CN111815632A - Visual inspection method and device for sewing stitches - Google Patents
Visual inspection method and device for sewing stitches Download PDFInfo
- Publication number
- CN111815632A CN111815632A CN202010910731.5A CN202010910731A CN111815632A CN 111815632 A CN111815632 A CN 111815632A CN 202010910731 A CN202010910731 A CN 202010910731A CN 111815632 A CN111815632 A CN 111815632A
- Authority
- CN
- China
- Prior art keywords
- sewing
- stitch
- center
- straight line
- product
- 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
- 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
- G06T7/0008—Industrial image inspection checking presence/absence
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Sewing Machines And Sewing (AREA)
Abstract
The invention relates to the technical field of machine vision, in particular to a visual detection method of sewing stitches, which comprises the following steps: step S1: establishing a database of different sewing products; step S2: correspondingly inputting parameters of the jumper defects of different sewing products and inputting parameters of the uneven sewing threads; step S3: adjusting the brightness of the backlight source; step S4: and acquiring the image and judging whether the sewing product in the image has defects or not according to the jumper defect parameter and/or the uneven sewing defect parameter corresponding to the sewing product in the image. The invention also provides a visual detection device for the sewing stitches, which comprises an industrial camera, an infrared backlight source and a control cabinet, wherein the industrial camera is electrically connected with the control cabinet, the infrared backlight source is electrically connected with the control cabinet, and the sewing products are positioned between the industrial camera and the infrared backlight source.
Description
Technical Field
The invention relates to the technical field of machine vision, in particular to a visual detection method and device for sewing stitches.
Background
Most sewing stitch detection on the market is carried out in a manual visual inspection mode at present, the problems of fatigue and reduced attention can occur after manual detection operation is carried out for a long time, so that the problems of influencing detection rate and reducing production efficiency, such as false detection or missing detection and the like are easily caused in the detection process, sewing products with defects are easy to flow into the market, the reputation of enterprises is influenced, and the production benefits of the enterprises are not facilitated; and the sewing machine is more prone to hurt the detection personnel with fatigue and reduced attention when in work, and certain potential safety hazards exist.
Therefore, the prior art is not sufficient and needs to be improved.
Disclosure of Invention
In order to overcome the technical problems, the invention provides a visual detection method and device for sewing stitches.
The invention provides a visual inspection method for sewing stitches, which solves the technical problem and comprises the following steps:
step S1: establishing a database of different sewing products;
step S2: correspondingly inputting parameters of the jumper defects of different sewing products and inputting parameters of the uneven sewing threads;
step S3: adjusting the brightness of the backlight source;
step S4: and acquiring the image and judging whether the sewing product in the image has defects or not according to the jumper defect parameter and/or the uneven sewing defect parameter corresponding to the sewing product in the image.
Preferably, the step S4 further includes the steps of:
step S41: collecting an image;
step S42: determining the specific type of the sewing product in the image;
step S43: fitting according to the light source background and the background polarity of the sewing product by a FindLine algorithm to obtain an edge straight line L1 of the left sewing line of the sewing product, an angle B formed by the straight line L1 and a horizontal line and a straight line central point coordinate (center X1, center Y1);
step S44: expanding the Image acquired in the step S41 to obtain a straight line through which pinholes of a left stitch and a right stitch in the sewn product are respectively connected to form an Image 1;
step S45: determining an interested area of the left stitch of the sewing product by combining the straight line angle B and the Image1, and combining the searched left line of the sewing thread in the step S43 according to the left stitch product background and the background after the left stitch hole site processing by using a FindLine algorithm and parameter fitting to obtain a left stitch straight line L2 and straight line center coordinates (center X2, center Y2);
step S46: determining an interested area of a right stitch of the sewing product by combining the Image1 and the straight line angle B, and combining the searched left line of the sewing thread in the step S43 according to the background of the right stitch product and the processed background of the right stitch hole site by using a FindLine algorithm and parameter fitting to obtain a left stitch straight line L2 and straight line center coordinates (center X3, center Y3);
step S47: performing binarization processing and median processing on the Image in the step S41, and filtering the surface texture of the sewn product to obtain a processed Image 2;
step S48: determining the interested region of the left-stitch pinhole according to the Image2, the angle B and the straight line center coordinates (center X2, center Y2), and obtaining each center coordinate of the left-stitch pinhole through the Blob algorithm;
step S49: and (5) obtaining the distance between the pinholes of the left stitch by circular calculation, and determining whether the left stitch has the jumper defect or not by referring to the jumper defect parameters in the step S2.
