CN117147582A - Fabric flaw identification device and control method thereof - Google Patents
Fabric flaw identification device and control method thereof Download PDFInfo
- Publication number
- CN117147582A CN117147582A CN202311118230.3A CN202311118230A CN117147582A CN 117147582 A CN117147582 A CN 117147582A CN 202311118230 A CN202311118230 A CN 202311118230A CN 117147582 A CN117147582 A CN 117147582A
- Authority
- CN
- China
- Prior art keywords
- fabric
- flaw
- image
- image acquisition
- workbench
- 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
- 239000004744 fabric Substances 0.000 title claims abstract description 146
- 238000000034 method Methods 0.000 title claims abstract description 19
- 230000007246 mechanism Effects 0.000 claims abstract description 66
- 230000033001 locomotion Effects 0.000 claims abstract description 21
- 230000008569 process Effects 0.000 claims abstract description 4
- 238000000605 extraction Methods 0.000 claims description 21
- 230000007547 defect Effects 0.000 claims description 17
- 230000008859 change Effects 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims 1
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06H—MARKING, INSPECTING, SEAMING OR SEVERING TEXTILE MATERIALS
- D06H1/00—Marking textile materials; Marking in combination with metering or inspecting
- D06H1/02—Marking by printing or analogous processes
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06H—MARKING, INSPECTING, SEAMING OR SEVERING TEXTILE MATERIALS
- D06H3/00—Inspecting textile materials
- D06H3/08—Inspecting textile materials by photo-electric or television means
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- 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
- 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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- 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
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
- G01N2021/0106—General arrangement of respective parts
- G01N2021/0112—Apparatus in one mechanical, optical or electronic block
-
- 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
- G01N2021/8854—Grading and classifying of flaws
- G01N2021/888—Marking defects
-
- 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
Abstract
The invention relates to a fabric flaw identification device and a control method thereof. The apparatus further comprises: the image acquisition mechanism is arranged at the starting end of the workbench and is used for acquiring fabric images when the fabric passes through the image acquisition mechanism; the flaw marking mechanism is used for marking flaws on the fabric in the process of the fabric flowing through the workbench; and the controller is used for determining the flaw position on the fabric according to the fabric image acquired by the image acquisition mechanism, controlling the distance between the image acquisition mechanism and the flaw marking mechanism in the length direction of the fabric according to the preset inertial movement amount to be equal to the preset inertial movement amount, and controlling the flaw marking mechanism to mark corresponding flaws on the fabric according to the flaw position on the fabric. The invention aims to solve the problem that the existing machine can only identify flaws of the fabric but cannot identify the flaws on the fabric, so that the flaws still need to be manually confirmed to avoid flaw omission.
Description
Technical Field
The invention belongs to the technical field of clothing manufacturing and production, and particularly relates to a fabric flaw identification device and a control method thereof.
Background
The fabric is a basic raw material for making clothing, and quality inspection of the fabric is required after spinning or before making clothing, and defects existing on the surface of the fabric are mainly screened so as to avoid missing the defects and influencing the rejection rate and quality of the finished clothing.
The fabric flaw identification is divided into manual identification and machine identification, the visual fatigue is generated when the duration of the manual identification is too long, omission is very easy, and the efficiency is low; the machine identification accuracy is high and the efficiency is high, but the machine identification at the present stage can only identify the flaw, but can not identify the position of the flaw.
Disclosure of Invention
The invention aims to solve the problem that the existing machine can only identify flaws of the fabric but cannot identify the flaws on the fabric, so that the flaws still need to be manually confirmed to avoid flaw omission.
In order to achieve the above object, the present invention provides a fabric defect recognition device and a control method thereof.
