CN107356207B - A kind of the winged of view-based access control model identification knits vamp deformation detection method - Google Patents

A kind of the winged of view-based access control model identification knits vamp deformation detection method Download PDF

Info

Publication number
CN107356207B
CN107356207B CN201710502157.8A CN201710502157A CN107356207B CN 107356207 B CN107356207 B CN 107356207B CN 201710502157 A CN201710502157 A CN 201710502157A CN 107356207 B CN107356207 B CN 107356207B
Authority
CN
China
Prior art keywords
mark point
vamp
deformation
amount
knit
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
CN201710502157.8A
Other languages
Chinese (zh)
Other versions
CN107356207A (en
Inventor
杜天福
元波
张晓龙
廖龙兴
黄天财
王平江
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.)
Quanzhou Huazhong University Of Science And Technology Institute Of Manufacturing
Original Assignee
Quanzhou Huazhong University Of Science And Technology Institute Of Manufacturing
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 Quanzhou Huazhong University Of Science And Technology Institute Of Manufacturing filed Critical Quanzhou Huazhong University Of Science And Technology Institute Of Manufacturing
Priority to CN201710502157.8A priority Critical patent/CN107356207B/en
Publication of CN107356207A publication Critical patent/CN107356207A/en
Application granted granted Critical
Publication of CN107356207B publication Critical patent/CN107356207B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/16—Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
    • 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
    • G01N21/8851—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

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Cosmetics (AREA)

Abstract

The present invention passes through in the mark point to setting on cut-out with contrast for flying to knit vamp, and combine the location information of Visual identification technology acquisition mark point, obtain vamp stretcher strain amount and torsional deflection amount according to the location information combination threshold process of mark point, judge stretcher strain amount and torsional deflection amount whether respectively fall in stretcher strain amount threshold range and torsional deflection amount threshold range can determine whether to fly to knit vamp it is whether qualified.For artificial detection, which can be realized automatic detection, and detection efficiency is high, eliminate the influence of human factor, and the stability of detection is high.

