CN107102007B - Pattern consistency recognition methods in cloth detection - Google Patents

Pattern consistency recognition methods in cloth detection Download PDF

Info

Publication number
CN107102007B
CN107102007B CN201710463911.1A CN201710463911A CN107102007B CN 107102007 B CN107102007 B CN 107102007B CN 201710463911 A CN201710463911 A CN 201710463911A CN 107102007 B CN107102007 B CN 107102007B
Authority
CN
China
Prior art keywords
cloth
reference picture
image
light source
group
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.)
Active
Application number
CN201710463911.1A
Other languages
Chinese (zh)
Other versions
CN107102007A (en
Inventor
刘颖
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
ZHEJIANG PAPA INFANTS ARTICLE CO., LTD.
Original Assignee
Zhejiang Papa Infants Article Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang Papa Infants Article Co Ltd filed Critical Zhejiang Papa Infants Article Co Ltd
Priority to CN201710463911.1A priority Critical patent/CN107102007B/en
Publication of CN107102007A publication Critical patent/CN107102007A/en
Application granted granted Critical
Publication of CN107102007B publication Critical patent/CN107102007B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/89Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
    • G01N21/892Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
    • G01N21/898Irregularities in textured or patterned surfaces, e.g. textiles, wood
    • G01N21/8983Irregularities in textured or patterned surfaces, e.g. textiles, wood for testing textile webs, i.e. woven material
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/22Matching criteria, e.g. proximity measures

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Textile Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Wood Science & Technology (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Treatment Of Fiber Materials (AREA)

Abstract

In order to avoid cloth buyer can not quickly and accurately screen the defect of the cloth quality of the complex pattern of dyeing preparation of piece goods or spray printing or the pattern of fringe spacing very little in purchase, the present invention provides the pattern consistency recognition methods in a kind of detection of cloth, it include: that cloth to be detected is set on the conveyer belt of one-way movement by (1), the direction of motion of the conveyer belt and the length direction of cloth are consistent;(2) multiple labels extended perpendicular to cloth surface are set on cloth to be detected;(3) obtaining has the cloth reference picture of the shade of the label determines whether cloth pattern is consistent according to the cloth reference picture.This method overcomes the drawbacks of needing to expend great amount of images processing time and image processing machine resource in the prior art existing for the image analysis algorithm for often relying on generally use in the prior art, can quickly and accurately realize the detection of cloth pattern consistency.

