CN106897997B - The method of detection ring bobbin tail yarn based on Computer Image Processing and pattern-recognition - Google Patents
The method of detection ring bobbin tail yarn based on Computer Image Processing and pattern-recognition Download PDFInfo
- Publication number
- CN106897997B CN106897997B CN201710078985.3A CN201710078985A CN106897997B CN 106897997 B CN106897997 B CN 106897997B CN 201710078985 A CN201710078985 A CN 201710078985A CN 106897997 B CN106897997 B CN 106897997B
- Authority
- CN
- China
- Prior art keywords
- binary map
- spool
- projection
- width
- data
- 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.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20036—Morphological image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
A method of the detection ring bobbin tail yarn based on Computer Image Processing and pattern-recognition, including, acquire spool image pattern, binary map is generated to spool image preprocessing, extracts binary map feature, makes binary map feature database, it is incoming to handle spool image, binary map is generated to spool image preprocessing need to be handled, extraction need to handle binary map feature, judge to handle whether binary map feature meets feature planting modes on sink characteristic.First, the management in modern textile factory by the non-professional practitioner of only a few to several spinning frames in workshop may be implemented in the present invention.It reduces enterprise and employs people's quantity, while improving the efficiency of the process.Second, the Image Acquisition tool that the present invention uses is common camera, low in cost without hardware device is additionally added to system.Third, the method for the present invention can whether there is tail yarn in automatic identification and feedback image, not need manual intervention, using being simple and efficient.
Description
Technical field
The present invention relates to field of image recognition, and in particular to the detection spun yarn based on Computer Image Processing and pattern-recognition
The method of pipe tail yarn.
Background technique
In traditional textile weaving process, the first procedure for spinning Weaving prepartion is winder (also known as doff), and task is
By from spinning portion coil or reeled yarn be processed on bobbin-winding machine and meet necessarily required bobbin.Ring bobbin tail yarn is then that spun yarn is fallen
When yarn, the remaining yarn on ring bobbin.Since ring bobbin needs to reuse after the completion of winder, ring bobbin is being reused
Must assure that before cannot have tail yarn on ring bobbin, it is therefore desirable to be purged to the tail yarn on ring bobbin.Removing tail yarn
The process to be completed before is the sorting to ring bobbin, and ring bobbin and the ring bobbin without tail yarn with tail yarn are separated.
In traditional textile industry, since the tail yarn removal of ring bobbin is all that manually sorting is removed, this makes relevant industry have to
Part manpower is employed to go to complete this procedure.
Computer image recognition technology has been applied in many industries at present, but and textile industry in terms of combination
It studies seldom.This to have to employ manpower to go to carry out spool sorting and the processing of tail yarn in most textile company.So that raw
It produces efficiency to be difficult to be promoted always, causes the bottleneck of Textile Enterprise Information, production automation.If computer technology can be combined
The identification and relevant sorting work that are accomplished manually ring bobbin tail yarn are replaced with digital image processing techniques, this will be effectively
Promote the improved efficiency of textile industry.
Summary of the invention
In view of the deficiencies of the prior art, the present invention proposes a kind of detection based on Computer Image Processing and pattern-recognition is thin
The method of spool tail yarn, specific as follows:
A method of the detection ring bobbin tail yarn based on Computer Image Processing and pattern-recognition, it is characterised in that: S1:
Spool image of the acquisition without containing yarn is as standard spool image pattern;
S2: binary map is generated to the spool image preprocessing;
S3: the binary map is projected in vertical direction, obtains the width data of total upright projection;
S4: the width data of total upright projection is stored in total Database as reference data;
S5: the binary map is uniformly divided at least three sections, three sections of binary maps are respectively perpendicular direction projection, are obtained
First projection width's data, second projection width's data and third projection width data;
S6: respectively using first projection width data, second projection width's data and third projection width data as
Reference data is stored in first database, the second database and third database;
S7: the incoming spool image that need to be handled, and according to S2It is handled;
S8: by S7Obtained in total upright projection width data compared with the reference data in total Database, if always
Upright projection data are greater than the reference data in total Database, then are judged as containing yarn, otherwise enter S9;
S9: the spool that need to be handled uniformly is divided at least three sections, which corresponds to S6In database,
And three sections of binary maps are respectively perpendicular direction projection, respectively obtain three sections of new binary map upright projection width datas;
S10: by three sections of new binary map upright projection data respectively with corresponding first database, the second database
It is compared with third database, in three sections of new binary map upright projection data, the upright projection of either segment binary map is wide
Degree is then judged as containing yarn, is otherwise judged as without yarn according to the reference data for being greater than correspondence database.