Description

A kind of the winged of view-based access control model identification knits vamp deformation detection method
Technical field
The present invention relates to a kind of deformation detection methods for flying to knit vamp, and in particular to a kind of the winged of view-based access control model identification knits shoes Face deformation detection method.
Background technique
Fly to knit vamp technology to be disposably to knit out the fabric of a shoes to come, substitutes multi-panel sewing machine technique.This Sample greatly increases the production efficiency of vamp, but knit out come vamp it is difficult to ensure that its shape stability, it may occur that Deformation.Scene needs to detect decorative pattern deflection on vamp after calendaring technology sizing, thus judges whether it is qualified product, such as If deformation will correct deformation by the flat technique of soup greatly very much.Before this technological invention, the deformation detection for flying to knit vamp is using people Mode of the work to film original text decorative pattern, the slow low efficiency of speed.
Summary of the invention
Winged the purpose of the present invention is to provide a kind of identification of view-based access control model knits vamp deformation detection method, by flying Increase specific markers point is knitted on vamp, sets deformation judgement in conjunction with the location information that Visual identification technology obtains mark point line position of going forward side by side Judge with torsional deflection, thus judgement fly to knit vamp it is whether qualified.
To achieve the above object, the technical solution adopted by the present invention is that:
A kind of the winged of view-based access control model identification knits vamp deformation detection method, by fly to knit vamp on cut-out Mark point with contrast is set, and combines the location information of Visual identification technology acquisition mark point, the position according to mark point Confidence breath combines threshold process to obtain vamp stretcher strain amount and torsional deflection amount, judges stretcher strain amount and torsional deflection amount is It is no respectively fall in stretcher strain amount threshold range and torsional deflection amount threshold range can determine whether to fly to knit vamp it is whether qualified.
The detection method specifically includes the following steps:
Step 1, in the mark point to setting on cut-out with contrast for flying to knit vamp, which includes one Tagging point, a size-mark point and at least one set of deformation mark point；
The datum mark that the position mark point is identified as vamp is arranged in vamp symmetrical center line and is located at entire The centre of area point region of vamp；
The size-mark point is arranged in vamp symmetrical center line at the position of close over；
One group of deformation mark point is made of two deformation mark points for being separately positioned on vamp two sides；
Step 2, by camera to flying to knit vamp and take pictures obtaining to fly to knit vamp picture, then in conjunction with Visual identification technology In the position for flying to knit acquisition position mark point, size-mark point and deformation mark point in vamp picture；
Step 3 opens up multiple threads an information processing is marked, wherein
First thread is for calculating stretching distance BXi, i=1,2 ..., 3n and windup-degree ∠ θi, i=1,2 ..., 2n, n are the group number of deformation mark point；The stretching distance be in every group of deformation mark point the distance between 2 deformation mark points with And deformation mark point, at a distance from position mark point, windup-degree is the line and middle line of deformation mark point and position mark point Angle；
Second thread is for calculating the distance between size-mark point and position mark point to obtain corresponding size, according to this Size transfers the ideal stretching distance BX for flying to knit vampi', i=1,2 ..., 3n, ideal windup-degree ∠ θi', i=1,2 ..., 2n and stretcher strain amount threshold range Δ Xmin~Δ Xmax and torsional deflection amount threshold range Δ ∠ min~Δ ∠ max；
Step 4 calculates stretcher strain amount and torsional deflection amount, and stretcher strain amount is what first thread obtained
The absolute value for the difference between ideal stretching distance that stretching distance and the second thread obtain, i.e.,
ΔBXi=| BXi-BX′i|, i=1,2 ..., 3n
Torsional deflection amount is the absolute value of the difference between the windup-degree of first thread arrived and ideal windup-degree, i.e.,
Δ∠θi=| ∠ θi-∠θi' |, i=1,2 ..., 2n
Step 5 seeks comprehensive deformation amount using weighted average method, must stretch comprehensive deformation amount are as follows:
Reverse comprehensive deformation amount are as follows:
WXiFor Δ BXiWeighting coefficient, W ∠iFor Δ ∠iWeighting coefficient；
Step 6 judges to stretch comprehensive deformation amount whether in stretcher strain amount threshold range, and torsion comprehensive deformation amount Whether in torsional deflection amount threshold range, threshold range only is fallen into comprehensive deformation amount is reversed when stretching comprehensive deformation amount, Fly to knit vamp to be just qualified products, is otherwise substandard product.
For artificial detection, which can be realized automatic detection, and detection efficiency is high, eliminate human factor It influences, the stability of detection is high.
Detailed description of the invention
Fig. 1 is overhaul flow chart of the present invention；
Fig. 2 is that the present invention flies to knit the mark point schematic diagram of vamp.