Preferably, the step S4 further includes the steps of:
step S50: the distance D1 is obtained by making a perpendicular to the left-stitch straight line L2 by the straight-line center point coordinates (center x1, center y 1), and the distance D1 is compared with the parameter of the unevenness defect of the sewing thread recorded in step S2 to determine whether the left sewing thread is uneven.
Preferably, the step S4 further includes the steps of:
step S51: determining the interested region of the right-stitch pinhole according to the Image2, the angle B and the straight line center coordinates (center X3, center Y3), and obtaining each center coordinate of the right-stitch pinhole through a Blob algorithm;
step S52: and (5) obtaining the distance between every two pinholes of the right stitch through cyclic calculation, and determining whether the right stitch has a jumper defect or not by referring to the jumper defect parameters in the step S2.
Preferably, the step S4 further includes the steps of:
step S53: the distance D2 is obtained by making a perpendicular to the right-hand-stitch straight line L3 by the straight-line center point coordinates (center x1, center y 1), and the distance D2 is compared with the parameter of the unevenness defect of the sewing thread registered in step S2 to determine whether the right sewing thread is uneven.
The invention further provides a sewing stitch visual detection device, which adopts the sewing stitch visual detection method and comprises an industrial camera, an infrared backlight source and a control cabinet, wherein the industrial camera is electrically connected with the control cabinet, the infrared backlight source is electrically connected with the control cabinet, and the sewing product is positioned between the industrial camera and the infrared backlight source.
Preferably, sewing stitch visual inspection device still includes the display screen, display screen and control cabinet electric connection, the display screen is used for showing the image that industrial camera shot under infrared backlight opens.
Preferably, the model of the industrial camera is ZVIT-CA013-20GM, and the model of the lens matched with the industrial camera is ZVIT-C3516-2M.
Preferably, the model of the infrared backlight source is ZVIT-FLG 7070-IR.
Preferably, the infrared backlight source adopts an infrared light source with the wavelength of 850 nm.
Compared with the prior art, the visual detection method and the visual detection device for the sewing stitches have the following advantages that:
detect the defect of stitch department of sewing product through machine vision, compare in artifical the detection, have better detection rate, the less probability appears the false retrieval, the condition of lou examining, owing to need not the staff in the testing process, consequently can not produce the potential safety hazard to the staff, be favorable to promoting the outgoing of sewing product quality, promote the reputation of enterprise.
Drawings
FIG. 1 is a schematic view of a detailed flow structure of the visual inspection method of sewing stitches of the present invention.
Fig. 2 is a schematic structural flow chart of step S4 of the visual sewing stitch detection method of the present invention.
FIG. 3 is an image of a sewn product.
Fig. 4 is a processed image of the sewn product presented through step S43.
Fig. 5 is a processed image of the sewn product presented through step S45.
Fig. 6 is a processed image of the sewn product presented through step S46.
Fig. 7 is a processed image of the sewn product presented through step S52.
Fig. 8 is a processed image of the sewn product presented through step S53.
FIG. 9 is a schematic view showing a detailed connection structure of the visual inspection apparatus for sewing stitches of the present invention.
Description of reference numerals:
10. a sewing stitch visual detection device; 11. a control cabinet; 12. an industrial camera; 13. an infrared backlight source; 14. a display screen.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1-9, the present invention provides a visual inspection method for sewing stitches, comprising the following steps:
step S1: and establishing a database of different sewing products.
The database mainly includes names of different sewn products.
Step S2: and correspondingly inputting parameters of the jumper defects of different sewing products and inputting parameters of the uneven sewing threads.
And recording parameters corresponding to different sewing products when the jump line defect occurs and parameters when the sewing line is recorded with the uneven defect into a database so as to compare detected data with the parameters when the jump line defect occurs and the parameters when the sewing line is uneven when detecting the sewing products, thereby determining whether the sewing products have the jump line defect and/or the uneven defect of the sewing line. Specifically, the parameters of the jumper defect include a left-stitch jumper qualified range parameter and a right-stitch jumper qualified range parameter.
