CN107622490A - Embedded plastic textile quality detection device and detection method based on machine vision - Google Patents
Embedded plastic textile quality detection device and detection method based on machine vision Download PDFInfo
- Publication number
- CN107622490A CN107622490A CN201710946683.3A CN201710946683A CN107622490A CN 107622490 A CN107622490 A CN 107622490A CN 201710946683 A CN201710946683 A CN 201710946683A CN 107622490 A CN107622490 A CN 107622490A
- Authority
- CN
- China
- Prior art keywords
- camera bellows
- guide roll
- camera
- image
- fabric
- 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
Abstract
A kind of embedded plastic textile quality detection device and detection method based on machine vision.Device：The camera bellows is fixed on above pedestal, the side of camera bellows is provided with fabric guide roll one, the opposite side of camera bellows is provided with fabric guide roll two, bottom in camera bellows is provided with artificial light source, top in camera bellows is provided with video camera, the signal output part of video camera is connected with digital signal processor, and gap, fabric guide roll one and fabric guide roll two are provided with the two side of camera bellows and is passed through for transmitting tested fabric from the gap on camera bellows.Method：Multi-scale wavelet transformation is carried out to textile image；Canny rim detections are carried out to textile image, Gaussian smoothing first is carried out to image, eliminate the abnormal pixel of individual gray；Non-maxima suppression is carried out using single order local derviation Difference Calculation gradient, and to gradient magnitude, positions the pixel that grey scale change is big in neighborhood；The binaryzation edge image of plastic fabric is worth to using dual threashold；Linear feature is extracted using Hough transformation, judges whether latitude and longitude running phenomenon.
Description
Technical field
The present invention relates to a kind of embedded plastic textile quality detection device and detection method based on machine vision, belong to
Plastic fabric quality detection device and detection method technical field.
Background technology
Existing machine vision technique is as follows mainly for cloth progress quality testing, identification fault, subject matter：Due to knitting
Thing breadth is wider, it is necessary to uses multiple while work high-resolution video camera to be needed to ensure the complete detection to product
When using the collaborative work of multiple cameras, it on the one hand must assure that the position of each camera is accurately installed, another aspect polyphaser
Data need to synchronize processing, to detect, identify that flaw whether there is, as having which kind of type belonged to.Therefore, method of comparison pair
System installation accuracy requires high, and when fabric transmission speed difference, light interference can all cause severe jamming to result, and adaptability is not
It is enough.And the detection algorithm based on statistic law, frequency domain method and modelling causes computation complexity height, run time due to model complexity
It is long.And statistic law changes sensitivity to cloth texture thickness, frequency domain method carries out multiscale analysis to image, but only to broadwise
It is effective with the fault of warp-wise, and markov random file and Parameters of Autoregressive Models selection have weight to treatment effect in modelling
Influence.
The content of the invention
The invention aims to solve the above-mentioned problems of the prior art, and then one kind is provided and is based on machine vision
Embedded plastic textile quality detection device and detection method.
The purpose of the present invention is achieved through the following technical solutions：
A kind of embedded plastic textile quality detection device based on machine vision, including：Pedestal, artificial light source, camera bellows,
Fabric guide roll one, fabric guide roll two, video camera and digital signal processor, the camera bellows are fixed on above pedestal, the side of camera bellows
Provided with fabric guide roll one, the opposite side of camera bellows is provided with fabric guide roll two, and the bottom in camera bellows is provided with artificial light source, and the top in camera bellows is set
There is video camera, the signal output part of video camera is connected with digital signal processor, and gap, selvage guide are provided with the two side of camera bellows
Roller one and fabric guide roll two pass through for transmitting tested fabric from the gap on camera bellows.
A kind of detection method of the embedded plastic textile quality detection device based on machine vision, step are as follows：
Step 1: carry out multi-scale wavelet transformation to textile image, extracted respectively under each yardstick in wavelet field signal and
The wavelet coefficient of noise, after the wavelet coefficient of noise is eliminated, textile image is reconstructed using wavelet inverse transformation, completes image denoising
Sound；
Step 2: carrying out Canny rim detections to textile image, Gaussian smoothing first is carried out to image, eliminates individual gray
Abnormal pixel；Then single order local derviation Difference Calculation gradient is utilized, and non-maxima suppression is carried out to gradient magnitude, positioning is adjacent
The big pixel of grey scale change (i.e. edge) in domain；The binaryzation edge image of plastic fabric is finally worth to using dual threashold；
Step 3: extracting linear feature using Hough transformation, extraction result is judged as warp being present if meeting given threshold
Parallel running phenomenon.
