S6, extracting the outline of each defective area image by adopting an edge detection method to obtain a detected defective outline;
step S7, for each defective region image, calculating an intersection ratio of overlapping areas between the real defective region outline and the detected defective region outline, and using the camera configuration parameter corresponding to the defective region image with the largest intersection ratio of the overlapping areas as a camera light source configuration of the camera.
As a preferred aspect of the present invention, the camera configuration parameters include one or more of a camera exposure time, a camera color gain, and a camera light source brightness.
As a preferred embodiment of the present invention, in the step S5, the marking result of the real defect contour is accurate to pixels.
As a preferable embodiment of the present invention, the step S6 specifically includes:
step S61, extracting the outline of each image of the defect area by adopting an edge detection method to obtain a plurality of outline images;
step S62 is to calculate the area of each of the contour images, and to take the contour image with the largest area as the detected defect contour.
As a preferable embodiment of the present invention, in step S7, the overlap area intersection ratio is calculated by using the following formula:
wherein,
IOU represents the overlapping area intersection ratio;
a represents the true flaw profile;
b represents the detected flaw profile.
An automatic camera light source configuration system applying any one of the above automatic camera light source configuration methods, the automatic camera light source configuration system specifically includes:
the template generating module is used for acquiring a marker image of a prefabricated defective area marker and generating a marker image template according to the marker image;
the camera configuration lookup table establishing module is used for establishing a camera configuration lookup table, and each element in the camera configuration lookup table corresponds to different camera configuration parameters respectively;
the image acquisition module is connected with the lookup table establishing module and used for controlling a camera to shoot a defect area of the cloth with the defect area markers placed on the defect area according to the camera configuration parameters in the camera configuration lookup table to obtain a plurality of cloth images;
the template matching module is respectively connected with the template generating module and the image acquiring module and is used for matching the marker image template with each cloth image to obtain a flaw area image corresponding to each cloth image;
the contour marking module is connected with the template matching module and used for marking the flaw contour of each flaw area image to obtain a real flaw contour;
the contour extraction module is connected with the template matching module and used for extracting the contour of each defective area image by adopting an edge detection method to obtain a detected defective contour;
and the automatic configuration module is respectively connected with the contour marking module and the contour extraction module and is used for calculating the intersection ratio of the overlapping areas between the real defect contour and the detected defect contour aiming at each defect region image, and taking the camera configuration parameter corresponding to the defect region image with the largest intersection ratio of the overlapping areas as the camera light source configuration of the camera.
As a preferred aspect of the present invention, the contour extraction module specifically includes:
the first extraction unit is used for extracting the outline of each defective area image by adopting an edge detection method to obtain a plurality of outline images;
and the second extraction unit is connected with the first extraction unit and used for respectively calculating the area of each contour image and taking the contour image with the largest area as the detected flaw contour.
The invention has the beneficial effects that:
1) the operation is simple, and a large amount of labor cost is saved;
2) the advantages and disadvantages of the camera and light source configuration schemes can be quantitatively described, and errors caused by judgment by human experience are avoided;
3) the process is organized and streamlined, the result is accurate, and the repeatability is high.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required to be used in the embodiments of the present invention will be briefly described below. It is obvious that the drawings described below are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
Fig. 1 is a schematic flowchart of a method for automatically configuring a camera light source according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating a method for detecting a defect contour according to an embodiment of the invention.
Fig. 3 is a schematic structural diagram of an automatic configuration system of a camera light source according to an embodiment of the present invention.
Fig. 4 is a flowchart of a method for automatically configuring a camera light source according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further explained by the specific implementation mode in combination with the attached drawings.
Wherein the showings are for the purpose of illustration only and are shown by way of illustration only and not in actual form, and are not to be construed as limiting the present patent; to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right", "inner", "outer", etc. are used for indicating the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not indicated or implied that the referred device or element must have a specific orientation, be constructed in a specific orientation and be operated, and therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and are not to be construed as limitations of the present patent, and the specific meanings of the terms may be understood by those skilled in the art according to specific situations.