Step S3: and adjusting the brightness of the backlight source.
Specifically, different sewn products require different backlight brightness to meet the requirements for subsequent image acquisition. If the sewing product is thick and the material density is large, the brightness of the backlight source can be correspondingly increased, and if the sewing product is thin and the material density is small, the brightness of the backlight source can be correspondingly reduced. The backlight brightness can be actually adjusted, and the advantage of adjusting the backlight brightness is that the subsequently acquired image meets the requirements of subsequent processing.
Step S4: and acquiring the image and judging whether the sewing product in the image has defects or not according to the jumper defect parameter and/or the uneven sewing defect parameter corresponding to the sewing product in the image.
And determining whether the defects exist or not by detecting the jumping line defect parameters and/or the uneven sewing line defect parameters of the sewing products in the acquired images.
Preferably, step S4 further includes the steps of:
step S41: collecting an image;
step S42: the specific type of sewn product in the image is determined.
In particular, the determination of the specific type of sewn product may be selected by the operator in the database, and accordingly, the defect parameters for the specific sewn product may also be determined from the database.
Step S43: fitting according to the light source background and the background polarity of the sewing product by a FindLine algorithm to obtain an edge straight line L1 of the left sewing line of the sewing product, an angle B formed by the straight line L1 and a horizontal line and a straight line central point coordinate A point (center X1, center Y1);
step S44: expanding the Image acquired in the step S41 to obtain a straight line through which pinholes of a left stitch and a right stitch in a sewn product are respectively connected to form an Image 1;
step S45: determining an interested area of the left stitch of the sewing product by combining the straight line angle B and the Image1, and combining the searched left line of the sewing thread in the step S43 according to the left stitch product background and the background after the left stitch hole site processing by using a FindLine algorithm and parameter fitting to obtain a left stitch straight line L2 and a straight line center coordinate C point (center X2, center Y2);
step S46: determining an interested area of a right stitch of the sewing product by combining the Image1 and the straight line angle B, and combining the searched left line of the sewing thread in the step S43 according to the background of the right stitch product and the processed background of the right stitch hole site by using a FindLine algorithm and parameter fitting to obtain a left stitch straight line L2 and a straight line center coordinate D point (center X3, center Y3);
step S47: performing binarization processing and median processing on the Image in the step S41, and filtering the surface texture of the sewn product to obtain a processed Image 2;
step S48: determining the interested region of the left-stitch pinhole according to the Image2, the angle B and the straight line center coordinates (center X2, center Y2), and obtaining each center coordinate of the left-stitch pinhole through the Blob algorithm;
step S49: and (5) obtaining the distance between the pinholes of the left stitch by circular calculation, and determining whether the left stitch has the jumper defect or not by referring to the jumper defect parameters in the step S2.
Whether the left stitch has the jumper defect or not is detected when the sewn product in the image is located in the left stitch, the left stitch can be determined to have the jumper defect when the distance between every two pinholes of the left stitch is larger than the parameter which is recorded in the database and is related to the sewn product and has the jumper defect, and a worker can actually check the sewn product so as to finally determine the correctness of the jumper defect.
Step S50: the distance D1 is obtained by making a perpendicular line to the left-stitch straight line L2 from the straight-line center point coordinate E (center x1, center y 1), i.e., point a in fig. 4, and the distance D1 is compared with the parameter of the unevenness defect of the sewing thread recorded in step S2 to determine whether the left sewing thread is uneven.
By comparing the distance D1 with the parameters of the sewing line unevenness registered in the database, when the left sewing line is uneven, the distance D1 is not in the range of the parameters of the sewing line unevenness defect registered. The staff can carry out the actual examination once more to further confirm the exactness that the uneven defect of left side sewing line appears, compare in artifical range estimation, can reduce staff's work load through the detection to the image, change staff's work focus to final examination from preliminary detection, make the sewing product quality of leaving the factory or carrying out follow-up technology better, effectively reduce the probability that the substandard product flows, be favorable to promoting enterprise reputation.