Description

Pattern consistency recognition methods in cloth detection
Technical field
The present invention relates to technical field of textile production, know more particularly, to the pattern consistency in a kind of detection of cloth Other method.
Background technique
With the raising that people require the aesthetics and complexity of cloth decorative pattern, print and dye on cloth or the pattern of spray printing such as There is some slight misalignment or deformation in fruit, will lead to the significant wastage in raw material and working hour.Especially for small compared with standard cloth size And need the cloth or size of printing and dyeing or spray printing complex pattern larger and the cloth of printing and dyeing or the lesser pattern of spray printing fringe spacing , when printing and dyeing or jet printing process needs to complete the printing and dyeing of multiple tracks difference or jet printing technique on cloth, difference is printed and dyed or spray printing work Skill needs cloth carrying out accurate position restriction to each other.For example, for it is expected printing and dyeing or spray printing in some side of cloth When a variety of pairs of techniques require different stripeds, need to make cloth by multiple and different printing and dyeing or spatterwork line, each printing and dyeing Or spatterwork line completes printing and dyeing or the spray printing of the different candy strips under different technology conditions.Per pass printing and dyeing or jet printing technique At the end of, it is desirable that cloth is carried out transverse shifting preset distance in the direction of advance relative to printing and dyeing or spray printing line, once distance Difference, then pattern of the cloth completed by multiple tracks printing and dyeing or jet printing technique in side will be unable to reach expected, become substandard products Even unqualified cloth.Then, desirably cloth, can be real-time during being moved along production line in the prior art Ground knows whether it is laterally moved expected distance or do not occurred as desired transverse to cloth direction of advance Displacement.
The above situation it is particularly disadvantageous in cloth buyer (for example, cloth manufactured after be purchased when purchase manufacturer) Examine the demand of the quality of the cloth of the complex pattern for the above two situation having.Once being made into the products such as ready-made clothes, then originally The style of body excellent in design then may cause the reduction of finished product aesthetics due to above-mentioned displacement or dislocation.
Through retrieving, Defect Detection and tension adjustment side are related generally to the detection of cloth in process of production in the prior art Face, for example, application No. is the Chinese invention patent applications of CN201310522031 to disclose a kind of cross embroidery Numerical Control Printer cloth Location information real-time correction method, bearing calibration are as follows: a. is whole to read camera acquired image information in real time;B. to figure As be filtered, binaryzation, contours extract, square hole identifying processing, obtain the ranks coordinate information of each square hole;C. it obtains each The actual physics coordinate of square hole central point;D. the actual physics coordinate of square hole central point vision guide locating module is supplied to make For benchmark reference point, accurately cloth texture information is obtained;E., the texture information is supplied to the drive module of inkjet print head. For another example, one kind is disclosed application No. is the Chinese invention patent application of CN201410467061 to convert based on adaptive orthogonal wavelet Fabric Defects Inspection detection method and device, replace artificial range estimation and original first by manually carrying out the selection of wavelet basis, then into Automatic defect inspection method of the row based on wavelet transformation, overcome traditional artificial range estimation detection speed slowly, low efficiency, erroneous detection, leakage The defects of inspection rate is high and drawn in the original defect detection method based on wavelet transformation by not optimized to wavelet basis The not high problem of the detection accuracy risen.
However, above-mentioned technical proposal can not solve drawbacks described above in the prior art.
Summary of the invention
In order to avoid cloth buyer can not quickly and accurately screen the complex pattern of dyeing preparation of piece goods or spray printing in purchase Or the defect of the cloth quality of the pattern of fringe spacing very little, the present invention provides the pattern consistency knowledges in a kind of detection of cloth Other method, comprising:
(1) cloth to be detected is set on the conveyer belt of one-way movement, the direction of motion of the conveyer belt and the length of cloth It is consistent to spend direction;
(2) multiple labels extended perpendicular to cloth surface are set on cloth to be detected;
(3) obtaining, there is the cloth reference picture of the shade of the label to determine cloth according to the cloth reference picture Whether pattern is consistent.
Further, the label in the step (2) is arranged in Fabric Defects Inspection.
Further, the step (3) includes:
(31) multiple sets of light sources is set around conveyer belt, and the light source can issue the Line of light of one-way;
(32) cloth to be detected first position on a moving belt and the second place are irradiated using the light source, The first cloth reference picture and the second cloth reference picture are acquired respectively at two positions to cloth to be detected simultaneously;
