CN104198496A - Automatic cotton defect detection device - Google Patents
Automatic cotton defect detection device Download PDFInfo
- Publication number
- CN104198496A CN104198496A CN201410449254.1A CN201410449254A CN104198496A CN 104198496 A CN104198496 A CN 104198496A CN 201410449254 A CN201410449254 A CN 201410449254A CN 104198496 A CN104198496 A CN 104198496A
- Authority
- CN
- China
- Prior art keywords
- cotton
- image
- images
- fault
- camera
- 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
Landscapes
- Treatment Of Fiber Materials (AREA)
Abstract
The invention discloses an automatic cotton defect detection device which comprises a detection box, wherein an LED front lighting lamp is arranged at the top of the detection box; a camera is arranged at the bottom of the detection box; a piece of frosted glass which is fixed on the detection box is arranged below the LED front lighting lamp; a transparent sample box which is used for placing cotton samples is arranged between the frosted glass and the camera; the camera is connected with a computer image processing system; the computer image processing system is used for respectively capturing the background images and the transmission light images of the cotton samples, carrying out difference processing to obtain difference images, carrying out filtration on the mid-value of the difference images to obtain filtered images, carrying out binary division on the filtered images to primarily divide the cotton defects from the background, carrying out full scan on the divided images to ensure that the areas of the cotton defects in the images are labeled by using a seed filling algorithm, recording the pixel points of the filling and comparing with a set limiting value to obtain the number of the defects in the cotton samples; and the detection process is automatically finished, so that the detection efficiency and the detection correctness are improved.
Description
Technical field
The present invention relates to cotton detection field, specifically the fault automatic detection device that grows cotton.
Background technology
Known, in field of textiles, the Ginning Quality of cotton is one of quality index of wanting of heavy cotton, because Developmental of Cotton is bad and roll the bad reason of work, can form the cotton fault that spinning is had to harm; At present the detection of cotton fault is generally adopted to manual method, the cotton national standard GB1103.1-2012 implementing for 2013 has increased GB/T6103 < < raw cotton fault test method manual method > > specially, using Ginning Quality as a quality index independently, and set up Ginning Quality material standard, stipulated the method for inspection; But because the many sizes of defect level in a lot of cottons are little, naked eyes detect easily tired, work poor continuity, inefficiency, and also the consistance of different people detection results is bad, poor accuracy.
Summary of the invention
The object of the present invention is to provide the fault automatic detection device that grows cotton, this device can detect the fault in cotton automatically, improves the accuracy of detection efficiency and detection.
The technical solution adopted for the present invention to solve the technical problems is:
The one fault automatic detection device that grows cotton, comprise detection case, the top of detection case is provided with LED face light modulation, and the bottom of detection case is provided with camera, LED face light modulation below is provided with the frosted glass that is fixed on detection case, is provided with for placing the transparent sample box of cotton sample between frosted glass and camera; Detection case is provided with the Computerized image processing system being connected with camera outward, Computerized image processing system gathers respectively the transmitted light images of background image and cotton sample, and do difference and process and to obtain error image, by the medium filtering to error image, process and obtain filtering image, filtered image is carried out to binary segmentation cotton fault and background are tentatively cut apart; Image after cutting apart is carried out to full scan, use seed fill algorithm that the region of the cotton fault in image is marked; Record the pixel of filling simultaneously, by the mark limit value with setting, obtain more afterwards the number of fault in cotton sample.
Further, in described transparent sample box, be also provided with for compressing the glass plate of cotton sample.
Further, described detection case is also provided with the adjustable stabilized voltage supply being connected with LED face light modulation outward.
The invention has the beneficial effects as follows, setting can be obtained the detection case of cotton sample transmitted light images, and by the Computerized image processing system being connected with camera, transmitted light images is carried out to Treatment Analysis, obtain the fault number in cotton sample, testing process completes automatically, give up traditional manual detection method, improved the efficiency of detection and the accuracy of detection.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the present invention is further described:
Fig. 1 is structural representation of the present invention;
Fig. 2 be in Fig. 1 cotton sample box just analyse and observe enlarged diagram.