Further: the S2Including,
S21: gray processing and binary conversion treatment are carried out to the spool image, obtain bianry image;
S22: to the bianry image noise reduction process;
S23: determine position of the spool in binary map;
S24: the spool position in the bianry image is corrected, so that spool axial direction and the binary map bottom
Side is vertical.
Further: the S24Including,
S241: it the spool is rotated clockwise 1 degree in binary map, obtains the 4th upright projection, will then not rotate
The spool rotates 1 degree counterclockwise in binary map, obtains the 5th upright projection.
S242If: the width of the 4th upright projection is greater than the width of the 5th upright projection, judges the spool in two-value
It is biased as right avertence in figure, it is counterclockwise for setting correction rotation direction, if the width of the 4th upright projection is less than the 5th upright projection
Width, then judge that the spool is biased as left avertence in binary map, set correction rotation direction be clockwise.
S243: by being rotation angularly correction rotation direction deflection with 1 degree, while carrying out horizontal direction projection and vertical direction throwing
Shadow is determined as the yarn when upright projection width minimum of the spool in binary map, while when floor projection width maximum
Pipe axis is in binary map perpendicular to binary map bottom edge.
Further: being using the Glycerine enema and closure operation in mathematical morphology to the bianry image noise reduction process
Processing.
The invention has the benefit that first, the present invention may be implemented non-professional by only a few in modern textile factory
Management of the practitioner to several spinning frames in workshop.It reduces enterprise and employs people's quantity, while improving the efficiency of the process.Second,
The Image Acquisition tool that the present invention uses is common camera, low in cost without hardware device is additionally added to system.The
Three, the method for the present invention can whether there is tail yarn in automatic identification and feedback image, not need manual intervention, using being simple and efficient.
Detailed description of the invention
Fig. 1 is flow chart of the invention.
Specific embodiment
The preferred embodiments of the present invention will be described in detail with reference to the accompanying drawing, so that advantages and features of the invention energy
It is easier to be readily appreciated by one skilled in the art, so as to make a clearer definition of the protection scope of the present invention.
A kind of method of the detection ring bobbin tail yarn based on Computer Image Processing and pattern-recognition as shown in Figure 1:, packet
It includes:
S1: the spool image of yarn is not contained by camera acquisition, uploads to PC machine as standard spool image pattern;
S2: binary map is generated to spool image preprocessing, utilizes formula
Wherein, f (x, y) is the pixel value in original image, and the pixel value of g (x, y) is that treated black white image, T is ash
Spend threshold value.The principle of function is, if the grey scale pixel value of image is greater than threshold value, to be set as 255, what is be less than is set as 0.
S3: binary map is projected in vertical direction, obtains the width data of total upright projection;
S4: the width data of total upright projection is stored in total Database as reference data;
S5: binary map is uniformly divided at least three sections, three sections of binary maps are respectively perpendicular direction projection, obtain the first projection
Width data, second projection width's data and third projection width data can more accurately go to determine whether deposit on ring bobbin
In yarn, while which section that yarn is particularly located in spool can also be determined.
S6: respectively using first projection width's data, second projection width's data and third projection width data as benchmark
Data are stored in first database, the second database and third database;
S7: the incoming spool image that need to be handled, and according to S2It is handled;
S8: by S7Obtained in total upright projection width data compared with the reference data in total Database, if always
Upright projection data are greater than the reference data in total Database, then are judged as containing yarn, otherwise enter S9;
S9: the spool that need to be handled uniformly is divided at least three sections, which corresponds to S6In database number,
And three sections of binary maps are respectively perpendicular direction projection, respectively obtain three sections of new binary map upright projection width datas;
S10: by three sections of new binary map upright projection data respectively with corresponding first database, the second database and
Three databases compare, in three sections of new binary map upright projection data, the upright projection width number of either segment binary map
According to the reference data for being greater than correspondence database, then it is judged as containing yarn, is otherwise judged as without yarn.
Above-mentioned S2In include step,
S21: gray processing and binary conversion treatment are carried out to spool image, obtain bianry image;
S22: using in mathematical morphology Glycerine enema and closure operation handle to bianry image noise reduction process;
S23: determine position of the spool in binary map;
S24: the spool position in bianry image is corrected, so that spool axial direction and binary map base vertical.