(33) information of cloth label is determined according to the first cloth reference picture and the second cloth reference picture.
Further, the step (31) includes:
(311) one group of light source, the one group of light source is arranged in the first side at the first position on a moving belt For irradiating the cloth to be detected on conveyer belt from the first side;
(312) second group of light source is arranged in second side of the second place on a moving belt, wherein the first side and the Two sides are not ipsilateral for opposite two, and second group of light source is used for from the cloth to be detected on second side irradiation conveyer belt.
Further, the step (32) includes:
(321) the first image collecting device and the second figure is respectively set above the first position and the second position As acquisition device, described image acquisition device is used to the cloth reference picture that acquisition is disposed below;
(322) at the first moment, the one group of light source is since the opposite direction of conveyer belt direction of advance, towards conveyer belt Direction of advance rotates 180 ° in the plane for the direction of advance for being parallel to conveyer belt, the one group of light source during this 180 ° The cloth to be detected of irradiation always;
(323) during one group of light source rotation, the first image collecting device is with the figure of first frequency acquisition cloth As being used as the first cloth reference picture;
(324) at the second moment, second group of light source is since conveyer belt direction of advance, towards the anti-of transmission tape travel Direction rotates 180 ° in the plane for the direction of advance for being parallel to conveyer belt, the beginning of second group of light source during this 180 ° Cloth to be detected is irradiated eventually, and at the second moment, the one group of light source has completed 180 ° of rotations;
(325) during second group of light source rotation, the second image collecting device is with the figure of second frequency acquisition cloth As being used as the second cloth reference picture.
Further, the first frequency is identical with the second frequency.
Further, the step (31) further include:
(313) plane locating for the cloth of direction provides ambient lighting light on a moving belt.
Further, the step (33) includes:
(3301) determine the first image acquisition device collected the during the one group of light source rotates 180 ° One cloth reference picture and the last one cloth reference picture;
(3302) time for being acquired according to conveyer belt transmission speed and the last one described cloth reference picture and described the One cloth reference picture acquisition time between time difference, obtain cloth the first image acquisition device acquisition during The length moved on conveyer belt;
(3303) according to first cloth reference picture and the last one cloth reference picture and pre-stored packet It includes the length that the cloth image of cloth pattern is matched, and moved on a moving belt in conjunction with the cloth, determines described the The corresponding practical cloth pattern image of the first image acquisition device acquired image during one group of light source rotates 180 °;
(3304) based on first cloth reference picture and the last one cloth reference picture and pre-stored packet Include cloth pattern cloth image carry out it is matched as a result, obtain it is collected from the first image acquisition device, remove the One cloth reference picture reality corresponding with other each cloth reference pictures except the last one cloth reference picture Border cloth pattern image;
(3305) collected from the first image acquisition device, remove first cloth reference picture and the last one In other cloth reference pictures except cloth reference picture, the corresponding practical cloth figure of these cloth reference pictures is removed Case image obtains multiple label shadow images;
(3306) based on label each in first label shadow image in chronological order in one group of light source The lower shade generated of irradiation, determines the neighborhood of the predefined size around each shade region;
(3307) each label determined in shadow image is marked to generate under one group of light source irradiation based at one The neighborhood of predefined size around shade region calculates remaining each label shadow image in multiple label shadow images The sum of shaded area in the neighborhood, by this and as the first reference value of label;
(3308) determine second image collecting device collected the during second group of light source rotates 180 ° Two cloth reference pictures and the last one cloth reference picture;
(3309) time for being acquired according to conveyer belt transmission speed and the last one described cloth reference picture and described the Two cloth reference pictures acquisition time between time difference, obtain cloth during second image acquisition device The length moved on conveyer belt;
(3310) according to second cloth reference picture and the last one cloth reference picture and pre-stored packet It includes the length that the cloth image of cloth pattern is matched, and moved on a moving belt in conjunction with the cloth, determines described the The corresponding practical cloth pattern image of image that second image acquisition device arrives during two groups of light sources rotate 180 °;
