CN111088597A - Contour line analysis-based yarn state detection method - Google Patents
Contour line analysis-based yarn state detection method Download PDFInfo
- Publication number
- CN111088597A CN111088597A CN201911333961.3A CN201911333961A CN111088597A CN 111088597 A CN111088597 A CN 111088597A CN 201911333961 A CN201911333961 A CN 201911333961A CN 111088597 A CN111088597 A CN 111088597A
- Authority
- CN
- China
- Prior art keywords
- yarn
- image sensor
- contour line
- processor
- emission unit
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 21
- 230000003068 static effect Effects 0.000 claims abstract description 7
- 230000033001 locomotion Effects 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 15
- 230000000052 comparative effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 239000004753 textile Substances 0.000 description 1
Images
Classifications
-
- D—TEXTILES; PAPER
- D04—BRAIDING; LACE-MAKING; KNITTING; TRIMMINGS; NON-WOVEN FABRICS
- D04B—KNITTING
- D04B35/00—Details of, or auxiliary devices incorporated in, knitting machines, not otherwise provided for
- D04B35/10—Indicating, warning, or safety devices, e.g. stop motions
-
- D—TEXTILES; PAPER
- D04—BRAIDING; LACE-MAKING; KNITTING; TRIMMINGS; NON-WOVEN FABRICS
- D04B—KNITTING
- D04B35/00—Details of, or auxiliary devices incorporated in, knitting machines, not otherwise provided for
- D04B35/10—Indicating, warning, or safety devices, e.g. stop motions
- D04B35/14—Indicating, warning, or safety devices, e.g. stop motions responsive to thread breakage
Landscapes
- Engineering & Computer Science (AREA)
- Textile Engineering (AREA)
- Treatment Of Fiber Materials (AREA)
- Spinning Or Twisting Of Yarns (AREA)
Abstract
The invention discloses a yarn state detection method based on contour line analysis, which is provided with a U-shaped shell and an electronic control device arranged in the shell, and comprises a power circuit for providing a power supply, a processor for performing operation processing, an infrared emission unit and an image sensor, wherein the infrared emission unit and the image sensor are connected with the processor, an infrared filter is arranged on the image sensor, the infrared emission unit is arranged right above the image sensor, and the yarn state detection method is arranged in the processor and comprises the following steps: (1) the processor collects the image data output by the image sensorf t(x, y); (2) adopting a binarization algorithm to image dataf t(x, y) is subjected to binarization treatment to obtainy t(x, y); (3) extracting a binary functiony tContour line y' of (x, y)t(x, y); (4) extracting the contour line y ″tNumerical descriptor R of (x, y)t(ii) a (5) Comparative numerical descriptor RtAnd Rt‑1: when Rt‑Rt‑1If the | is greater than or equal to a preset threshold value K, judging that the yarn is in a motion state; otherwise, the yarn is judged to be in a static state.
Description
Technical Field
The invention relates to a contour line analysis-based yarn state detection method, and belongs to the technical field of textile electronics.
Background
The fully-automatic seamless underwear machine and the automatic sock machine can completely weave one sock without the participation of people. The lack of human and high efficiency can lead to increased production and reduced costs, but if a set of yarns is broken or missing, if not discovered in time, the entire garment is scrapped. Therefore, yarn condition detection is indispensable to seamless underwear machines and hosiery machines. The currently used yarn state sensor uses a differential infrared photodiode to detect. The mode has the advantages of simple principle and low cost, but the gain of the amplifying circuit is very large and is easy to be interfered, and the detection area is very narrow and has high installation requirements. With the development of computer vision, not only the costs of imaging devices and image processing devices are greatly reduced, but also image processing techniques are fully developed, making it possible to analyze the state of the yarn based on the complete image morphology.
Disclosure of Invention
The invention aims to overcome the defects in the prior art, adopts the detection mode of an image sensor, provides a yarn state detection method based on contour line analysis, carries out contour line contrast analysis on two sampled images of the front and the back of a yarn, and is a non-contact detection scheme with simple principle and reliable work.