Beneficial effects of the present invention：
1st, detection object is plastic fabric.2nd, detection means uses camera bellows structure, eliminates ambient light to detection process
Interference, effectively increase the accuracy rate of detection.3rd, plastic fabric latitude and longitude running is detected using rim detection and Hough transformation
Fault, algorithm amount of calculation is few, and calculating speed is fast.4th, automatic detection is carried out using more cameras, detection range is big, the degree of accuracy
It is high.5th, IMAQ, analysis are realized using embedded detecting system, small volume is easy to install, and the speed of service is fast, suitable for industry
Production environment.
Brief description of the drawings
Fig. 1 is the structural representation of the embedded plastic textile quality detection device of the invention based on machine vision.
Fig. 2 is the flow chart of detection method.
Reference in Fig. 1,1 is pedestal, and 2 be artificial light source, and stable light source is provided for measurement, and 3 be camera bellows, with row
Except influence of the extraneous illumination to detection, 4 be fabric guide roll one, and 5 be fabric guide roll two, and 6 be tested fabric, and two fabric guide rolls are constantly defeated
Send tested fabric；7 be video camera, and 8 be digital signal processor (DSP), and 9 be gap.
Embodiment
Below in conjunction with accompanying drawing, the present invention is described in further detail：The present embodiment using technical solution of the present invention as
Under the premise of implemented, give detailed embodiment, but protection scope of the present invention is not limited to following embodiments.
A kind of as shown in figure 1, embedded plastic fabric quality detection dress based on machine vision involved by the present embodiment
Put, including：Pedestal 1, artificial light source 2, camera bellows 3, fabric guide roll 1, fabric guide roll 25, video camera 7 and digital signal processor 8, institute
Camera bellows 3 to be stated to be fixed on above pedestal 1, the side of camera bellows 3 is provided with fabric guide roll 1, and the opposite side of camera bellows 3 is provided with fabric guide roll 25,
Bottom in camera bellows 3 is provided with artificial light source 2, and the top in camera bellows 3 is provided with video camera 7, the signal output part and numeral of video camera 7
Signal processor 8 is connected, and gap 9 is provided with the two side of camera bellows 3, and fabric guide roll 1 and fabric guide roll 25 are used to transmit tested knit
Thing 6 passes through from the gap 9 on camera bellows 3.
The quantity of the artificial light source 2 is two to six.
The quantity of the video camera 7 is two to six.
The video camera 7 is digital camera.
The tested fabric of fabric guide roll transmission passes through camera bellows, and video camera and artificial light source are fixedly mounted inside camera bellows, and video camera is real
When gather plastic fabric image, number of cameras increases appropriate increase according to the area of plastic fabric, the quantity of artificial light source and
Position can be adjusted according to the area and reflective/saturating characteristic of plastic fabric.
As shown in Fig. 2 a kind of detection method of the embedded plastic textile quality detection device based on machine vision,
Step 1: carry out multi-scale wavelet transformation to textile image, extracted respectively under each yardstick in wavelet field signal and
The wavelet coefficient of noise, after the wavelet coefficient of noise is eliminated, textile image is reconstructed using wavelet inverse transformation, completes image denoising
Sound；
Step 2: carrying out Canny rim detections to textile image, Gaussian smoothing first is carried out to image, eliminates individual gray
Abnormal pixel；Then single order local derviation Difference Calculation gradient is utilized, and non-maxima suppression is carried out to gradient magnitude, positioning is adjacent
The big pixel of grey scale change (i.e. edge) in domain；The binaryzation edge image of plastic fabric is finally worth to using dual threashold；
Step 3: extracting linear feature using Hough transformation, extraction result is judged as warp being present if meeting given threshold
Parallel running phenomenon.
The foregoing is only a preferred embodiment of the present invention, these embodiments are all based on the present invention
Different implementations under general idea, and protection scope of the present invention is not limited thereto, it is any to be familiar with the art
Technical staff the invention discloses technical scope in, the change or replacement that can readily occur in, should all cover the present invention's
Within protection domain.Therefore, protection scope of the present invention should be defined by the protection domain of claims.
Claims (5)
1. a kind of embedded plastic textile quality detection device based on machine vision, including：Pedestal (1), artificial light source (2),
Camera bellows (3), fabric guide roll one (4), fabric guide roll two (5), video camera (7) and digital signal processor (8), it is characterised in that described
Camera bellows (3) is fixed on above pedestal (1), and the side of camera bellows (3) is provided with fabric guide roll one (4), and the opposite side of camera bellows (3), which is provided with, leads
Cloth rewinder roll two (5), the bottom in camera bellows (3) are provided with artificial light source (2), and the top in camera bellows (3) is provided with video camera (7), video camera
(7) signal output part is connected with digital signal processor (8), and gap (9), fabric guide roll are provided with the two side of camera bellows (3)
One (4) and fabric guide roll two (5) pass through for transmitting tested fabric (6) from the gap (9) on camera bellows (3).