In the description of the present invention, unless otherwise explicitly specified or limited, the term "connected" or the like, if appearing to indicate a connection relationship between the components, is to be understood broadly, for example, as being fixed or detachable or integral; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or may be connected through one or more other components or may be in an interactive relationship with one another. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Aiming at the problems in the prior art, the invention provides an automatic camera light source configuration method, which is applied to a cloth defect detection task and specifically comprises the following steps as shown in fig. 1 and 4:
step S1, obtaining a marker image of a prefabricated flaw area marker, and generating a marker image template according to the marker image;
step S2, establishing a camera configuration lookup table, wherein each element in the camera configuration lookup table corresponds to different camera configuration parameters respectively;
step S3, placing the flaw area markers in the flaw areas of the cloth, and controlling the cameras to shoot according to the camera configuration parameters in the camera configuration lookup table to obtain a plurality of cloth images;
each cloth image corresponds to a camera configuration parameter;
step S4, matching the marker image template with each cloth image respectively to obtain a flaw area image corresponding to each cloth image;
step S5, marking the flaw outline of each flaw area image to obtain a real flaw outline;
step S6, extracting the outline of each defective area image by adopting an edge detection method to obtain a detected defective outline;
step S7, for each defective area image, calculating an overlap area intersection ratio between the real defective area outline and the detected defective area outline, and using a camera configuration parameter corresponding to the defective area image with the largest overlap area intersection ratio as a camera light source configuration of the camera.
Specifically, in this embodiment, the flawless cloth is generally uniform in color and fine and clear in texture. When flaws, such as dirt, holes, silks and the like, appear, the overall uniformity of the cloth is damaged, and the positions where the flaws appear and the background have obvious differences. With some edge extraction methods, such as the Hollistincally-nested edge detection method, etc., in the case of sharp images, the edges of flaws can be extracted. The extraction effect of the flaw edge can reflect the shooting effect of the flaw in the image to a certain extent. In this embodiment, the advantages and disadvantages of the camera and the light source configuration are quantitatively described by comparing the automatic extraction effect of the defect edge with the manual mark.
More specifically, it is necessary to prepare a defective area marker, preferably a small frame-like object, and to select a defective area on the cloth by frame. After a marker image of the defect area marker is acquired, a marker image template is generated from the marker image. It is also necessary to build a camera configuration look-up table, each element of which corresponds to a different camera configuration parameter including, but not limited to, camera exposure time, camera color gain, and camera light source brightness combination.
And then selecting a certain obvious flaw on the cloth, placing a flaw area marker at the position where the flaw appears on the cloth, and shooting the cloth to obtain a plurality of cloth images according to the camera configuration parameters in the camera configuration lookup table, preferably by changing the camera parameters and the light source brightness through a serial port program, wherein the shooting times are equal to the number of elements in the camera configuration lookup table. Preferably, a plurality of images are taken at a time under control of a computer program.
And then, carrying out template matching according to a marker image template to obtain the positions of the markers of the flaw areas in the cloth picture, and further obtaining the areas where flaws appear, namely flaw area images. And manually marking each defective area image and extracting by adopting an edge detection method to obtain a real defective outline and a detected defective outline corresponding to each defective area image. Preferably, the manual marking is performed to pixel accuracy to obtain a true flaw profile.
And finally, calculating an IOU between the real flaw outline and the detected flaw outline, wherein the IOU is named as an intersectionover intersection, namely, an overlap area intersection ratio, each flaw area image corresponds to one overlap area intersection ratio, and preferably, a camera configuration parameter corresponding to the flaw area image with the largest IOU is selected as the camera light source configuration of the camera. Because the image of the defect area with the largest IOU represents the best shooting quality, and the recognition effect of the defect is better, the defect and the cloth background have the largest contrast, and the camera configuration parameters in the corresponding camera configuration lookup table are the best configuration of the camera light source. The method has better effect on pure-color cloth generally.
As a preferred aspect of the present invention, the camera configuration parameters include one or more of camera exposure time, camera color gain, and camera light source brightness.
In a preferred embodiment of the present invention, in step S5, the marking result of the real defect contour is accurate to pixels.
As a preferable embodiment of the present invention, as shown in fig. 2, step S6 specifically includes:
step S61, extracting the outline of each image with an edge detection method to obtain a plurality of outline images;
in step S62, the area of each contour image is calculated, and the contour image having the largest area is set as the detected defect contour.
As a preferred embodiment of the present invention, in step S7, the intersection ratio is calculated by using the following formula:
wherein,
IOU represents the overlapping area intersection ratio;
a represents the true flaw profile;
b denotes the detected flaw profile.