(3311) based on second cloth reference picture and the last one cloth reference picture and pre-stored packet Include cloth pattern cloth image carry out it is matched as a result, obtain from second image acquisition device to, remove the Two cloth reference pictures reality corresponding with other each cloth reference pictures except the last one cloth reference picture Border cloth pattern image;
(3312) from second image acquisition device to, remove second cloth reference picture and the last one In other cloth reference pictures except cloth reference picture, the corresponding practical cloth figure of these cloth reference pictures is removed Case image obtains multiple label shadow images;
(3313) based on label each in second label shadow image in chronological order in second group of light source The lower shade generated of irradiation, determines the neighborhood of the predefined size around each shade region;
(3314) each label determined in shadow image is marked to generate in the case where second group of light source irradiates based at one The neighborhood of predefined size around shade region calculates remaining each label shadow image in multiple label shadow images The sum of shaded area in the neighborhood, by this and as the second reference value of label;
(3315) when the absolute value of the difference of first reference value of label and the second reference value of label is more than preset threshold, Indicate that cloth pattern is inconsistent.
Further, the one group of light source and second group of light source height apart from plane where cloth on a moving belt It spends not identical.
Further, the one group of light source and second group of light source are in the direction perpendicular to the transmission tape travel Height than fault to be detected is high.
The beneficial effects of the present invention are:
(1) it overcomes and is needed existing for the image analysis algorithm for often relying on generally use in the prior art in the prior art The drawbacks of expending great amount of images processing time and image processing machine resource;
(2) the graphic image data processing operand in cloth pattern consistency identification process is reduced;
(3) algorithm complexity that cloth pattern consistency determines is reduced;
(4) detection of cloth pattern consistency can be quickly and accurately realized.
Detailed description of the invention
Fig. 1 shows the flow chart of the pattern consistency recognition methods in cloth detection according to the present invention.
Specific embodiment
As shown in Figure 1, the present invention provides the pattern consistency recognition methods in a kind of detection of cloth, comprising:
(1) cloth to be detected is set on the conveyer belt of one-way movement, the direction of motion of the conveyer belt and the length of cloth It is consistent to spend direction;
(2) multiple labels extended perpendicular to cloth surface are set on cloth to be detected;
(3) obtaining, there is the cloth reference picture of the shade of the label to determine cloth according to the cloth reference picture Whether pattern is consistent.
Preferably, the label in the step (2) is arranged in Fabric Defects Inspection.
Preferably, the step (3) includes:
(31) multiple sets of light sources is set around conveyer belt, and the light source can issue the Line of light of one-way;
(32) cloth to be detected first position on a moving belt and the second place are irradiated using the light source, The first cloth reference picture and the second cloth reference picture are acquired respectively at two positions to cloth to be detected simultaneously;
(33) information of cloth label is determined according to the first cloth reference picture and the second cloth reference picture.
Preferably, the step (31) includes:
(311) one group of light source, the one group of light source is arranged in the first side at the first position on a moving belt For irradiating the cloth to be detected on conveyer belt from the first side;
(312) second group of light source is arranged in second side of the second place on a moving belt, wherein the first side and the Two sides are not ipsilateral for opposite two, and second group of light source is used for from the cloth to be detected on second side irradiation conveyer belt.
Preferably, the step (32) includes:
(321) the first image collecting device and the second figure is respectively set above the first position and the second position As acquisition device, described image acquisition device is used to the cloth reference picture that acquisition is disposed below;
(322) at the first moment, the one group of light source is since the opposite direction of conveyer belt direction of advance, towards conveyer belt Direction of advance rotates 180 ° in the plane for the direction of advance for being parallel to conveyer belt, the one group of light source during this 180 ° The cloth to be detected of irradiation always;
(323) during one group of light source rotation, the first image collecting device is with the figure of first frequency acquisition cloth As being used as the first cloth reference picture;
(324) at the second moment, second group of light source is since conveyer belt direction of advance, towards the anti-of transmission tape travel Direction rotates 180 ° in the plane for the direction of advance for being parallel to conveyer belt, the beginning of second group of light source during this 180 ° Cloth to be detected is irradiated eventually, and at the second moment, the one group of light source has completed 180 ° of rotations;
(325) during second group of light source rotation, the second image collecting device is with the figure of second frequency acquisition cloth As being used as the second cloth reference picture.
Preferably, the first frequency is identical with the second frequency.
Preferably, the step (31) further include:
(313) plane locating for the cloth of direction provides ambient lighting light on a moving belt.
Preferably, the step (33) includes:
(3301) determine the first image acquisition device collected the during the one group of light source rotates 180 ° One cloth reference picture and the last one cloth reference picture;
(3302) time for being acquired according to conveyer belt transmission speed and the last one described cloth reference picture and described the One cloth reference picture acquisition time between time difference, obtain cloth the first image acquisition device acquisition during The length moved on conveyer belt;
(3303) according to first cloth reference picture and the last one cloth reference picture and pre-stored packet It includes the length that the cloth image of cloth pattern is matched, and moved on a moving belt in conjunction with the cloth, determines described the The corresponding practical cloth pattern image of the first image acquisition device acquired image during one group of light source rotates 180 °;
(3304) based on first cloth reference picture and the last one cloth reference picture and pre-stored packet Include cloth pattern cloth image carry out it is matched as a result, obtain it is collected from the first image acquisition device, remove the One cloth reference picture reality corresponding with other each cloth reference pictures except the last one cloth reference picture Border cloth pattern image;
(3305) collected from the first image acquisition device, remove first cloth reference picture and the last one In other cloth reference pictures except cloth reference picture, the corresponding practical cloth figure of these cloth reference pictures is removed Case image obtains multiple label shadow images;
(3306) based on label each in first label shadow image in chronological order in one group of light source The lower shade generated of irradiation, determines the neighborhood of the predefined size around each shade region;
(3307) each label determined in shadow image is marked to generate under one group of light source irradiation based at one The neighborhood of predefined size around shade region calculates remaining each label shadow image in multiple label shadow images The sum of shaded area in the neighborhood, by this and as the first reference value of label;
(3308) determine second image collecting device collected the during second group of light source rotates 180 ° Two cloth reference pictures and the last one cloth reference picture;
(3309) time for being acquired according to conveyer belt transmission speed and the last one described cloth reference picture and described the Two cloth reference pictures acquisition time between time difference, obtain cloth during second image acquisition device The length moved on conveyer belt;
(3310) according to second cloth reference picture and the last one cloth reference picture and pre-stored packet It includes the length that the cloth image of cloth pattern is matched, and moved on a moving belt in conjunction with the cloth, determines described the The corresponding practical cloth pattern image of image that second image acquisition device arrives during two groups of light sources rotate 180 °;
(3311) based on second cloth reference picture and the last one cloth reference picture and pre-stored packet Include cloth pattern cloth image carry out it is matched as a result, obtain from second image acquisition device to, remove the Two cloth reference pictures reality corresponding with other each cloth reference pictures except the last one cloth reference picture Border cloth pattern image;
(3312) from second image acquisition device to, remove second cloth reference picture and the last one In other cloth reference pictures except cloth reference picture, the corresponding practical cloth figure of these cloth reference pictures is removed Case image obtains multiple label shadow images;
(3313) based on label each in second label shadow image in chronological order in second group of light source The lower shade generated of irradiation, determines the neighborhood of the predefined size around each shade region;
(3314) each label determined in shadow image is marked to generate in the case where second group of light source irradiates based at one The neighborhood of predefined size around shade region calculates remaining each label shadow image in multiple label shadow images The sum of shaded area in the neighborhood, by this and as the second reference value of label;
(3315) when the absolute value of the difference of first reference value of label and the second reference value of label is more than preset threshold, Indicate that cloth pattern is inconsistent.
Preferably, the one group of light source and second group of light source height apart from plane where cloth on a moving belt It is not identical.
Preferably, the one group of light source and second group of light source compare in the direction perpendicular to the transmission tape travel The height of fault to be detected wants high.
Above for the purpose that narration made by presently preferred embodiments of the present invention is to illustrate, and it is not intended to limit essence of the invention Really it is disclosed form, learns and make an amendment or change to be possible based on above introduction or from the embodiment of the present invention , embodiment is to explain the principle of the present invention and those skilled in the art being allowed to exist with various embodiments using the present invention It is selected in practical application and narration, technical idea attempt of the invention is determined by claim and its equalization.