According to a first aspect of the present invention, there is provided a fabric defect recognition device comprising a table and a fabric feed mechanism for passing fabric through the table, the device further comprising:
the image acquisition mechanism is arranged at the starting end of the workbench and is used for acquiring fabric images when the fabric passes through the image acquisition mechanism;
the flaw marking mechanism is used for marking flaws on the fabric in the process of the fabric flowing through the workbench;
and the controller is used for determining the flaw position on the fabric according to the fabric image acquired by the image acquisition mechanism, controlling the distance between the image acquisition mechanism and the flaw marking mechanism in the length direction of the fabric according to the preset inertial movement amount to be equal to the preset inertial movement amount, and controlling the flaw marking mechanism to mark corresponding flaws on the fabric according to the flaw position on the fabric.
Optionally, the flaw marking mechanism includes:
the first sliding rail and the second sliding rail are respectively and horizontally fixed on two sides of the workbench and are oppositely arranged, and a first sliding block and a second sliding block are respectively arranged on the first sliding rail and the second sliding rail;
the first sliding rod and the second sliding rod are vertically arranged on two sides of the workbench respectively and are oppositely arranged, the bottom end of the first sliding rod is fixedly connected with the first sliding block, a third sliding block is arranged on the first sliding rod, the bottom end of the second sliding rod is fixedly connected with the second sliding block, and a fourth sliding block is arranged on the second sliding rod;
the two ends of the transverse connecting rod are fixedly connected with the third sliding block and the fourth sliding block respectively;
the electric control telescopic rod is movably arranged on the transverse connecting rod, can linearly move along the transverse connecting rod and can perform telescopic movement in the vertical direction, and a chalk block is arranged at the tail end of the electric control telescopic rod.
Optionally, an illuminating lamp is arranged in the table top of the workbench.
Optionally, the image acquisition mechanism includes:
the image acquisition bracket is characterized in that connecting rods of the image acquisition bracket are respectively fixedly connected with two sides of the workbench, and a mounting rod which is suspended above the workbench is arranged between the two connecting rods;
the high-speed camera is movably arranged on the mounting rod and can linearly move along the mounting rod, and is used for collecting fabric images when the fabric passes through the mounting rod.
According to a second aspect of the present invention, there is provided a control method of any one of the fabric defect recognition devices described above, applied to the controller, the control method comprising:
determining the flaw position on the fabric according to the fabric image acquired by the image acquisition mechanism;
controlling the distance between the image acquisition mechanism and the flaw marking mechanism in the length direction of the fabric to be equal to the preset inertial movement amount according to the preset inertial movement amount;
and controlling the flaw marking mechanism to mark corresponding flaws on the fabric according to the flaw positions on the fabric.
Optionally, the determining the flaw position on the fabric according to the fabric image acquired by the image acquisition mechanism includes:
carrying out denoising and enhancing pretreatment on the fabric image;
carrying out edge feature extraction, color feature extraction and texture feature extraction on the pretreated fabric image;
and carrying out flaw identification on the fabric image subjected to the feature extraction according to the classifier.
Optionally, the denoising enhancement preprocessing is implemented based on the following formula:
wherein g (x, y) is the denoised image, x, y=0, 1, 2..n-1; s is a set of fields centered on the (x, y) point; m is the total number of coordinates of S.
Alternatively, the color feature extraction includes:
converting the color into HSV color space, dividing the preprocessed fabric image into a plurality of areas according to the color information, dividing the color into a plurality of bins, carrying out color space quantization on each area to establish a color index, and establishing a binary image color index table.
Optionally, the texture feature extraction includes:
dividing the preprocessed fabric image into 16×16 units, and comparing 8 points in the annular neighborhood of one pixel in each unit clockwise or anticlockwise;
if the central pixel value is larger than the adjacent point, the adjacent point is assigned to be 1, otherwise, the adjacent point is assigned to be 0, and 8-bit binary numbers of each point are determined;
calculating a histogram of each unit, and carrying out normalization processing on the histogram;
and connecting the obtained histograms of the units to obtain LBP texture characteristics of the fabric image.
Optionally, the edge feature extraction includes:
according to the fact that a sobel operator of a certain point of a region on the preprocessed fabric image is a zero vector, a group of vector values on points on an edge line are brightness gradients, and a change gradient approximation value in the horizontal direction and the vertical direction is calculated on a source image according to a 3 multiplied by 3 mask;
* Representing a two-dimensional convolution operation; the coordinate system established here is to the right in the x-coordinate direction and downward in the y-coordinate direction, and a is the source image.