An automatic camera light source configuration system applying any one of the above automatic camera light source configuration methods is shown in fig. 3, and specifically includes:
the template generating module 1 is used for acquiring a marker image of a prefabricated defective area marker and generating a marker image template according to the marker image;
the lookup table establishing module 2 is used for establishing a camera configuration lookup table, and each element in the camera configuration lookup table corresponds to different camera configuration parameters respectively;
the image acquisition module 3 is connected with the lookup table establishing module 2 and is used for controlling the camera to shoot the defect area of the cloth with the defect area markers according to the camera configuration parameters in the camera configuration lookup table to obtain a plurality of cloth images;
the template matching module 4 is respectively connected with the template generating module 1 and the image obtaining module 3 and is used for matching the marker image template with each cloth image to obtain a flaw area image corresponding to each cloth image;
the outline marking module 5 is connected with the template matching module 4 and used for marking the flaw outline of each flaw area image to obtain a real flaw outline;
the contour extraction module 6 is connected with the template matching module 4 and is used for extracting the contour of each image of the flaw area by adopting an edge detection method to obtain a detected flaw contour;
and the automatic configuration module 7 is respectively connected with the contour marking module 5 and the contour extraction module 6 and is used for calculating the intersection ratio of the overlapping areas between the real defect contour and the detected defect contour for each defect region image, and taking the camera configuration parameter corresponding to the defect region image with the largest intersection ratio of the overlapping areas as the camera light source configuration of the camera.
As a preferred embodiment of the present invention, the contour extraction module 6 specifically includes:
the first extraction unit 61 is configured to perform contour extraction on each defective area image by using an edge detection method to obtain a plurality of contour images;
and the second extraction unit 62 is connected with the first extraction unit 61 and used for respectively calculating the area of each contour image and taking the contour image with the largest area as the detected flaw contour.
It should be understood that the above-described embodiments are merely preferred embodiments of the invention and the technical principles applied thereto. It will be understood by those skilled in the art that various modifications, equivalents, changes, and the like can be made to the present invention. However, such variations are within the scope of the invention as long as they do not depart from the spirit of the invention. In addition, certain terms used in the specification and claims of the present application are not limiting, but are used merely for convenience of description.
Claims (7)
1. A camera light source automatic configuration method is applied to a cloth flaw detection task and is characterized by comprising the following steps:
step S1, obtaining a marker image of a prefabricated flaw area marker, and generating a marker image template according to the marker image;
step S2, establishing a camera configuration lookup table, wherein each element in the camera configuration lookup table corresponds to different camera configuration parameters respectively;
step S3, placing the flaw area markers in the flaw areas of the cloth, and controlling a camera to shoot according to the camera configuration parameters in the camera configuration lookup table to obtain a plurality of cloth images;
each cloth image corresponds to one camera configuration parameter;
step S4, matching the marker image template with each cloth image respectively to obtain a flaw area image corresponding to each cloth image;
step S5, marking the flaw outline of each flaw area image to obtain a real flaw outline;
step S6, extracting the outline of each defective area image by adopting an edge detection method to obtain a detected defective outline;
step S7, for each defective region image, calculating an intersection ratio of overlapping areas between the real defective region outline and the detected defective region outline, and using the camera configuration parameter corresponding to the defective region image with the largest intersection ratio of the overlapping areas as a camera light source configuration of the camera.
2. The method of claim 1, wherein the camera configuration parameters include one or more of camera exposure time, camera color gain, and camera light source brightness.
3. The method for automatically configuring a light source of a camera according to claim 1, wherein in the step S5, the labeling result of the real defect contour is accurate to a pixel.
4. The method for automatically configuring a camera light source according to claim 1, wherein the step S6 specifically comprises:
step S61, extracting the outline of each image of the defect area by adopting an edge detection method to obtain a plurality of outline images;
step S62 is to calculate the area of each of the contour images, and to take the contour image with the largest area as the detected defect contour.
5. The method for automatically configuring a light source of a camera according to claim 1, wherein in the step S7, the overlap area intersection ratio is calculated by using the following formula:
wherein,
IOU represents the overlapping area intersection ratio;
a represents the true flaw profile;
b represents the detected flaw profile.