Above-mentioned S24Including step,
S241: spool is rotated clockwise to 1 degree in binary map, obtains the 4th upright projection, the spool that will then not rotate
It rotates 1 degree counterclockwise in binary map, obtains the 5th upright projection.
S242If: the width of the 4th upright projection is greater than the width of the 5th upright projection, judges spool in binary map
Be biased as right avertence, set correction rotation direction be counterclockwise, if the width of the 4th upright projection is less than the width of the 5th upright projection
Degree, then judge that spool is biased as left avertence in binary map, and it is clockwise for setting correction rotation direction.
S243: by being rotation angularly correction rotation direction deflection with 1 degree, while carrying out horizontal direction projection and vertical direction throwing
Shadow is determined as that spool axis exists when upright projection width minimum of the spool in binary map, while when floor projection width maximum
Perpendicular to binary map bottom edge in binary map.
Claims (4)
1. a kind of method of the detection ring bobbin tail yarn based on Computer Image Processing and pattern-recognition, it is characterised in that: S1: it adopts
Spool image of the collection without containing yarn is as standard spool image pattern;
S2: binary map is generated to the spool image preprocessing;
S3: the binary map is projected in vertical direction, obtains the width data of total upright projection;
S4: the width data of total upright projection is stored in total Database as reference data;
S5: the binary map is uniformly divided at least three sections, three sections of binary maps are respectively perpendicular direction projection, obtain first
Projection width's data, second projection width's data and third projection width data;
S6: respectively using first projection width data, second projection width's data and third projection width data as base value
According to being stored in first database, the second database and third database;
S7: the incoming spool image that need to be handled, and according to S2It is handled;
S8: by S7Obtained in total upright projection width data compared with the reference data in total Database, if it is total vertically
Data for projection is greater than the reference data in total Database, then is judged as containing yarn, otherwise enters S9;
S9: the spool that need to be handled uniformly is divided at least three sections, which corresponds to S6In database, and will
Three sections of binary maps are respectively perpendicular direction projection, respectively obtain three sections of new binary map upright projection width datas;
S10: by three sections of new binary map upright projection data respectively with corresponding first database, the second database and the
Three databases compare, in three sections of new binary map upright projection data, the upright projection width number of either segment binary map
According to the reference data for being greater than correspondence database, then it is judged as containing yarn, is otherwise judged as without yarn.
2. the method for the detection ring bobbin tail yarn according to claim 1 based on Computer Image Processing and pattern-recognition,
It is characterized in that: the S2Including,
S21: gray processing and binary conversion treatment are carried out to the spool image, obtain bianry image;
S22: to the bianry image noise reduction process;
S23: determine position of the spool in binary map;
S24: the spool position in the bianry image is corrected, is hung down so that the spool is axial with the binary map bottom edge
Directly.
3. the method for the detection ring bobbin tail yarn according to claim 2 based on Computer Image Processing and pattern-recognition,
It is characterized in that: the S24Including,
S241: the spool is rotated clockwise 1 degree in binary map, obtains the 4th upright projection, will then not rotate described in
Spool rotates 1 degree counterclockwise in binary map, obtains the 5th upright projection;
S242If: the width of the 4th upright projection is greater than the width of the 5th upright projection, judges the spool in binary map
Be biased as right avertence, set correction rotation direction be counterclockwise, if the width of the 4th upright projection is less than the width of the 5th upright projection
Degree, then judge that the spool is biased as left avertence in binary map, and it is clockwise for setting correction rotation direction;
S243: by being the angular correction rotation direction deflection of rotation with 1 degree, while horizontal direction projection and vertical direction projection are carried out, when
Upright projection width of the spool in binary map is minimum, while when floor projection width maximum, being determined as the yarn tube axis
Line is in binary map perpendicular to binary map bottom edge.