The invention has the beneficial effects that: the image acquisition mechanism acquires the fabric image, the controller determines the flaw position on the fabric according to the fabric image acquired by the image acquisition mechanism, and controls the flaw marking mechanism to mark corresponding flaws on the fabric.
Drawings
The invention may be better understood by referring to the following description in conjunction with the accompanying drawings in which the same or similar reference numerals are used throughout the several drawings to designate the same or similar components.
Fig. 1 shows a schematic diagram of a fabric defect recognition device according to an embodiment of the present invention;
FIG. 2 shows an enlarged view of portion A of FIG. 1 in accordance with the present invention;
in the figure: the device comprises a workbench, a 2-supporting leg, a 3-cloth conveying roller, a 301-cloth conveying roller mounting seat, a 4-illuminating lamp, a 5-image acquisition bracket, a 6-high-speed camera, a 7-first sliding rail, an 8-first sliding block, a 9-transverse connecting rod, a 10-first sliding rod, an 11-electric control telescopic rod, a 12-chalk block, a 14-second sliding rail, a 15-second sliding rod, a 16-third sliding block and a 17-fourth sliding block.
Detailed Description
In order that those skilled in the art will more fully understand the technical solutions of the present invention, exemplary embodiments of the present invention will be described more fully and in detail below with reference to the accompanying drawings. It should be apparent that the following description of one or more embodiments of the invention is merely one or more of the specific ways in which the technical solutions of the invention may be implemented and is not intended to be exhaustive. It should be understood that the technical solution of the present invention may be implemented in other ways belonging to one general inventive concept, and should not be limited by the exemplary described embodiments. All other embodiments, which may be made by one or more embodiments of the invention without inventive faculty, are intended to be within the scope of the invention.
Examples: as shown in fig. 1 and 2, this embodiment provides a fabric defect identifying device, which includes a workbench 1 and a fabric feeding mechanism for making fabric flow through the workbench 1, and further includes:
the image acquisition mechanism is arranged at the starting end of the workbench 1 and is used for acquiring fabric images when the fabric passes through the image acquisition mechanism;
the flaw marking mechanism is used for marking flaws on the fabric in the process of the fabric flowing through the workbench 1;
and the controller is used for determining the flaw position on the fabric according to the fabric image acquired by the image acquisition mechanism, controlling the distance between the image acquisition mechanism and the flaw marking mechanism in the length direction of the fabric according to the preset inertial movement amount to be equal to the preset inertial movement amount, and controlling the flaw marking mechanism to mark corresponding flaws on the fabric according to the flaw position on the fabric.
Specifically speaking, surface fabric flaw recognition device includes workstation 1, cloth conveying mechanism, image acquisition mechanism, flaw marking mechanism and controller, and cloth conveying mechanism carries the surface fabric to workstation 1, and the surface fabric image is gathered to image acquisition mechanism, and the controller is according to the surface fabric image that image acquisition mechanism gathered after discerned that the surface fabric has the flaw, and the motion is stopped to the immediate control cloth conveying mechanism, and simultaneously according to the inertial motion of predetermineeing, the interval of image acquisition mechanism and flaw marking mechanism in surface fabric length direction equals the inertial motion of predetermineeing, and the corresponding flaw of flaw is marked out to flaw position control flaw marking mechanism on the surface fabric according to the surface fabric.
Further, two ends of the workbench 1 are provided with cloth conveying rollers through cloth conveying roller mounting seats 301, two cloth conveying rollers are arranged at two ends, fabric moves from the cloth conveying roller at one end of the workbench 1 to the cloth conveying roller at the other end of the workbench 1 through the workbench 1, an image acquisition bracket 5 is arranged on the workbench 1 close to the cloth conveying roller at one end of the fabric conveying, connecting rods of the image acquisition bracket are respectively fixedly connected with two sides of the workbench 1, and a mounting rod which is arranged above the workbench 1 in a suspending manner is arranged between the two connecting rods; the high-speed camera 6 is movably arranged on the mounting rod, and the high-speed camera 6 reciprocates along the mounting rod under the control of the controller to acquire images of fabrics passing through the mounting rod.