Specific embodiment
Winged present invention discloses a kind of identification of view-based access control model knits vamp deformation detection method comprising following steps:
Step 1, in the mark point to setting on cut-out with contrast for flying to knit vamp, which includes one Tagging point, a size-mark point and at least one set of deformation mark point；
The datum mark that the position mark point is identified as vamp is arranged in vamp symmetrical center line and is located at entire The centre of area region of vamp；
The size-mark point is arranged in vamp symmetrical center line at the position of toe cap；
One group of deformation mark point is made of two deformation mark points for being separately positioned on vamp two sides；
Step 2, by camera to flying to knit vamp and take pictures obtaining to fly to knit vamp picture, then in conjunction with Visual identification technology In the position for flying to knit acquisition position mark point, size-mark point and deformation mark point in vamp picture；
Step 3 opens up multiple threads an information processing is marked, wherein
First thread is for calculating stretching distance BXi, i=1,2 ..., 3n and windup-degree ∠ θi, i=1,2 ..., 2n, n are the group number of deformation mark point；The stretching distance be in every group of deformation mark point the distance between 2 deformation mark points with And deformation mark point, at a distance from position mark point, windup-degree is the line and middle line of deformation mark point and position mark point Angle；
Second thread is for calculating the distance between size-mark point and position mark point to obtain corresponding size, according to this Size transfers the ideal stretching distance BX for flying to knit vampi', i=1,2 ..., 3n, ideal windup-degree ∠ θi', i=1,2 ..., 2n and stretcher strain amount threshold range Δ Xmin~Δ Xmax and torsional deflection amount threshold range Δ ∠ min~Δ ∠ max；
Step 4 calculates stretcher strain amount and torsional deflection amount, stretcher strain amount be the stretching distance that first thread obtains and The absolute value for the difference between ideal stretching distance that second thread obtains, i.e.,
ΔBXi=| BXi-BX′i|, i=1,2 ..., 3n
Torsional deflection amount is the absolute value of the difference between the windup-degree of first thread arrived and ideal windup-degree, i.e.,
Δ∠θi=| ∠ θi-∠θi' |, i=1,2 ..., 2n
Step 5 seeks comprehensive deformation amount using weighted average method, must stretch comprehensive deformation amount are as follows:
Reverse comprehensive deformation amount are as follows:
WXiFor Δ BXiWeighting coefficient, W ∠iFor Δ ∠iWeighting coefficient, the weighting coefficient by experiment test gained；
Step 6 judges to stretch comprehensive deformation amount whether in stretcher strain amount threshold range, and torsion comprehensive deformation amount Whether in torsional deflection amount threshold range, threshold range only is fallen into comprehensive deformation amount is reversed when stretching comprehensive deformation amount, Fly to knit vamp to be just qualified products, is otherwise substandard product.
In an embodiment of the present invention, setting position mark point is PA, and setting size-mark point is PF, and deformation mark is arranged Point is P00 and P01, P10 and P11 and P20 and tri- groups of P21, then stretching distance are as follows:
BX1=| P00-P01 |
BX2=| P10-P11 |
BX3=| P20-P21 |
BX4=| P00-PA |
BX5=| P10-PA |
BX6=| P20-PA |
BX7=| PA-P01 |
BX8=| PA-P11 |
BX9=| PA-P21 |
Windup-degree are as follows:
∠θ1=∠ PF-PA-P00
∠θ2=∠ PF-PA-P01
∠θ3=∠ PF-PA-P10
∠θ4=∠ PF-PA-P11
∠θ5=∠ PF-PA-P20
∠θ6=∠ PF-PA-P21
The distance between size-mark point PF and position mark point PA are to obtain corresponding size, corresponding relationship such as following table institute Show,
Table 1
Corresponding size is transferred to fly to knit the ideal stretching distance BX of vampi', i=1,2 ..., 9, ideal windup-degree ∠ θi', I=1,2 ..., 6, stretcher strain amount threshold range Δ Xmin~Δ Xmax, torsional deflection amount threshold range Δ ∠ min~Δ ∠ max；
Calculate stretcher strain amount are as follows:
ΔBXi=| BXi-BXi' |, i=1,2 ..., 9
Torsional deflection amount are as follows:
Δ∠θi=| ∠ θi-∠θi' |, i=1,2 ..., 6
Δ ∠ θ i=| ∠ θ i- ∠ θ i ' |, i=1,2 ..., 6
It finally seeks stretching comprehensive deformation amount are as follows:
Reverse comprehensive deformation amount are as follows:
As Δ X ∈ [Δ Xmin, Δ Xmax], Δ ∠ ∈ [Δ ∠ min, Δ ∠ max], fly to knit vamp just to be qualified production Otherwise product are non-qualified products.
The present invention is by flying to knit knowing to mark point of the setting with contrast on cut-out, and in conjunction with vision for vamp Other technology obtains the location information of mark point, and the location information combination threshold process according to mark point obtains vamp stretcher strain amount And torsional deflection amount, judge whether stretcher strain amount and torsional deflection amount respectively fall in stretcher strain amount threshold range and torsion becomes Whether shape amount threshold range can determine whether to fly to knit vamp qualified.For artificial detection, which can be realized automatic inspection It surveys, detection efficiency is high, eliminates the influence of human factor, and the stability of detection is high.
The above is only the embodiment of the present invention, is not intended to limit the scope of the present invention, therefore all Any subtle modifications, equivalent variations and modifications to the above embodiments according to the technical essence of the invention still fall within this In the range of inventive technique scheme.