Step S51: determining the interested region of the right-stitch pinhole according to the Image2, the angle B and the straight line center coordinates (center X3, center Y3), and obtaining each center coordinate of the right-stitch pinhole through a Blob algorithm;
step S52: and (5) obtaining the distance between every two pinholes of the right stitch through cyclic calculation, and determining whether the right stitch has a jumper defect or not by referring to the jumper defect parameters in the step S2.
Through the operation of the step, whether the right stitch of the sewing product has the jumper defect or not can be determined. Through the steps, whether the stitches on the two sides of the sewing product have the jumper defect or not can be determined.
Step S53: the distance D2 is obtained by making a perpendicular to the right-hand-stitch straight line L3 by the straight-line center point coordinates (center x1, center y 1), and the distance D2 is compared with the parameter of the unevenness defect of the sewing thread registered in step S2 to determine whether the right sewing thread is uneven.
It will be appreciated that when the right stitch line is non-uniform, the distance D1 is not within the range of parameters that register a stitch line non-uniformity defect. The worker may again perform the actual inspection to further confirm the correctness of the occurrence of the right sewing unevenness defect. The work intensity of workers can be reduced by detecting the images.
Through the step S4, whether the sewing product in the image has the defect of line jumping and/or uneven sewing line can be determined, the recovery processing of the sewing product with the defect is facilitated, the influence of unqualified defects on reputation of enterprises caused by market inflow is reduced, the labor intensity of workers is reduced, and the possibility of potential safety hazards is reduced.
Further, the invention also provides a sewing stitch visual detection device 10, which adopts the sewing stitch visual detection method, and comprises a control cabinet 11, an industrial camera 12, an infrared backlight source 13 and a display screen 14, wherein the control cabinet 11 is electrically connected with the industrial camera 12, the infrared backlight source 13 is electrically connected with the control cabinet 11, and the display screen 14 is electrically connected with the control cabinet 11. The industrial camera 12 is used for obtaining an image of a sewn product, the sewn product is located between the industrial camera 12 and the infrared backlight 13, the infrared backlight 13 irradiates the sewn product, the display screen 14 is used for displaying the image of the sewn product, and a worker can adjust the brightness emitted by the infrared backlight 13 according to the image displayed by the display screen 14 so that the collected image is suitable for processing of the control cabinet 11, and the control cabinet 11 is used for receiving and emitting a signal instruction and processing the image so as to determine whether the sewn product in the image has a jump line defect and/or a sewing line unevenness defect.
Preferably, the model of the industrial camera 11 is ZVIT-CA013-20GM, and the model of a lens matched with the industrial camera 11 is ZVIT-C3516-2M; the infrared backlight 12 is of the model ZVIT-FLG 7070-IR.
Preferably, the infrared backlight 12 employs an infrared light source having a wavelength of 850 nm.
Compared with the prior art, the visual detection method and the visual detection device for the sewing stitches have the following advantages that:
detect the defect of stitch department of sewing product through machine vision, compare in artifical the detection, have better detection rate, the less probability appears the false retrieval, the condition of lou examining, owing to need not the staff in the testing process, consequently can not produce the potential safety hazard to the staff, be favorable to promoting the outgoing of sewing product quality, promote the reputation of enterprise.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and any modifications, equivalents, improvements, etc. made within the spirit of the present invention should be included in the scope of the present invention.
Claims (10)
1. A visual inspection method for sewing stitches is characterized in that: the visual detection method of the sewing stitches comprises the following steps:
step S1: establishing a database of different sewing products;
step S2: correspondingly inputting parameters of the jumper defects of different sewing products and inputting parameters of the uneven sewing threads;
step S3: adjusting the brightness of the backlight source;
step S4: and acquiring the image and judging whether the sewing product in the image has defects or not according to the jumper defect parameter and/or the uneven sewing defect parameter corresponding to the sewing product in the image.