Embodiment
As shown in Figure 1, the provided by the invention one fault automatic detection device that grows cotton, comprise detection case 1, the top of detection case 1 is provided with LED face light modulation 2, the bottom of detection case 1 is provided with camera 4, the below of LED face light modulation 2 is provided with the frosted glass 3 that is fixed on detection case 1, is provided with for placing the transparent sample box 5 of cotton sample between frosted glass 3 and camera 4; The sidewall of detection case 1 is provided with notch, and transparent sample box 5 inserts in detection case 1 by notch, and 6 pairs of transparent sample boxes 5 of back-up block of being located at detection case 1 sidewall support, and camera 4 is connected with the Computerized image processing system 7 outside detection case; Computerized image processing system 7 adopts general computing machine, sets image pick-up card the image of camera 4 shootings is gathered in computing machine, and camera 4 can adopt the adjustable Basler A101 of focal length; The outer adjustable stabilized voltage supply 11 being connected with LED face light modulation 2 that is also provided with of detection case 1; Shown in Fig. 2, the bottom of transparent sample box 5 is lower glass plate 8.
During use, first open LED face light modulation 2, see through frosted glass 3 and produce uniform light visual field, Computerized image processing system 7 gathers background image; In order to obtain more uniform light visual field, need to light source, adjust in conjunction with the time shutter of camera 4, by regulating adjustable stabilized voltage supply 11, can regulate the brightness of LED face light modulation 2; For background image, detect the gray-scale value of each pixel, change the time shutter of camera simultaneously, until in background image the gray-scale value of all pixels all between 220～255.It is noted that can not make the gray-scale value of all pixels is all 255, because the heterogeneity of light field, when the gray-scale value of all pixels is all 255, the gray scale of inevitable some pixel is oversaturated, causes the brightness of image and departing from of true brightness.From experimental result, when having 5% grey scale pixel value to reach 255, can think that exposure reaches capacity, in this case, 95% grey scale pixel value has all reached more than 230, and the time shutter of writing down is now τ
0, in follow-up work, no longer needing to adjust light source, after each starter gear, the preheated one-section time, light source works is stable, and the image without test samples obtaining is background image.
Then cotton sample 10 is placed in lower glass plate 8, can uses the roller Y111 that cotton industry is conventional to prepare thin web as cotton style 10, upper glass plates 9 is put into transparent sample box 5, compress cotton sample 10 for strengthening image effect, afterwards transparent sample box 5 is inserted in detection case 1, Computerized image processing system 7 gathers the transmitted light images of cotton sample, because the transmittance of cotton fault is lower, therefore the relative background luminance of cotton fault is lower, is rendered as dim spot, in order to obtain the good transmitted light images of quality, need to determine the optimum exposure time τ that takes transmitted light images, in actual applications, can the dynamic adjustments time shutter and observe transmitted light images, make as far as possible the fault region of transmitted light images and the contrast in non-fault region larger, and make as far as possible the overall brightness of transmitted light images higher, in the region that there is no fault, its brightness approaches the brightness of background image corresponding region as far as possible, write down this time shutter τ, this time shutter is all used in acquisition of transmission light image later, because the thin web otherness of using roller Y111 to prepare is little, so not changing time shutter τ can ignore on the impact of difference test web picture quality.The transmitted light images that deducts cotton sample with background image obtains error image, processes the inhomogeneous information of light field in image obtained very large elimination by difference; With median filter, error image is carried out to filtering, obtain filtering image; Use adaptive threshold dividing method to carry out binary segmentation to filtered image, cotton fault and background are tentatively cut apart, now background pixel value is set to 0, and the pixel value of fault image is set to 1; From left to right, scan the image after binary segmentation from top to bottom, carry out full scan, whenever scanning fault, be that pixel value is 1 point, just with seed fill algorithm, fill fault region, until fault area filling is complete, meanwhile write down the number of pixels of filling, it and the mark limit value of predefined expression fault are compared, if be greater than mark limit value, show to have found a fault, complete the scanning filling to image after whole binary segmentation, can obtain the fault number in cotton sample.
The above, be only preferred embodiment of the present invention, not the present invention done to any pro forma restriction; Any those of ordinary skill in the art, do not departing from technical solution of the present invention scope situation, all can utilize method and the technology contents of above-mentioned announcement to make many possible changes and modification to technical solution of the present invention, or be revised as the equivalent embodiment of equivalent variations.Therefore, every content that does not depart from technical solution of the present invention, according to technical spirit of the present invention to any simple modification made for any of the above embodiments, be equal to replacements, equivalence changes and modify, all still belong in the scope that technical solution of the present invention protects.