Claims (1)

1. a kind of the winged of view-based access control model identification knits vamp deformation detection method, it is characterised in that: by flying to knit the to be cut of vamp Except setting has the mark point of contrast on part, and the location information of Visual identification technology acquisition mark point is combined, according to mark The location information combination threshold process of note point obtains vamp stretcher strain amount and torsional deflection amount, judges stretcher strain amount and torsion Whether deflection respectively falls in stretcher strain amount threshold range and torsional deflection amount threshold range can determine whether fly whether to knit vamp It is qualified；
Specifically includes the following steps:
Step 1, in the mark point to setting on cut-out with contrast for flying to knit vamp, which includes position mark Remember point, a size-mark point and at least one set of deformation mark point；
The datum mark that the position mark point is identified as vamp is arranged in vamp symmetrical center line and is located at entire vamp Centre of area region；
The size-mark point is arranged in vamp symmetrical center line at the position of close over；
One group of deformation mark point is made of two deformation mark points for being separately positioned on vamp two sides；
Step 2, by camera to flying to knit vamp and take pictures obtaining to fly to knit vamp picture, flying then in conjunction with Visual identification technology Knit the position that position mark point, size-mark point and deformation mark point are obtained in vamp picture；
Step 3 opens up multiple threads an information processing is marked, wherein
First thread is for calculating stretching distance BXi, i=1,2 ..., 3n and windup-degree ∠ θi, i=1,2 ..., 2n, n For the group number of deformation mark point；The stretching distance is the distance between 2 deformation mark points and change in every group of deformation mark point For shape mark point at a distance from position mark point, windup-degree is deformation mark point and the line of position mark point and the folder of middle line Angle；
Second thread is for calculating the distance between size-mark point and position mark point to obtain corresponding size, according to the size Transfer the ideal stretching distance BX for flying to knit vampi', i=1,2 ..., 3n, ideal windup-degree ∠ θi', i=1,2 ..., 2n with And stretcher strain amount threshold range △ Xmin~△ Xmax and torsional deflection amount threshold range △ ∠ min~△ ∠ max；
Step 4 calculates stretcher strain amount and torsional deflection amount, and stretcher strain amount is the stretching distance and second that first thread obtains The absolute value for the difference between ideal stretching distance that thread obtains, i.e.,
△BXi=| BXi-BXi' |, i=1,2 ..., 3n
Torsional deflection amount is the absolute value of the difference between the windup-degree of first thread arrived and ideal windup-degree, i.e.,
△∠θi=| ∠ θi-∠θi' |, i=1,2 ..., 2n
Step 5 seeks comprehensive deformation amount using weighted average method, must stretch comprehensive deformation amount are as follows:
Reverse comprehensive deformation amount are as follows:
WXiFor △ BXiWeighting coefficient, W ∠iFor △ ∠iWeighting coefficient；
Step 6 judges to stretch comprehensive deformation amount whether in stretcher strain amount threshold range, and whether reverses comprehensive deformation amount In torsional deflection amount threshold range, threshold range only is fallen into comprehensive deformation amount is reversed when stretching comprehensive deformation amount, flies to knit Vamp is just qualified products, is otherwise substandard product.
CN201710502157.8A 2017-06-27 2017-06-27 A kind of the winged of view-based access control model identification knits vamp deformation detection method Active CN107356207B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710502157.8A CN107356207B (en) 2017-06-27 2017-06-27 A kind of the winged of view-based access control model identification knits vamp deformation detection method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710502157.8A CN107356207B (en) 2017-06-27 2017-06-27 A kind of the winged of view-based access control model identification knits vamp deformation detection method

Publications (2)

Publication Number Publication Date
CN107356207A CN107356207A (en) 2017-11-17
CN107356207B true CN107356207B (en) 2019-04-16

Family

ID=60273711

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710502157.8A Active CN107356207B (en) 2017-06-27 2017-06-27 A kind of the winged of view-based access control model identification knits vamp deformation detection method