Further, a support leg 2 is arranged at four corners of the lower side of the workbench 1.
Further, the flaw marking mechanism includes:
the first slide rail 7 and the second slide rail 14 are respectively and horizontally fixed on two sides of the workbench 1 and are oppositely arranged, and the first slide rail 7 and the second slide rail 14 are respectively provided with a first slide block 8 and a second slide block;
the first slide bar 10 and the second slide bar 15 are vertically arranged at two sides of the workbench 1 respectively and are oppositely arranged, the bottom end of the first slide bar 10 is fixedly connected with the first slide block 8, a third slide block 16 is arranged on the first slide bar, the bottom end of the second slide bar 15 is fixedly connected with the second slide block, and a fourth slide block 17 is arranged on the second slide block;
the two ends of the transverse connecting rod 9 are fixedly connected with a third sliding block 16 and a fourth sliding block 17 respectively;
the electric control telescopic rod 11 is movably arranged on the transverse connecting rod 9, can linearly move along the transverse connecting rod 9 and can vertically perform telescopic movement, and a chalk block 12 is arranged at the tail end of the electric control telescopic rod 11.
Because the fabric has inertia, after the controller controls the cloth conveying mechanism to stop moving, the fabric can continuously move forwards for a certain distance due to the inertia, so that after the fabric is conveyed and the positions of the first sliding block 8 and the second sliding block on the first sliding rail 7 and the second sliding rail 14 are controlled according to the inertial movement amount of different types of fabrics, the position of the transverse connecting rod 9 is changed, after the cloth conveying mechanism stops moving, the defect on the fabric just moves below the transverse connecting rod 9 under the action of the inertia, at the moment, the controller controls the electric control telescopic rod 11 to move above the defect, the third sliding block 16 and the fourth sliding block 17 respectively slide downwards along the first sliding rod 10 and the second sliding rod 15, and after the chalk block 12 contacts the fabric, the defect position is marked.
Further, an illuminating lamp 4 is arranged in the surface of the workbench 1.
Specifically speaking, the illuminating lamp 4 is embedded in the workbench 1, the illuminating lamp 4 is used for illuminating the fabric, and after light transmission, exposure of the flaw position is facilitated, so that the high-speed camera 6 can collect images with obvious flaws.
Based on the fabric defect recognition device, the embodiment provides a control method, which is applied to a controller and comprises the following steps:
determining the flaw position on the fabric according to the fabric image acquired by the image acquisition mechanism;
controlling the distance between the image acquisition mechanism and the flaw marking mechanism in the length direction of the fabric to be equal to the preset inertial movement amount according to the preset inertial movement amount;
and controlling the flaw marking mechanism to mark corresponding flaws on the fabric according to the flaw positions on the fabric.
Further, determining the flaw position on the fabric according to the fabric image acquired by the image acquisition mechanism comprises:
carrying out denoising and enhancing pretreatment on the fabric image;
carrying out edge feature extraction, color feature extraction and texture feature extraction on the pretreated fabric image;
and carrying out flaw identification on the fabric image subjected to the feature extraction according to the classifier.
Further, denoising enhancement preprocessing is realized based on the following formula:
wherein g (x, y) is the denoised image, x, y=0, 1, 2..n-1; s is a set of fields centered on the (x, y) point; m is the total number of coordinates of S.
Further, the color feature extraction includes:
converting the color into HSV color space, dividing the preprocessed fabric image into a plurality of areas according to the color information, dividing the color into a plurality of bins, carrying out color space quantization on each area to establish a color index, and establishing a binary image color index table.