4. the method for the detection ring bobbin tail yarn based on Computer Image Processing and pattern-recognition described in claim 2, feature
It is: is Glycerine enema and the closure operation processing used in mathematical morphology to the bianry image noise reduction process.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710078985.3A CN106897997B (en) | 2017-02-14 | 2017-02-14 | The method of detection ring bobbin tail yarn based on Computer Image Processing and pattern-recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710078985.3A CN106897997B (en) | 2017-02-14 | 2017-02-14 | The method of detection ring bobbin tail yarn based on Computer Image Processing and pattern-recognition |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106897997A CN106897997A (en) | 2017-06-27 |
CN106897997B true CN106897997B (en) | 2019-12-03 |
Family
ID=59198459
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710078985.3A Expired - Fee Related CN106897997B (en) | 2017-02-14 | 2017-02-14 | The method of detection ring bobbin tail yarn based on Computer Image Processing and pattern-recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106897997B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108038858A (en) * | 2017-12-26 | 2018-05-15 | 青岛大学 | The recognition methods of amount of thread on yarn tube in field of textiles NI Vision Builder for Automated Inspection |
CN110956656A (en) * | 2019-12-17 | 2020-04-03 | 北京工业大学 | Spindle positioning method based on depth target detection |
CN111020766B (en) * | 2019-12-19 | 2020-11-10 | 夏津仁和纺织科技有限公司 | Spinning frame backward spindle searching method based on industrial camera image acquisition |
CN113920086B (en) * | 2021-10-09 | 2024-04-05 | 云路复合材料(上海)有限公司 | Yarn state detection method and device in carbon fiber weaving process |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103471974A (en) * | 2013-09-05 | 2013-12-25 | 东华大学 | Method for determining theoretic porosity of fabric through image method |
CN105386175A (en) * | 2015-12-03 | 2016-03-09 | 江南大学 | Online detection device and detection method of rough yarn uniformity of roving machine |
-
2017
- 2017-02-14 CN CN201710078985.3A patent/CN106897997B/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103471974A (en) * | 2013-09-05 | 2013-12-25 | 东华大学 | Method for determining theoretic porosity of fabric through image method |
CN105386175A (en) * | 2015-12-03 | 2016-03-09 | 江南大学 | Online detection device and detection method of rough yarn uniformity of roving machine |
Non-Patent Citations (2)
Title |
---|
基于视觉传感的纱线检测系统和研究与实现;沈凌飞;《中国优秀硕士学位论文全文数据库(信息科技辑)》;20131215;全文 * |
数学图像处理技术在纺织测试分析中的应用;李艳梅等;《上海工程技术大学学报》;20050630;第19卷(第2期);第41-44页 * |
Also Published As
Publication number | Publication date |
---|---|
CN106897997A (en) | 2017-06-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106897997B (en) | The method of detection ring bobbin tail yarn based on Computer Image Processing and pattern-recognition | |
CN113658133B (en) | Gear surface defect detection method and system based on image processing | |
CN1162803C (en) | Bill distinguishing device and method and recording medium for recording the method | |
CN109190623B (en) | Method for identifying brand and model of projector | |
CN111127429A (en) | Water conservancy system pipe thread defect detection method based on self-training deep neural network | |
CN111079803B (en) | Template matching method based on gradient information | |
CN111754422A (en) | Visual edge inspection method based on EDLines and LSM | |
WO2021135675A1 (en) | Automatic bar counting method and apparatus | |
CN109540917B (en) | Method for extracting and analyzing yarn appearance characteristic parameters in multi-angle mode | |
CN111680681B (en) | Image post-processing method and system for eliminating abnormal recognition target and counting method | |
CN107766854B (en) | Method for realizing rapid page number identification based on template matching | |
CN110490185A (en) | One kind identifying improved method based on repeatedly comparison correction OCR card information | |
CN112330598A (en) | Method and device for detecting stiff silk defects on chemical fiber surface and storage medium | |
CN103295009A (en) | License plate character recognition method based on stroke decomposition | |
CN109544513A (en) | A kind of steel pipe end surface defect extraction knowledge method for distinguishing | |
CN109977910B (en) | Rapid bill positioning method and system based on color line segments | |
CN106650735B (en) | A kind of LED character automatic positioning recognition methods | |
CN113642570A (en) | Method for recognizing license plate of mine car in dark environment | |
CN104809460B (en) | Germ nucleus position drawing generating method and transistor pixel search table generating method | |
CN116129187A (en) | Quick target detection method and system based on local stable characteristic points | |
CN110349150A (en) | A kind of product defects recognition methods | |
CN116310294A (en) | Subway train bolt loosening detection method and device | |
CN109461150B (en) | Yarn tube color sorting method based on machine vision | |
CN114155313A (en) | Rapid graph automatic drawing method based on image recognition | |
CN112489015A (en) | Chemical fiber impurity floating identification method for mobile robot |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191203 Termination date: 20210214 |