2. the embedded plastic textile quality detection device according to claim 1 based on machine vision, it is characterised in that
The quantity of the artificial light source (2) is two to six.
3. the embedded plastic textile quality detection device according to claim 2 based on machine vision, it is characterised in that
The quantity of the video camera (7) is two to six.
4. the embedded plastic textile quality detection device according to claim 3 based on machine vision, it is characterised in that
The video camera (7) is digital camera.
A kind of 5. embedded plastic textile quality detection device based on machine vision using described in claim 1,2,3 or 4
Detection method, it is characterised in that
Step 1: carrying out multi-scale wavelet transformation to textile image, signal and noise are extracted respectively under each yardstick in wavelet field
Wavelet coefficient, eliminate noise wavelet coefficient after, utilize wavelet inverse transformation reconstruct textile image, complete image denoising sound；
Step 2: carrying out Canny rim detections to textile image, Gaussian smoothing first is carried out to image, it is abnormal to eliminate individual gray
Pixel；Then single order local derviation Difference Calculation gradient is utilized, and non-maxima suppression is carried out to gradient magnitude, is positioned in neighborhood
The big pixel of grey scale change；The binaryzation edge image of plastic fabric is finally worth to using dual threashold；
Step 3: extracting linear feature using Hough transformation, extraction result is judged as latitude and longitude being present if meeting given threshold
Running phenomenon.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710946683.3A CN107622490A (en) | 2017-10-12 | 2017-10-12 | Embedded plastic textile quality detection device and detection method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710946683.3A CN107622490A (en) | 2017-10-12 | 2017-10-12 | Embedded plastic textile quality detection device and detection method based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107622490A true CN107622490A (en) | 2018-01-23 |
Family
ID=61091770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710946683.3A Pending CN107622490A (en) | 2017-10-12 | 2017-10-12 | Embedded plastic textile quality detection device and detection method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107622490A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109211937A (en) * | 2018-08-28 | 2019-01-15 | 西安工程大学 | A kind of detection system and its detection method of underwear elastic woven tape curved strip defect |
| CN110111350A (en) * | 2019-04-24 | 2019-08-09 | 桂林航天工业学院 | A kind of welding pool edge detection method, device and storage medium |
| CN110516667A (en) * | 2019-08-15 | 2019-11-29 | 浙江万朋教育科技股份有限公司 | A kind of text rectification method based on Android |
| CN111982774A (en) * | 2020-08-14 | 2020-11-24 | 江西环境工程职业学院 | Garment fabric experiment detection device and using method |
| CN112834383A (en) * | 2020-12-30 | 2021-05-25 | 常州创度信息技术有限公司 | Fabric density detection method based on image analysis |
| CN113222958A (en) * | 2021-05-26 | 2021-08-06 | 浙江网联毛衫汇科技股份有限公司 | Monitoring device and monitoring method for textile fabric |
| CN113588677A (en) * | 2021-07-21 | 2021-11-02 | 安吉八塔机器人有限公司 | Real-time defect detection equipment for mesh bag |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203337567U (en) * | 2013-07-18 | 2013-12-11 | 常州市宏大电气有限公司 | Fabric detection device based on machine vision |
| CN104268505A (en) * | 2014-09-12 | 2015-01-07 | 河海大学常州校区 | Automatic cloth defect point detection and recognition device and method based on machine vision |
| CN104766327A (en) * | 2015-04-15 | 2015-07-08 | 华侨大学 | Fabric deviation detection method and system based on image |
| CN205643191U (en) * | 2016-04-08 | 2016-10-12 | 胡文港 | Fabric quality on -line measuring equipment based on machine vision |
-
2017
- 2017-10-12 CN CN201710946683.3A patent/CN107622490A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN203337567U (en) * | 2013-07-18 | 2013-12-11 | 常州市宏大电气有限公司 | Fabric detection device based on machine vision |
| CN104268505A (en) * | 2014-09-12 | 2015-01-07 | 河海大学常州校区 | Automatic cloth defect point detection and recognition device and method based on machine vision |
| CN104766327A (en) * | 2015-04-15 | 2015-07-08 | 华侨大学 | Fabric deviation detection method and system based on image |