Claims (3)
1. the fault automatic detection device that grows cotton, it is characterized in that, described pick-up unit comprises detection case (1), the top of detection case (1) is provided with LED face light modulation (2), the bottom of detection case (1) is provided with camera (4), LED face light modulation (2) below is provided with the frosted glass (3) that is fixed on detection case, is provided with for placing the transparent sample box (5) of cotton sample (10) between frosted glass (3) and camera (4); The outer Computerized image processing system (7) being connected with camera (4) that is provided with of detection case (1), Computerized image processing system (7) gathers respectively the transmitted light images of background image and cotton sample, and do difference and process and to obtain error image, by the medium filtering to error image, process and obtain filtering image, filtered image is carried out to binary segmentation cotton fault and background are tentatively cut apart; Image after cutting apart is carried out to full scan, use seed fill algorithm that the region of the cotton fault in image is marked; Record the pixel of filling simultaneously, by the mark limit value with setting, obtain more afterwards the number of fault in cotton sample.
2. the according to claim 1 one fault automatic detection device that grows cotton, is characterized in that, in described transparent sample box, is also provided with for compressing the glass plate of cotton sample.
3. the according to claim 1 and 2 one fault automatic detection device that grows cotton, is characterized in that, the outer adjustable stabilized voltage supply (11) being connected with LED face light modulation (2) that is also provided with of described detection case (1).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410449254.1A CN104198496A (en) | 2014-09-04 | 2014-09-04 | Automatic cotton defect detection device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410449254.1A CN104198496A (en) | 2014-09-04 | 2014-09-04 | Automatic cotton defect detection device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104198496A true CN104198496A (en) | 2014-12-10 |
Family
ID=52083821
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410449254.1A Pending CN104198496A (en) | 2014-09-04 | 2014-09-04 | Automatic cotton defect detection device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104198496A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107621468A (en) * | 2017-10-19 | 2018-01-23 | 河南省纤维检验局 | A kind of quality of roll for cotton rapid classification system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5345515A (en) * | 1990-05-28 | 1994-09-06 | Kanebo Ltd. | Method and apparatus for inspecting the cleanliness of top slibers |
| US20010006220A1 (en) * | 1999-09-09 | 2001-07-05 | Fritz Hosel | Method and apparatus for examining fiber material travelling in a fiber processing machine |
| CN101398392A (en) * | 2007-09-26 | 2009-04-01 | 中国科学院自动化研究所 | Cotton impurity high speed real-time detection method based on HSI color space |
| CN101510262A (en) * | 2009-03-17 | 2009-08-19 | 江苏大学 | Automatic measurement method for separated-out particles in steel and morphology classification method thereof |
| CN201859123U (en) * | 2010-06-25 | 2011-06-08 | 南通棉花机械有限公司 | Detection and removal equipment for transparent plastic impurities in seed cotton |
| US8199319B2 (en) * | 2009-06-29 | 2012-06-12 | Uster Technologies Ag | Fiber property measurement |
| CN102680481A (en) * | 2012-05-16 | 2012-09-19 | 陕西长岭纺织机电科技有限公司 | Detection method for cotton fiber impurities |
| CN102914545A (en) * | 2012-11-15 | 2013-02-06 | 潍坊学院 | Gear defect detection method and system based on computer vision |
| CN103698341A (en) * | 2013-12-31 | 2014-04-02 | 中华全国供销合作总社郑州棉麻工程技术设计研究所 | System for detecting cotton rolling quality and method for detecting cotton rolling quality based on image |
| CN203732457U (en) * | 2013-12-31 | 2014-07-23 | 中华全国供销合作总社郑州棉麻工程技术设计研究所 | Cotton rolling quality image acquisition and display system |
-
2014
- 2014-09-04 CN CN201410449254.1A patent/CN104198496A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5345515A (en) * | 1990-05-28 | 1994-09-06 | Kanebo Ltd. | Method and apparatus for inspecting the cleanliness of top slibers |