Claims (6)

1. the pattern consistency recognition methods in a kind of cloth detection, includes the following steps:
(1) cloth to be detected is set on the conveyer belt of one-way movement, the direction of motion of the conveyer belt and the length side of cloth To consistent;
(2) multiple labels extended perpendicular to cloth surface are set on cloth to be detected;
(3) obtaining, there is the cloth reference picture of the shade of the label to determine cloth pattern according to the cloth reference picture It is whether consistent;
Label in the step (2) is arranged in Fabric Defects Inspection;
The step (3) includes the following steps:
(31) multiple sets of light sources is set around conveyer belt, and the light source can issue the Line of light of one-way;
(32) cloth to be detected first position on a moving belt and the second place are irradiated using the light source, simultaneously The first cloth reference picture and the second cloth reference picture are acquired respectively at two positions to cloth to be detected;
(33) information of cloth label is determined according to the first cloth reference picture and the second cloth reference picture;
The step (31) includes the following steps:
(311) one group of light source is arranged in the first side at the first position on a moving belt, and the one group of light source is used for Cloth to be detected from the first side irradiation conveyer belt;
(312) second group of light source is arranged in second side of the second place on a moving belt, wherein the first side and second side Not ipsilateral for opposite two, second group of light source is used for from the cloth to be detected on second side irradiation conveyer belt;
It is characterized in that, the step (32) includes the following steps:
(321) the first image collecting device is respectively set above the first position and the second position and the second image is adopted Acquisition means, described image acquisition device are used to the cloth reference picture that acquisition is disposed below;
(322) at the first moment, the one group of light source is since the opposite direction of conveyer belt direction of advance, towards transmission tape travel Direction rotates 180 ° in the plane for the direction of advance for being parallel to conveyer belt, the beginning of the one group of light source during this 180 ° Cloth to be detected is irradiated eventually;
(323) during one group of light source rotation, the first image collecting device is made with the image of first frequency acquisition cloth For the first cloth reference picture;
(324) at the second moment, second group of light source is since conveyer belt direction of advance, towards the negative side of transmission tape travel To rotating 180 ° in the plane for the direction of advance for being parallel to conveyer belt, second group of light source are always during this 180 ° Cloth to be detected is irradiated, and at the second moment, the one group of light source has completed 180 ° of rotations;
(325) during second group of light source rotation, the second image collecting device is made with the image of second frequency acquisition cloth For the second cloth reference picture.
2. the method according to claim 1, wherein the first frequency is identical with the second frequency.
3. according to the method described in claim 2, it is characterized in that, the step (31) further includes following steps:
(313) plane locating for the cloth of direction provides ambient lighting light on a moving belt.
4. according to the method described in claim 3, it is characterized in that, the step (33) includes the following steps:
(3301) determine the first image acquisition device collected first during the one group of light source rotates 180 ° Cloth reference picture and the last one cloth reference picture;
(3302) according to the time and first cloth of conveyer belt transmission speed and the acquisition of the last one described cloth reference picture Time difference between the time of reference picture acquisition obtains cloth and is transmitting during the acquisition of the first image acquisition device Take mobile length;
(3303) according to first cloth reference picture and the last one cloth reference picture and it is pre-stored include cloth The length that the cloth image of pattern is matched, and moved on a moving belt in conjunction with the cloth is determined at described first group The corresponding practical cloth pattern image of the first image acquisition device acquired image during light source rotates 180 °;
(3304) first cloth reference picture and the last one cloth reference picture are based on pre-stored including cloth The cloth image of pattern carry out it is matched as a result, obtain it is collected from the first image acquisition device, remove first Cloth reference picture practical cloth corresponding with other each cloth reference pictures except the last one cloth reference picture Pattern image;
(3305) collected from the first image acquisition device, first cloth reference picture of removing and the last one cloth In other cloth reference pictures except reference picture, the corresponding practical cloth pattern figure of these cloth reference pictures is removed Picture obtains multiple label shadow images;
(3306) it is irradiated based on label each in first label shadow image in chronological order in one group of light source The shade of lower generation determines the neighborhood of the predefined size around each shade region;
(3307) based on the shade for marking each label determined in shadow image to generate under one group of light source irradiation at one The neighborhood of predefined size around region calculates in multiple label shadow images remaining each label shadow image at this The sum of shaded area in neighborhood, by this and as the first reference value of label;
(3308) determine second image collecting device collected first during second group of light source rotates 180 ° Cloth reference picture and the last one cloth reference picture;
(3309) according to the time and second cloth of conveyer belt transmission speed and the acquisition of the last one described cloth reference picture Time difference between the time of reference picture acquisition obtains cloth and is transmitting during second image acquisition device Take mobile length;
(3310) according to first cloth reference picture and the last one cloth reference picture and it is pre-stored include cloth The length that the cloth image of pattern is matched, and moved on a moving belt in conjunction with the cloth is determined at described second group The light source corresponding practical cloth pattern image of image that second image acquisition device arrives during rotating 180 °;
(3311) first cloth reference picture and the last one cloth reference picture are based on pre-stored including cloth The cloth image of pattern carry out it is matched as a result, obtain from second image acquisition device to, remove first Cloth reference picture practical cloth corresponding with other each cloth reference pictures except the last one cloth reference picture Pattern image;
(3312) from second image acquisition device to, remove first cloth reference picture and the last one cloth In other cloth reference pictures except reference picture, the corresponding practical cloth pattern figure of these cloth reference pictures is removed Picture obtains multiple label shadow images;
(3313) it is irradiated based on label each in second label shadow image in chronological order in second group of light source The shade of lower generation determines the neighborhood of the predefined size around each shade region;
(3314) based on the shade for marking each label determined in shadow image to generate in the case where second group of light source irradiates at one The neighborhood of predefined size around region calculates in multiple label shadow images remaining each label shadow image at this The sum of shaded area in neighborhood, by this and as the second reference value of label;
(3315) it when the absolute value of the difference of first reference value of label and the second reference value of label is more than preset threshold, indicates Cloth pattern is inconsistent.
5. according to the method described in claim 4, it is characterized in that, the one group of light source and second group of light source are transmitting The height taken apart from plane where cloth is not identical.
6. according to the method described in claim 5, it is characterized in that, the one group of light source and second group of light source are vertical In higher than the height of fault to be detected on the direction of the transmission tape travel.
CN201710463911.1A 2017-06-19 2017-06-19 Pattern consistency recognition methods in cloth detection Active CN107102007B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710463911.1A CN107102007B (en) 2017-06-19 2017-06-19 Pattern consistency recognition methods in cloth detection