| CN205643191U (en) * | 2016-04-08 | 2016-10-12 | 胡文港 | Fabric quality on -line measuring equipment based on machine vision |
Non-Patent Citations (3)
| Title |
|---|
| 张凤鸣: "《武器装备数据挖掘技术》", 30 September 2017, 国防工业出版社 * |
| 楼少敏: "基于MATLAB的织品缝线疵点检测研究", 《计算机测量与控制》 * |
| 赵谦: "《智能视频图像处理技术与应用》", 30 November 2016, 西安电子科技大学出版社 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109211937A (en) * | 2018-08-28 | 2019-01-15 | 西安工程大学 | A kind of detection system and its detection method of underwear elastic woven tape curved strip defect |
| CN109211937B (en) * | 2018-08-28 | 2021-02-19 | 西安工程大学 | Detection system and detection method for bending defect of elastic braid of underwear |
| CN110111350A (en) * | 2019-04-24 | 2019-08-09 | 桂林航天工业学院 | A kind of welding pool edge detection method, device and storage medium |
| CN110516667A (en) * | 2019-08-15 | 2019-11-29 | 浙江万朋教育科技股份有限公司 | A kind of text rectification method based on Android |
| CN110516667B (en) * | 2019-08-15 | 2021-10-22 | 浙江万朋教育科技股份有限公司 | Character horizontal correction method based on android |
| CN111982774A (en) * | 2020-08-14 | 2020-11-24 | 江西环境工程职业学院 | Garment fabric experiment detection device and using method |
| CN111982774B (en) * | 2020-08-14 | 2024-03-29 | 江西环境工程职业学院 | Garment fabric experimental detection device and use method |
| CN112834383A (en) * | 2020-12-30 | 2021-05-25 | 常州创度信息技术有限公司 | Fabric density detection method based on image analysis |
| CN113222958A (en) * | 2021-05-26 | 2021-08-06 | 浙江网联毛衫汇科技股份有限公司 | Monitoring device and monitoring method for textile fabric |
| CN113588677A (en) * | 2021-07-21 | 2021-11-02 | 安吉八塔机器人有限公司 | Real-time defect detection equipment for mesh bag |
| CN113588677B (en) * | 2021-07-21 | 2024-03-01 | 安吉八塔机器人有限公司 | Real-time defect detection equipment for mesh bag |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107622490A (en) | Embedded plastic textile quality detection device and detection method based on machine vision | |
| CN109685766B (en) | Cloth flaw detection method based on region fusion characteristics | |
| CN102331425B (en) | Textile defect detection method based on defect enhancement | |
| CN103530878B (en) | A kind of edge extracting method based on convergence strategy | |
| CN101852768B (en) | Workpiece flaw identification method based on compound characteristics in magnaflux environment | |
| CN108364291A (en) | Grey cloth rapid detection method based on computer vision technique | |
| CN108051449A (en) | The online visible detection method of Salted duck egg face crack based on morphologic edge detection | |
| Dubey et al. | Maximally stable extremal region marking-based railway track surface defect sensing | |
| CN107132235B (en) | Online fabric defect detection method | |
| CN109190624B (en) | Kitchen oil smoke concentration detection method based on image processing | |
| CN104101600A (en) | Method and apparatus for detecting fine cracks on cross section of continuous casting slab | |
| CN111402215B (en) | Contact net insulator state detection method based on robust principal component analysis method | |
| CN108318491A (en) | A kind of fabric defect detection method based on frequency spectrum curvature analysis | |
| CN104949990A (en) | Online detecting method suitable for defects of woven textiles | |
| CN106841381A (en) | Steel wire rope line flaw detection monitoring system, method and mining multi-rope friction hoist system | |
| CN110097538A (en) | A kind of online cloth examination device of loom and defects identification method | |
| CN106914428A (en) | A kind of New Algorithm of the steel ball surface defect Differential Detection based on machine vision | |
| CN104392441A (en) | Method for detecting and evaluating spray rating of high anti-noise fabric based on image processing | |
| CN111275705A (en) | Intelligent cloth inspecting method and device, electronic equipment and storage medium | |
| CN106408563B (en) | A kind of snow noise detection method based on the coefficient of variation | |
| CN114881960A (en) | Feature enhancement-based cloth linear defect detection method and system | |
| CN112950541A (en) | Synthetic leather gluing online monitoring method based on machine vision | |
| CN115239711A (en) | Online operation abnormity identification system of sewing equipment | |
| CN104392203A (en) | Video-analysis-based point-like stripe noise detection method | |
| CN115330799A (en) | Automatic fault diagnosis method for instrument |
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 |