Country Status (1)

Country Link
CN (1) CN107356207B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108346161B (en) * 2017-12-18 2020-07-21 上海咔咻智能科技有限公司 Flying woven vamp matching and positioning method based on image, system and storage medium thereof

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1784595A (en) * 2003-03-27 2006-06-07 马洛有限及两合公司 Method for inspecting the quality criteria of flat textile structures embodied in a multilayer form according to a contour
CN101979751A (en) * 2010-09-28 2011-02-23 中华人民共和国陕西出入境检验检疫局 Method for detecting dimensional stability of fabric based on image analysis
CN106767484A (en) * 2017-02-13 2017-05-31 北京和众视野科技有限公司 Fabric size rate of change automatic testing method, apparatus and system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1784595A (en) * 2003-03-27 2006-06-07 马洛有限及两合公司 Method for inspecting the quality criteria of flat textile structures embodied in a multilayer form according to a contour
CN101979751A (en) * 2010-09-28 2011-02-23 中华人民共和国陕西出入境检验检疫局 Method for detecting dimensional stability of fabric based on image analysis
CN106767484A (en) * 2017-02-13 2017-05-31 北京和众视野科技有限公司 Fabric size rate of change automatic testing method, apparatus and system

Also Published As

Publication number Publication date
CN107356207A (en) 2017-11-17

Similar Documents

Publication Publication Date Title
WO2021098323A1 (en) Cloth defect detection method based on multi-modal fusion deep learning
CN106485275B (en) A method of realizing that cover-plate glass is bonded with liquid crystal display positioning
CN105094337B (en) A kind of three-dimensional gaze estimation method based on iris and pupil
CN106875373B (en) Mobile phone screen MURA defect detection method based on convolutional neural network pruning algorithm
CN106203370B (en) A kind of test near and distance system based on computer vision technique
CN106373124B (en) Industrial products surface defect visible detection method based on gray level co-occurrence matrixes and RANSAC
CN109977781A (en) Method for detecting human face and device, readable storage medium storing program for executing
US20180182118A1 (en) Establishment method of 3D Saliency Model Based on Prior Knowledge and Depth Weight
CN105631852B (en) Indoor human body detection method based on depth image contour
US11205262B2 (en) Online detection method of circular weft knitting stripe defects based on gray gradient method
CN103384847A (en) Method for determining, in a natural posture, at least one geometric/physiognomic parameter associated with the mounting of an ophthalmic lens in a spectacle frame
CN102592288A (en) Method for matching pursuit of pedestrian target under illumination environment change condition
CN107356207B (en) A kind of the winged of view-based access control model identification knits vamp deformation detection method
CN109345513A (en) Cigarette package defect detection method with cigarette package posture calculation function
CN108346161B (en) Flying woven vamp matching and positioning method based on image, system and storage medium thereof
CN105825204A (en) Method for identifying power equipment meter at night through intelligent camera
CN110245592A (en) A method of for promoting pedestrian's weight discrimination of monitoring scene
CN104598914A (en) Skin color detecting method and device
Qiang et al. Detection method of PCB component based on automatic optical stitching algorithm
CN109191461A (en) A kind of Countryside Egg recognition methods and identification device based on machine vision technique
CN106235486A (en) Personalized clothing method based on 3D anthropometric scanning instrument
CN113610932B (en) Binocular camera external parameter calibration method and device
CN106504211A (en) Based on the low-light-level imaging method for improving SURF characteristic matchings
CN110135268A (en) Face comparison method, device, computer equipment and storage medium
Zhang et al. Weave pattern recognition by measuring fiber orientation with Fourier transform

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20171117

Assignee: QUANZHOU HUASHU ROBOT CO.,LTD.

Assignor: QUANZHOU-HUST INTELLIGENT MANUFACTURING FUTURE

Contract record no.: X2023350000282

Denomination of invention: A Visual Recognition Based Deformation Detection Method for Flywoven Upper

Granted publication date: 20190416

License type: Common License

Record date: 20230606