2. The visual inspection method of sewing stitches as set forth in claim 1, wherein: the step S4 further includes the steps of:
step S41: collecting an image;
step S42: determining the specific type of the sewing product in the image;
step S43: fitting according to the light source background and the background polarity of the sewing product by a FindLine algorithm to obtain an edge straight line L1 of the left sewing line of the sewing product, an angle B formed by the straight line L1 and a horizontal line and a straight line central point coordinate (center X1, center Y1);
step S44: expanding the Image acquired in the step S41 to obtain a straight line through which pinholes of a left stitch and a right stitch in a sewn product are respectively connected to form an Image 1;
step S45: determining an interested area of the left stitch of the sewing product by combining the straight line angle B and the Image1, and combining the searched left line of the sewing thread in the step S43 according to the left stitch product background and the background after the left stitch hole site processing by using a FindLine algorithm and parameter fitting to obtain a left stitch straight line L2 and straight line center coordinates (center X2, center Y2);
step S46: determining an interested area of a right stitch of the sewing product by combining the Image1 and the straight line angle B, and combining the searched left line of the sewing thread in the step S43 according to the background of the right stitch product and the processed background of the right stitch hole site by using a FindLine algorithm and parameter fitting to obtain a left stitch straight line L2 and straight line center coordinates (center X3, center Y3);
step S47: performing binarization processing and median processing on the Image in the step S41, and filtering the surface texture of the sewn product to obtain a processed Image 2;
step S48: determining the interested region of the left-stitch pinhole according to the Image2, the angle B and the straight line center coordinates (center X2, center Y2), and obtaining each center coordinate of the left-stitch pinhole through the Blob algorithm;
step S49: and (5) obtaining the distance between the pinholes of the left stitch by circular calculation, and determining whether the left stitch has the jumper defect or not by referring to the jumper defect parameters in the step S2.
3. The visual inspection method of sewing stitches as set forth in claim 2, wherein: the step S4 further includes the steps of:
step S50: the distance D1 is obtained by making a perpendicular to the left-stitch straight line L2 by the straight-line center point coordinates (center x1, center y 1), and the distance D1 is compared with the parameter of the unevenness defect of the sewing thread recorded in step S2 to determine whether the left sewing thread is uneven.
4. The visual inspection method of sewing stitches as set forth in claim 2, wherein: the step S4 further includes the steps of:
step S51: determining the interested region of the right-stitch pinhole according to the Image2, the angle B and the straight line center coordinates (center X3, center Y3), and obtaining each center coordinate of the right-stitch pinhole through a Blob algorithm;
step S52: and (5) obtaining the distance between every two pinholes of the right stitch through cyclic calculation, and determining whether the right stitch has a jumper defect or not by referring to the jumper defect parameters in the step S2.
5. The visual inspection method of sewing stitches as set forth in claim 2, wherein: the step S4 further includes the steps of:
step S53: the distance D2 is obtained by making a perpendicular to the right-hand-stitch straight line L3 by the straight-line center point coordinates (center x1, center y 1), and the distance D2 is compared with the parameter of the unevenness defect of the sewing thread registered in step S2 to determine whether the right sewing thread is uneven.
6. A visual inspection device for sewing stitches using the visual inspection method for sewing stitches as claimed in any one of claims 1 to 5, characterized in that: the sewing stitch visual inspection device comprises an industrial camera, an infrared backlight source and a control cabinet, wherein the industrial camera is electrically connected with the control cabinet, the infrared backlight source is electrically connected with the control cabinet, and a sewing product is located between the industrial camera and the infrared backlight source.
7. The visual inspection device of sewing stitch as claimed in claim 6, wherein: the sewing stitch visual inspection device further comprises a display screen, the display screen is electrically connected with the control cabinet, and the display screen is used for displaying images shot by the industrial camera when the infrared backlight source is opened.
8. The visual inspection device of sewing stitch as claimed in claim 6, wherein: the model of the industrial camera is ZVIT-CA013-20GM, and the model of a lens matched with the industrial camera is ZVIT-C3516-2M.
9. The visual inspection device of sewing stitch as claimed in claim 6, wherein: the model of the infrared backlight source is ZVIT-FLG 7070-IR.