Further, the texture feature extraction includes:
dividing the preprocessed fabric image into 16×16 units, and comparing 8 points in the annular neighborhood of one pixel in each unit clockwise or anticlockwise;
if the central pixel value is larger than the adjacent point, the adjacent point is assigned to be 1, otherwise, the adjacent point is assigned to be 0, and 8-bit binary numbers of each point are determined;
calculating a histogram of each unit, and carrying out normalization processing on the histogram;
and connecting the obtained histograms of the units to obtain LBP texture characteristics of the fabric image.
Further, the edge feature extraction includes:
according to the fact that a sobel operator of a certain point of a region on the preprocessed fabric image is a zero vector, a group of vector values on points on an edge line are brightness gradients, and a change gradient approximation value in the horizontal direction and the vertical direction is calculated on a source image according to a 3 multiplied by 3 mask;
* Representing a two-dimensional convolution operation; the coordinate system established here is to the right in the x-coordinate direction and downward in the y-coordinate direction, and a is the source image.
And (3) identifying defects of a classifier: selecting a classifier model, training the model by using a training set, and then verifying the recognition effect of the model by using a verification set; and constructing a classifier model meeting the requirements for identifying flaws.
Although one or more embodiments of the present invention have been described above, it will be appreciated by those of ordinary skill in the art that the invention can be embodied in any other form without departing from the spirit or scope thereof. The above-described embodiments are therefore intended to be illustrative rather than limiting, and many modifications and substitutions will now be apparent to those of ordinary skill in the art without departing from the spirit and scope of the present invention as defined in the appended claims.
Claims (10)
1. A fabric flaw identification device, includes workstation and is used for making the surface fabric flow through the cloth conveying mechanism of workstation, its characterized in that, the device still includes:
the image acquisition mechanism is arranged at the starting end of the workbench and is used for acquiring fabric images when the fabric passes through the image acquisition mechanism;
the flaw marking mechanism is used for marking flaws on the fabric in the process of the fabric flowing through the workbench;
and the controller is used for determining the flaw position on the fabric according to the fabric image acquired by the image acquisition mechanism, controlling the distance between the image acquisition mechanism and the flaw marking mechanism in the length direction of the fabric according to the preset inertial movement amount to be equal to the preset inertial movement amount, and controlling the flaw marking mechanism to mark corresponding flaws on the fabric according to the flaw position on the fabric.
2. The fabric defect recognition device of claim 1, wherein the defect marking mechanism comprises:
the first sliding rail and the second sliding rail are respectively and horizontally fixed on two sides of the workbench and are oppositely arranged, and a first sliding block and a second sliding block are respectively arranged on the first sliding rail and the second sliding rail;
the first sliding rod and the second sliding rod are vertically arranged on two sides of the workbench respectively and are oppositely arranged, the bottom end of the first sliding rod is fixedly connected with the first sliding block, a third sliding block is arranged on the first sliding rod, the bottom end of the second sliding rod is fixedly connected with the second sliding block, and a fourth sliding block is arranged on the second sliding rod;
the two ends of the transverse connecting rod are fixedly connected with the third sliding block and the fourth sliding block respectively;
the electric control telescopic rod is movably arranged on the transverse connecting rod, can linearly move along the transverse connecting rod and can perform telescopic movement in the vertical direction, and a chalk block is arranged at the tail end of the electric control telescopic rod.
3. The fabric defect identification device of claim 1, wherein an illumination lamp is arranged in the table top of the workbench.
4. The fabric defect recognition device of claim 1, wherein the image acquisition mechanism comprises:
the image acquisition bracket is characterized in that connecting rods of the image acquisition bracket are respectively fixedly connected with two sides of the workbench, and a mounting rod which is suspended above the workbench is arranged between the two connecting rods;
the high-speed camera is movably arranged on the mounting rod and can linearly move along the mounting rod, and is used for collecting fabric images when the fabric passes through the mounting rod.
5. The control method of the fabric defect identifying device according to any one of claims 1 to 4, characterized by being applied to the controller, the control method comprising:
determining the flaw position on the fabric according to the fabric image acquired by the image acquisition mechanism;
controlling the distance between the image acquisition mechanism and the flaw marking mechanism in the length direction of the fabric to be equal to the preset inertial movement amount according to the preset inertial movement amount;
and controlling the flaw marking mechanism to mark corresponding flaws on the fabric according to the flaw positions on the fabric.