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710463911.1A CN107102007B (en) 2017-06-19 2017-06-19 Pattern consistency recognition methods in cloth detection

Publications (2)

Publication Number Publication Date
CN107102007A CN107102007A (en) 2017-08-29
CN107102007B true CN107102007B (en) 2019-11-26

Family

ID=59661036

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710463911.1A Active CN107102007B (en) 2017-06-19 2017-06-19 Pattern consistency recognition methods in cloth detection

Country Status (1)

Country Link
CN (1) CN107102007B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110239232B (en) * 2019-04-08 2020-10-16 上海泰威技术发展股份有限公司 Intelligent identification method for multi-pattern change printing of plate
CN115937052B (en) * 2023-03-14 2023-05-16 四川福莱宝生物科技有限公司 Gel electrophoresis image processing method, device, equipment and medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0482942A (en) * 1990-07-16 1992-03-16 Toyota Autom Loom Works Ltd Fabric inspection system
CN1311834A (en) * 1998-07-24 2001-09-05 泽韦格路瓦有限公司 Method and device for evaluating defect in flat textile structures
CN101035946A (en) * 2004-04-19 2007-09-12 3M创新有限公司 Apparatus and method for the automated marking of defects on webs of material
CN101819165A (en) * 2009-02-27 2010-09-01 圣戈本玻璃法国公司 Method and system for detecting defect of patterned substrate
CN101923059A (en) * 2010-04-15 2010-12-22 北京经纬纺机新技术有限公司 Automatic cloth inspection method and system
CN103604809A (en) * 2013-10-22 2014-02-26 江南大学 Pattern cloth flaw online visual inspection method