| US20010006220A1 (en) * | 1999-09-09 | 2001-07-05 | Fritz Hosel | Method and apparatus for examining fiber material travelling in a fiber processing machine |
| CN101398392A (en) * | 2007-09-26 | 2009-04-01 | 中国科学院自动化研究所 | Cotton impurity high speed real-time detection method based on HSI color space |
| CN101510262A (en) * | 2009-03-17 | 2009-08-19 | 江苏大学 | Automatic measurement method for separated-out particles in steel and morphology classification method thereof |
| US8199319B2 (en) * | 2009-06-29 | 2012-06-12 | Uster Technologies Ag | Fiber property measurement |
| CN201859123U (en) * | 2010-06-25 | 2011-06-08 | 南通棉花机械有限公司 | Detection and removal equipment for transparent plastic impurities in seed cotton |
| CN102680481A (en) * | 2012-05-16 | 2012-09-19 | 陕西长岭纺织机电科技有限公司 | Detection method for cotton fiber impurities |
| CN102914545A (en) * | 2012-11-15 | 2013-02-06 | 潍坊学院 | Gear defect detection method and system based on computer vision |
| CN103698341A (en) * | 2013-12-31 | 2014-04-02 | 中华全国供销合作总社郑州棉麻工程技术设计研究所 | System for detecting cotton rolling quality and method for detecting cotton rolling quality based on image |
| CN203732457U (en) * | 2013-12-31 | 2014-07-23 | 中华全国供销合作总社郑州棉麻工程技术设计研究所 | Cotton rolling quality image acquisition and display system |
Non-Patent Citations (4)
| Title |
|---|
| R.A.TAYLOR: "用视频扫杂质分析仪测定棉花杂质", 《中国纤检》 * |
| 李碧丹等: "皮棉异性纤维剔除系统设计", 《农业机械学报》 * |
| 赵传文: "基于图像处理技术的棉花加工环节异性纤维在线检测装置的应用研究", 《科技信息》 * |
| 郏东耀等: "检测皮棉内部杂志的透射成像影响因素分析", 《农业机械学报》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107621468A (en) * | 2017-10-19 | 2018-01-23 | 河南省纤维检验局 | A kind of quality of roll for cotton rapid classification system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102735695B (en) | Rapid lens flaw detection method and apparatus thereof | |
| CN103196554B (en) | System and method for testing and adjusting light intensity uniformity of light source | |
| CN104118609B (en) | Labeling quality determining method and device | |
| CN103698341B (en) | A kind of quality of roll for cotton detection system and quality of roll for cotton image detecting method | |
| CN109507192A (en) | A kind of magnetic core detection method of surface flaw based on machine vision | |
| CN109727233B (en) | LCD defect detection method | |
| CN104034638B (en) | The diamond wire online quality detecting method of granule based on machine vision | |
| CN103473778A (en) | Detecting algorithm for eccentrically-inserting defect of LED luminous chip | |
| CN104809725A (en) | Cloth defect visual identify detecting device and method | |
| CN104568989A (en) | Glass substrate defect detecting method | |
| CN105606629A (en) | Automatic detection device and method of lens facet defects | |
| CN103645573A (en) | Liquid crystal display (LCD) detection method and system based on machine vision | |
| CN101074915A (en) | Device, method and program for detecting impurities in a fluid | |
| CN104792794A (en) | Machine vision based optical film surface defect detecting method | |
| CN102323272A (en) | Filter paper defect detecting system and detection method thereof based on machine vision technique | |
| CN204789357U (en) | Electrolytic capacitor outward appearance packing defect image detection system | |
| CN109900723A (en) | Glass surface defects detection method and device | |
| CN103743757A (en) | Device and method for detecting foreign matters on inner wall of glass bottle | |
| CN111179362B (en) | Test paper color uniformity detection method based on dynamic illumination correction algorithm | |
| CN107664644A (en) | A kind of apparent automatic detection device of object based on machine vision and method | |
| CN109509173A (en) | A kind of method of counting and counting device of bacterial clump | |
| CN104048966B (en) | The detection of a kind of fabric defect based on big law and sorting technique | |
| CN108037142A (en) | Mask plate optical defect detection method based on image intensity value | |
| CN104034637A (en) | Diamond wire particle online quality inspection device based on machine vision | |
| CN113628161A (en) | Defect detection method, defect detection device and computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141210 |
|
| RJ01 | Rejection of invention patent application after publication |