6. The control method according to claim 5, wherein the determining the flaw position on the fabric from the fabric image acquired by the image acquisition mechanism includes:
carrying out denoising and enhancing pretreatment on the fabric image;
carrying out edge feature extraction, color feature extraction and texture feature extraction on the pretreated fabric image;
and carrying out flaw identification on the fabric image subjected to the feature extraction according to the classifier.
7. The control method according to claim 6, characterized in that the denoising enhancement preprocessing is implemented based on the following formula:
wherein g (x, y) is the denoised image, x, y=0, 1, 2..n-1; s is a set of fields centered on the (x, y) point; m is the total number of coordinates of S.
8. The control method according to claim 6, characterized in that the color feature extraction includes:
converting the color into an HSV color space, dividing the preprocessed fabric image into a plurality of areas according to the color information, dividing the color into a plurality of bins, quantizing the color space at the inlet of each area to establish a color index, and establishing a binary image color index table.
9. The control method according to claim 6, characterized in that the texture feature extraction includes:
dividing the preprocessed fabric image into 16×16 units, and comparing 8 points in the annular neighborhood of one pixel in each unit clockwise or anticlockwise;
if the central pixel value is larger than the adjacent point, the adjacent point is assigned to be 1, otherwise, the adjacent point is assigned to be 0, and 8-bit binary numbers of each point are determined;
calculating a histogram of each unit, and carrying out normalization processing on the histogram;
and connecting the obtained histograms of the units to obtain LBP texture characteristics of the fabric image.
10. The control method according to claim 6, characterized in that the edge feature extraction includes:
according to the fact that a sobel operator of a certain point of a region on the preprocessed fabric image is a zero vector, a group of vector values on points on an edge line are brightness gradients, and a change gradient approximation value in the horizontal direction and the vertical direction is calculated on a source image according to a 3 multiplied by 3 mask;
* Representing a two-dimensional convolution operation; the coordinate system established here is directed to the right in the x-coordinate direction and downward in the y-coordinate direction, and a is the source image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311118230.3A CN117147582A (en) | 2023-08-31 | 2023-08-31 | Fabric flaw identification device and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311118230.3A CN117147582A (en) | 2023-08-31 | 2023-08-31 | Fabric flaw identification device and control method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117147582A true CN117147582A (en) | 2023-12-01 |
Family
ID=88886320
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311118230.3A Pending CN117147582A (en) | 2023-08-31 | 2023-08-31 | Fabric flaw identification device and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117147582A (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070081695A1 (en) * | 2005-10-04 | 2007-04-12 | Eric Foxlin | Tracking objects with markers |
| JP2011257343A (en) * | 2010-06-11 | 2011-12-22 | Asahi Kasei E-Materials Corp | Defect marker and method of marking defect for films |
| US20160371559A1 (en) * | 2015-06-22 | 2016-12-22 | Seiko Epson Corporation | Marker, method of detecting position and pose of marker, and computer program |
| US20190389600A1 (en) * | 2018-06-21 | 2019-12-26 | The Boeing Company | Positioning Enhancements to Localization Process for Three-Dimensional Visualization |
| CN112461850A (en) * | 2020-09-29 | 2021-03-09 | 江苏南高智能装备创新中心有限公司 | Workpiece surface flaw detection system |
| CN216107757U (en) * | 2021-09-23 | 2022-03-22 | 绍兴柯桥醉了数码纺织科技股份有限公司 | Cloth inspecting and rolling device with defect point marking function |
| CN115491891A (en) * | 2022-09-15 | 2022-12-20 | 塔里木大学 | Fabric defect recognition device and recognition method |