6. An automatic camera light source configuration system, which is characterized by applying the automatic camera light source configuration method according to any one of claims 1 to 5, and specifically comprises:
the template generating module is used for acquiring a marker image of a prefabricated defective area marker and generating a marker image template according to the marker image;
the camera configuration lookup table establishing module is used for establishing a camera configuration lookup table, and each element in the camera configuration lookup table corresponds to different camera configuration parameters respectively;
the image acquisition module is connected with the lookup table establishing module and used for controlling a camera to shoot a defect area of the cloth with the defect area markers placed on the defect area according to the camera configuration parameters in the camera configuration lookup table to obtain a plurality of cloth images;
the template matching module is respectively connected with the template generating module and the image acquiring module and is used for matching the marker image template with each cloth image to obtain a flaw area image corresponding to each cloth image;
the contour marking module is connected with the template matching module and used for marking the flaw contour of each flaw area image to obtain a real flaw contour;
the contour extraction module is connected with the template matching module and used for extracting the contour of each defective area image by adopting an edge detection method to obtain a detected defective contour;
and the automatic configuration module is respectively connected with the contour marking module and the contour extraction module and is used for calculating the intersection ratio of the overlapping areas between the real defect contour and the detected defect contour aiming at each defect region image, and taking the camera configuration parameter corresponding to the defect region image with the largest intersection ratio of the overlapping areas as the camera light source configuration of the camera.
7. The camera light source auto-configuration system of claim 6, wherein the contour extraction module specifically comprises:
the first extraction unit is used for extracting the outline of each defective area image by adopting an edge detection method to obtain a plurality of outline images;
and the second extraction unit is connected with the first extraction unit and used for respectively calculating the area of each contour image and taking the contour image with the largest area as the detected flaw contour.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911162753.1A CN110838149B (en) | 2019-11-25 | 2019-11-25 | Camera light source automatic configuration method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911162753.1A CN110838149B (en) | 2019-11-25 | 2019-11-25 | Camera light source automatic configuration method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110838149A true CN110838149A (en) | 2020-02-25 |
| CN110838149B CN110838149B (en) | 2020-10-23 |
Family
ID=69577187
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911162753.1A Active CN110838149B (en) | 2019-11-25 | 2019-11-25 | Camera light source automatic configuration method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110838149B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111402341A (en) * | 2020-03-10 | 2020-07-10 | 创新奇智(广州)科技有限公司 | Camera parameter determination method and device, electronic equipment and readable storage medium |
| CN112116668A (en) * | 2020-11-23 | 2020-12-22 | 常州微亿智造科技有限公司 | Optical copying method and device for quality inspection and quality inspection equipment |
| CN112270329A (en) * | 2020-10-30 | 2021-01-26 | 北京华维国创电子科技有限公司 | Accurate MARK point acquisition and identification algorithm based on multi-level algorithm fusion |
| CN112270687A (en) * | 2020-10-16 | 2021-01-26 | 鲸斛(上海)智能科技有限公司 | Cloth flaw identification model training method and cloth flaw detection method |
| CN114486903A (en) * | 2021-12-06 | 2022-05-13 | 浙江大学台州研究院 | Gray-scale self-adaptive coiled material detection system, device and algorithm |
| CN115508282A (en) * | 2022-10-18 | 2022-12-23 | 广东纱纤亿信息科技股份有限公司 | Online intelligent cloth inspection detection system |
| CN117191701A (en) * | 2023-08-25 | 2023-12-08 | 常州超音速智能装备有限公司 | Test method, system, platform and storage medium suitable for polishing quantification |