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH0482942A (en) * 1990-07-16 1992-03-16 Toyota Autom Loom Works Ltd Fabric inspection system
CN1311834A (en) * 1998-07-24 2001-09-05 泽韦格路瓦有限公司 Method and device for evaluating defect in flat textile structures
CN101035946A (en) * 2004-04-19 2007-09-12 3M创新有限公司 Apparatus and method for the automated marking of defects on webs of material
CN101819165A (en) * 2009-02-27 2010-09-01 圣戈本玻璃法国公司 Method and system for detecting defect of patterned substrate
CN101923059A (en) * 2010-04-15 2010-12-22 北京经纬纺机新技术有限公司 Automatic cloth inspection method and system
CN103604809A (en) * 2013-10-22 2014-02-26 江南大学 Pattern cloth flaw online visual inspection method

Also Published As

Publication number Publication date
CN107102007A (en) 2017-08-29

Similar Documents

Publication Publication Date Title
Çelik et al. Development of a machine vision system: real-time fabric defect detection and classification with neural networks
CN108548820B (en) Cosmetic paper label defect detection method
CN111179225B (en) Test paper surface texture defect detection method based on gray gradient clustering
CN103729655B (en) A kind of detection method for slice component vision localization
CN107102007B (en) Pattern consistency recognition methods in cloth detection
CN103604809B (en) A kind of online visible detection method of pattern cloth flaw
KR102143354B1 (en) Method of automatically detecting defect location in fabric and system for the same
CN106918600A (en) A kind of web surface defects detection and labeling method based on machine vision
CN115816471B (en) Unordered grabbing method, unordered grabbing equipment and unordered grabbing medium for multi-view 3D vision guided robot
CN109345554A (en) A kind of adhesion mushroom vision in-situ measuring method based on RGB-D camera
CN113643294A (en) Textile defect self-adaptive detection method based on frequency spectrum analysis
CN105866136A (en) Camera module optical filter gluing detection apparatus and method
WO2023052537A1 (en) Method for detecting at least one defect on a support, device and computer program associated
US20210343002A1 (en) Online Detection Method of Circular Weft Knitting Stripe Defects Based on Gray Gradient Method
CN107063130A (en) A kind of workpiece automatic soldering method based on optical grating projection three-dimensionalreconstruction
CN111656168A (en) Virtual camera array for inspection of manufactured web
CN112119360B (en) Method for automatically cutting soft sheet material and related numerical control equipment
CN107246843B (en) For the uniformity testing method in cloth measurer for thickness
CN108538961B (en) Method for positioning and marking crystalline silicon-based solar cell wafer
CN106770322A (en) Calibration point depth detection method and temperature controller appearance detecting method
Ren et al. A fine grained digital textile printing system based on image registration
CN102663769A (en) Method for target detection and attitude estimation based on main gradient direction characteristics
CN113145473A (en) Intelligent fruit sorting system and method
DE112020006158T5 (en) Image good/bad learning device, image good/bad determining device and image reading device
Shanthi et al. Robust fabric defects inspection system using deep learning architecture

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
TA01 Transfer of patent application right
TA01 Transfer of patent application right

Effective date of registration: 20191024

Address after: 310013 room 119-3, No. 18, Shihushan, Xihu District, Hangzhou City, Zhejiang Province

Applicant after: ZHEJIANG PAPA INFANTS ARTICLE CO., LTD.

Address before: 610000 Sichuan city of Chengdu province high tech Zone Kyrgyzstan Road No. 666 Building 2 floor 13 No. 2

Applicant before: Chengdu Hui Zhi distant view Science and Technology Ltd.

GR01 Patent grant
GR01 Patent grant