10. The visual inspection device of sewing stitch as claimed in claim 6, wherein: the infrared backlight source adopts an infrared light source with the wavelength of 850 nm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010910731.5A CN111815632A (en) | 2020-09-02 | 2020-09-02 | Visual inspection method and device for sewing stitches |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010910731.5A CN111815632A (en) | 2020-09-02 | 2020-09-02 | Visual inspection method and device for sewing stitches |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111815632A true CN111815632A (en) | 2020-10-23 |
Family
ID=72860119
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010910731.5A Pending CN111815632A (en) | 2020-09-02 | 2020-09-02 | Visual inspection method and device for sewing stitches |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111815632A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1894458A (en) * | 2003-12-15 | 2007-01-10 | 弗里茨·格高夫股份公司伯尔尼纳一缝纫机厂 | Method and device for controlling the movement of a needle in a sewing machine |
| CN105806849A (en) * | 2016-04-08 | 2016-07-27 | 广东工业大学 | Automobile seat surface defect detection system based on machine vision as well as detection method |
| CN106053479A (en) * | 2016-07-21 | 2016-10-26 | 湘潭大学 | System for visually detecting workpiece appearance defects based on image processing |
| CN109239076A (en) * | 2018-08-29 | 2019-01-18 | 西安理工大学 | A kind of sewing thread trace defect inspection method based on machine vision |
| CN109324056A (en) * | 2018-08-29 | 2019-02-12 | 西安理工大学 | A kind of sewing thread trace measurement method based on machine vision |
| WO2019046566A1 (en) * | 2017-08-30 | 2019-03-07 | Vf Jeanswear Lp | Automated control and inspection system for manufacture and measurement of apparel |
-
2020
- 2020-09-02 CN CN202010910731.5A patent/CN111815632A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1894458A (en) * | 2003-12-15 | 2007-01-10 | 弗里茨·格高夫股份公司伯尔尼纳一缝纫机厂 | Method and device for controlling the movement of a needle in a sewing machine |
| CN105806849A (en) * | 2016-04-08 | 2016-07-27 | 广东工业大学 | Automobile seat surface defect detection system based on machine vision as well as detection method |
| CN106053479A (en) * | 2016-07-21 | 2016-10-26 | 湘潭大学 | System for visually detecting workpiece appearance defects based on image processing |
| WO2019046566A1 (en) * | 2017-08-30 | 2019-03-07 | Vf Jeanswear Lp | Automated control and inspection system for manufacture and measurement of apparel |
| CN109239076A (en) * | 2018-08-29 | 2019-01-18 | 西安理工大学 | A kind of sewing thread trace defect inspection method based on machine vision |
| CN109324056A (en) * | 2018-08-29 | 2019-02-12 | 西安理工大学 | A kind of sewing thread trace measurement method based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109239076B (en) | Sewing stitch defect detection method based on machine vision | |
| CN100593716C (en) | On-line detecting method of machine vision system for printed calico flaw | |
| JP3431075B2 (en) | Liquid crystal display panel unevenness classification processing method, apparatus and program | |
| CN107886500A (en) | A kind of production monitoring method and system based on machine vision and machine learning | |
| WO2019041634A1 (en) | Detection method and device for display panel | |
| KR101256369B1 (en) | Flat display pannel test equipment and test method using multi ccd camera | |
| CN109324056B (en) | Sewing thread trace measuring method based on machine vision | |
| TWI707137B (en) | Intelligent production line monitoring system and implementation method thereof | |
| CN110728681A (en) | Mura defect detection method and device | |
| JP5786622B2 (en) | Image quality inspection method, image quality inspection apparatus, and image quality inspection program | |
| EP3876195A1 (en) | Image processor and method for evaluating dyeing quality of knit fabric | |
| CN108802052A (en) | A kind of detecting system and its detection method about slide fastener defect | |
| WO2020079694A1 (en) | Optimizing defect detection in an automatic visual inspection process | |
| CN113592852A (en) | Carbon fiber carbon wire quality online detection system and method | |
| KR20230137584A (en) | Vision inspection system for defect detection of fabric | |
| CN114612423A (en) | Chip packaging defect detection method | |
| CN111192246B (en) | Automatic detection method for welding spots | |
| CN111815632A (en) | Visual inspection method and device for sewing stitches | |
| CN112461846A (en) | Workpiece defect detection method and device | |
| CN116840240A (en) | Visual detection system of power supply distributor | |
| CN208155893U (en) | binocular vision scratch detection system based on high speed camera | |
| CN115690077A (en) | Bubble plate back defect detection method and system | |
| CN110148141A (en) | A kind of silk-screen optical filter small pieces detection method of counting and equipment | |
| JP6027717B2 (en) | Visual inspection apparatus provided with gaze position specifying means | |
| CN208902618U (en) | A kind of non-woven fabrics air hole detection device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201023 |
|
| RJ01 | Rejection of invention patent application after publication |