| WO2024161479A1 (en) * | 2023-01-30 | 2024-08-08 | 日本電信電話株式会社 | Evaluation device, evaluation method, and evaluation program |
| CN118570178A (en) * | 2024-06-11 | 2024-08-30 | 德车工坊(北京)科技有限公司 | Vehicle pre-inspection data processing method and platform |
| TWI863447B (en) * | 2023-07-21 | 2024-11-21 | 財團法人紡織產業綜合研究所 | Fabric detecting apparatus and fabric detecting method |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103529051A (en) * | 2013-11-01 | 2014-01-22 | 南通大学 | Method for automatic on-line detection of detects of woven textile |
| CN103841323A (en) * | 2014-02-20 | 2014-06-04 | 小米科技有限责任公司 | Shooting parameter allocation method and device and terminal device |
| CN106303243A (en) * | 2016-08-19 | 2017-01-04 | 乐视控股（北京）有限公司 | A kind of photographic method, device and terminal |
| CN106872487A (en) * | 2017-04-21 | 2017-06-20 | 佛山市南海区广工大数控装备协同创新研究院 | The surface flaw detecting method and device of a kind of view-based access control model |
| CN107063099A (en) * | 2017-04-11 | 2017-08-18 | 吉林大学 | A kind of machinery manufacturing industry online quality monitoring method of view-based access control model system |
| CN104463969B (en) * | 2014-12-09 | 2017-09-26 | 广西界围信息科技有限公司 | A kind of method for building up of the model of geographical photo to aviation tilt |
| CN107796825A (en) * | 2016-09-01 | 2018-03-13 | 宁波舜宇光电信息有限公司 | Device inspection method |
| CN108769542A (en) * | 2018-05-30 | 2018-11-06 | 北京图森未来科技有限公司 | A kind of exposure parameter determines method, apparatus and readable medium |
| CN109064459A (en) * | 2018-07-27 | 2018-12-21 | 江苏理工学院 | A kind of Fabric Defect detection method based on deep learning |
| CN109454006A (en) * | 2018-10-08 | 2019-03-12 | 杭州慧知连科技有限公司 | Chemical fiber wire ingot is stumbled the device and its detection stage division of a defect on-line checking and classification |
| EP3489664A1 (en) * | 2017-11-28 | 2019-05-29 | Henkel IP & Holding GmbH | Systems and methods for analyzing stained fabric articles |
| CN110057832A (en) * | 2019-04-24 | 2019-07-26 | 拓卡奔马机电科技有限公司 | A kind of fabric flaws detecting and controlling system on layout machine |
| CN110465749A (en) * | 2019-09-12 | 2019-11-19 | 深圳市聚鑫极光科技有限公司 | A kind of laser marking machine and positioning marking method |
-
2019
- 2019-11-25 CN CN201911162753.1A patent/CN110838149B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103529051A (en) * | 2013-11-01 | 2014-01-22 | 南通大学 | Method for automatic on-line detection of detects of woven textile |
| CN103841323A (en) * | 2014-02-20 | 2014-06-04 | 小米科技有限责任公司 | Shooting parameter allocation method and device and terminal device |
| CN104463969B (en) * | 2014-12-09 | 2017-09-26 | 广西界围信息科技有限公司 | A kind of method for building up of the model of geographical photo to aviation tilt |
| CN106303243A (en) * | 2016-08-19 | 2017-01-04 | 乐视控股（北京）有限公司 | A kind of photographic method, device and terminal |
| CN107796825A (en) * | 2016-09-01 | 2018-03-13 | 宁波舜宇光电信息有限公司 | Device inspection method |
| CN107063099A (en) * | 2017-04-11 | 2017-08-18 | 吉林大学 | A kind of machinery manufacturing industry online quality monitoring method of view-based access control model system |
| CN106872487A (en) * | 2017-04-21 | 2017-06-20 | 佛山市南海区广工大数控装备协同创新研究院 | The surface flaw detecting method and device of a kind of view-based access control model |
| EP3489664A1 (en) * | 2017-11-28 | 2019-05-29 | Henkel IP & Holding GmbH | Systems and methods for analyzing stained fabric articles |
| CN108769542A (en) * | 2018-05-30 | 2018-11-06 | 北京图森未来科技有限公司 | A kind of exposure parameter determines method, apparatus and readable medium |
| CN109064459A (en) * | 2018-07-27 | 2018-12-21 | 江苏理工学院 | A kind of Fabric Defect detection method based on deep learning |
| CN109454006A (en) * | 2018-10-08 | 2019-03-12 | 杭州慧知连科技有限公司 | Chemical fiber wire ingot is stumbled the device and its detection stage division of a defect on-line checking and classification |
| CN110057832A (en) * | 2019-04-24 | 2019-07-26 | 拓卡奔马机电科技有限公司 | A kind of fabric flaws detecting and controlling system on layout machine |
| CN110465749A (en) * | 2019-09-12 | 2019-11-19 | 深圳市聚鑫极光科技有限公司 | A kind of laser marking machine and positioning marking method |
Non-Patent Citations (2)
| Title |
|---|
| ZHOUFENG LIU 等: "abric Defects Detection based on Multi-Sources Features Fusion", 《PROCEEDINGS OF THE 2019 8TH INTERNATIONAL CONFERENCE ON COMPUTING AND PATTERN RECOGNITION》 * |