| CN115839958A (en) * | 2022-10-14 | 2023-03-24 | 苏州琼派瑞特科技股份有限公司 | Garment flaw detection method |
| CN219512124U (en) * | 2023-02-07 | 2023-08-11 | 苏州科彤净化科技有限公司 | Large particle intelligent detection device for dust-free cloth |
| CN116577072A (en) * | 2023-05-05 | 2023-08-11 | 虹软科技股份有限公司 | Calibration method, device, system and storage medium of equipment |
-
2023
- 2023-08-31 CN CN202311118230.3A patent/CN117147582A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070081695A1 (en) * | 2005-10-04 | 2007-04-12 | Eric Foxlin | Tracking objects with markers |
| JP2011257343A (en) * | 2010-06-11 | 2011-12-22 | Asahi Kasei E-Materials Corp | Defect marker and method of marking defect for films |
| US20160371559A1 (en) * | 2015-06-22 | 2016-12-22 | Seiko Epson Corporation | Marker, method of detecting position and pose of marker, and computer program |
| US20190389600A1 (en) * | 2018-06-21 | 2019-12-26 | The Boeing Company | Positioning Enhancements to Localization Process for Three-Dimensional Visualization |
| CN112461850A (en) * | 2020-09-29 | 2021-03-09 | 江苏南高智能装备创新中心有限公司 | Workpiece surface flaw detection system |
| CN216107757U (en) * | 2021-09-23 | 2022-03-22 | 绍兴柯桥醉了数码纺织科技股份有限公司 | Cloth inspecting and rolling device with defect point marking function |
| CN115491891A (en) * | 2022-09-15 | 2022-12-20 | 塔里木大学 | Fabric defect recognition device and recognition method |
| CN115839958A (en) * | 2022-10-14 | 2023-03-24 | 苏州琼派瑞特科技股份有限公司 | Garment flaw detection method |
| CN219512124U (en) * | 2023-02-07 | 2023-08-11 | 苏州科彤净化科技有限公司 | Large particle intelligent detection device for dust-free cloth |
| CN116577072A (en) * | 2023-05-05 | 2023-08-11 | 虹软科技股份有限公司 | Calibration method, device, system and storage medium of equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109115785B (en) | Casting polishing quality detection method and device and use method thereof | |
| CN108918543B (en) | Dynamic detection device and method for mirror surface scratch | |
| CN104101608B (en) | Intelligent detecting device for detecting defects of multi-type irregularly shaped product | |
| CN208574964U (en) | A kind of automatic identification and sorting cigarette case device based on machine vision | |
| JP7055212B2 (en) | How to inspect masks online | |
| CN109374634B (en) | Online mask detection system and method | |
| CN110216080A (en) | A kind of Quality Monitoring Control System of the PCB processing producing line based on image comparison | |
| CN108760747A (en) | A kind of 3D printing model surface defect visible detection method | |
| JP2018510338A (en) | Glass plate acquisition and positioning system | |
| CN103837552A (en) | System for detecting apparent defects on protective glass of touch screen | |
| CN208583658U (en) | A kind of metal box-lid automatic code-printing and stamp substandard products automatic reject mechanism | |
| CN104483320A (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| KR102445162B1 (en) | Fabric inspection system | |
| CN115100206A (en) | Printing defect identification method for textile with periodic pattern | |
| CN106153638A (en) | Fabric figured pattern identification and detection device | |
| CN113506255B (en) | Automatic detection method for clothing suture defects based on high-precision digital image | |
| CN111693535A (en) | Touch screen defect detection equipment and method based on machine vision analysis | |
| CN117147582A (en) | Fabric flaw identification device and control method thereof | |
| CN116563276B (en) | Chemical fiber filament online defect detection method and detection system | |
| CN105954288B (en) | Hollow plate detection and sorting system and detection method after electrolytic manganese negative plate stripping | |
| CN107504905A (en) | A kind of reticulated mesh size deviation ratio detecting system based on machine vision | |
| CN106881281A (en) | A kind of automatic sorting device and system | |
| CN209307576U (en) | A kind of cloth cover defective vision detection system of double rib warp loom | |
| CN114125435B (en) | Intelligent image defect detection method for network camera | |
| CN210604354U (en) | Cloth pattern and character online acquisition 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 |