| 胡峰: "基于机器视觉的布料瑕疵检测若干关键技术研究与实现", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111402341A (en) * | 2020-03-10 | 2020-07-10 | 创新奇智(广州)科技有限公司 | Camera parameter determination method and device, electronic equipment and readable storage medium |
| CN112270687A (en) * | 2020-10-16 | 2021-01-26 | 鲸斛(上海)智能科技有限公司 | Cloth flaw identification model training method and cloth flaw detection method |
| CN112270329A (en) * | 2020-10-30 | 2021-01-26 | 北京华维国创电子科技有限公司 | Accurate MARK point acquisition and identification algorithm based on multi-level algorithm fusion |
| CN112116668A (en) * | 2020-11-23 | 2020-12-22 | 常州微亿智造科技有限公司 | Optical copying method and device for quality inspection and quality inspection equipment |
| CN112116668B (en) * | 2020-11-23 | 2021-04-06 | 常州微亿智造科技有限公司 | Optical copying method and device for quality inspection and quality inspection equipment |
| CN114486903B (en) * | 2021-12-06 | 2024-05-14 | 浙江大学台州研究院 | A grayscale adaptive coil detection system, device and algorithm |
| CN114486903A (en) * | 2021-12-06 | 2022-05-13 | 浙江大学台州研究院 | Gray-scale self-adaptive coiled material detection system, device and algorithm |
| CN115508282A (en) * | 2022-10-18 | 2022-12-23 | 广东纱纤亿信息科技股份有限公司 | Online intelligent cloth inspection detection system |
| WO2024161479A1 (en) * | 2023-01-30 | 2024-08-08 | 日本電信電話株式会社 | Evaluation device, evaluation method, and evaluation program |
| TWI863447B (en) * | 2023-07-21 | 2024-11-21 | 財團法人紡織產業綜合研究所 | Fabric detecting apparatus and fabric detecting method |
| CN117191701A (en) * | 2023-08-25 | 2023-12-08 | 常州超音速智能装备有限公司 | Test method, system, platform and storage medium suitable for polishing quantification |
| CN118570178A (en) * | 2024-06-11 | 2024-08-30 | 德车工坊(北京)科技有限公司 | Vehicle pre-inspection data processing method and platform |
| CN118570178B (en) * | 2024-06-11 | 2025-01-07 | 德车工坊(北京)科技有限公司 | Vehicle pre-inspection data processing method and platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110838149B (en) | 2020-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110838149B (en) | Camera light source automatic configuration method and system | |
| CN112669394B (en) | Automatic calibration method for vision detection system | |
| JP4436810B2 (en) | Display multi-angle measuring system and method | |
| CN111025701B (en) | Curved surface liquid crystal screen detection method | |
| CN103162939A (en) | Camera lens focusing detection method and device using the same | |
| CN110769229A (en) | Method, device and system for detecting color brightness of projection picture | |
| JP2007188128A (en) | Measurement method and measurement device using color image | |
| CN113639630A (en) | Dimensional measuring instrument system based on multi-template matching and auto-focus function | |
| CN109712115B (en) | Automatic PCB detection method and system | |
| CN106773158A (en) | A kind of movable type seeks liquid crystal display pixel qualities analytical equipment and a method certainly | |
| KR102726317B1 (en) | Laser modification method, laser modification device | |
| CN113467664A (en) | Size measuring instrument using method based on template matching | |
| CN108171669A (en) | A kind of image correction method based on OpenCV algorithms | |
| JPH08254499A (en) | Displaying/appearance inspection device | |
| CN103905762B (en) | Method for automatically detecting projection picture for projection module | |
| CN114677326B (en) | Device, system and method for detecting surface flaws of shell of printing mobile phone based on machine vision and deep learning | |
| CN111127462A (en) | Ready-made garment printing defect detection system and detection method based on multi-exposure imaging | |
| JP4470659B2 (en) | Model registration method for parts inspection and inspection data creation apparatus using this method | |
| CN114486902B (en) | Quality detection system and method | |
| CN113689495A (en) | Hole center detection method based on deep learning and hole center detection device thereof | |
| CN113645398A (en) | Dimension measuring instrument system based on automatic focusing function | |
| CN113624129A (en) | Real-time measurement method of dimension measurement instrument | |
| JP3289070B2 (en) | Mounted parts inspection device | |
| JP2019215348A (en) | Image inspection robot | |
| US12332421B2 (en) | Microscopy system and method for the color correction of microscope images |
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 |