The technical scheme adopted by the invention for solving the technical problems is as follows:
the yarn state detection method based on contour line analysis is characterized by comprising a U-shaped shell and an electronic control device arranged in the shell, wherein the electronic control device comprises a power circuit for providing a power supply, a processor for performing operation processing, an infrared emission unit and an image sensor, the infrared emission unit and the image sensor are connected with the processor, an infrared filter is arranged on the image sensor, the infrared emission unit is arranged right above the image sensor, yarns penetrate through the lower part of the infrared emission unit and are projected onto the image sensor, a yarn state detection method is arranged in the processor, the yarn state detection method can detect a static state or a moving state under the slight movement state of the yarns, and the yarn state detection method comprises the following steps:
(1) every fixed period T, the processor collects the image data output by the image sensorf t(x, y), x = 1-M, y = 1-N, wherein M is the maximum pixel number in the x-axis direction, and N is the maximum pixel number in the y-axis direction;
(2) adopting binary algorithm to make the described image dataf t(x, y) performing binarization processing to obtain a binary functiony t(x, y), and the projected area of the yarny t(x, y) =1, non-projection areay t(x,y)=0；
(3) Extracting a binary functiony tContour line y' of (x, y)t(x,y)；
(4) Extracting the contour line y ″tNumerical descriptor R of (x, y)t；
(5) Comparing the currently acquired numerical descriptors RtWith the value descriptor R of the previous acquisitiont-1: when Rt-Rt-1If the | is greater than or equal to a preset threshold value K, judging that the yarn is in a motion state; when Rt-Rt-1And if the | is smaller than a preset threshold value K, judging that the yarn is in a static state.
In the step (3), a binary function is extractedy tContour line y' of (x, y)tThe method of (x, y) is: when in usey t(x,y)-y t(x-1, y) =1, y ″t(x, y) = 1; otherwise, y ″t(x,y)=0，x=2~M。
In the step (3), a binary function is extractedy tContour line y' of (x, y)tThe method of (x, y) is: when in usey t(x,y)-y t(x +1, y) =1, y ″t(x, y) = 1; otherwise, y ″t(x,y)=0，x=1~M-1。
In the step (4), the contour line y' is extractedtNumerical descriptor R of (x, y)tThe method comprises the following steps: rt=
。
The implementation of the invention has the positive effects that: 1. performing contour line contrast analysis on the front and rear sampled images of the yarn by adopting a detection mode of an image sensor, and judging the micro-motion state of the yarn; 2. the principle is simple, and the work is reliable; 3. and the non-contact detection has no influence on the yarn.
Drawings
Fig. 1 is an installation diagram of an electronic control device;
FIG. 2 is a schematic diagram of a binary function;
fig. 3 is a schematic diagram of the contour lines.
Detailed Description
The invention will now be further described with reference to the accompanying drawings in which:
referring to fig. 1-3, the yarn state detection method based on contour line analysis comprises a U-shaped shell and an electronic control device arranged in the shell, wherein the electronic control device comprises a power circuit for providing power, a processor for performing operation processing, an infrared emission unit 1 and an image sensor 2 which are connected with the processor, and an infrared filter 3 is arranged on the image sensor 2.
The power supply circuit performs level conversion on an input power supply, stabilizes voltage and provides power for other circuits.
The image sensor 2 is configured as a CCD linear image sensor or a CMOS linear image sensor sensitive to infrared rays, and the processor can read image data as needed.
The yarn state detection method is arranged in the processor, can detect a static state or a moving state under a slight yarn moving state, and comprises the following steps:
(1) every fixed period T, the processor collects the image data output by the image sensorf t(x, y), x = 1-M, y = 1-N, wherein M is the maximum pixel number in the x-axis direction, and N is the maximum pixel number in the y-axis direction;
in step (1), the processor 1 samples every fixed period T to obtain an image sequence of a two-dimensional matrixf t(x,y)，f t-1(x,y)，f t-2(x,y)，．．．．．．
(2) Adopting binary algorithm to make the described image dataf t(x, y) performing binarization processing to obtain a binary functiony t(x, y), and the projected area of the yarny t(x, y) =1, non-projection areay t(x,y)=0；
In step (2), empirical data is used as a segmentation threshold iff t(x, y) is greater than or equal to the segmentation threshold, theny t(x, y) =0, here a non-projected area of the yarn; if it is notf t(x, y) is less than the segmentation threshold, theny t(x, y) =1, here the projected area of the yarn.
(3) Extracting a binary functiony tContour line y' of (x, y)t(x,y)；
In the step (3), a binary function is extractedy tContour line y' of (x, y)tThe method of (x, y) is: when in usey t(x,y)-y t(x-1, y) =1, y ″t(x, y) = 1; otherwise, y ″t(x, y) =0, x =2~ M. The method extracts a binary functiony tLeft contour of projection of yarn in (x, y).
In the step (3), a binary function is extractedy tContour line y' of (x, y)tThe method of (x, y) is: when in usey t(x,y)-y t(x +1, y) =1, y ″t(x, y) = 1; otherwise, y ″t(x, y) =0, x =1~ M-1. The method extracts a binary functiony t(x, y) the projected right contour of the yarn.
(4) Extracting the contour line y ″tNumerical descriptor R of (x, y)t；
In the step (4), the contour line y' is extractedtNumerical descriptor R of (x, y)tThe method comprises the following steps: rt=
. Contour line yt(x, y) or binary image data, which is inconvenient for comparison or quantitative description. And a numerical descriptor RtTwo lines of outlinesThe x values are differentiated to obtain an absolute value, so that the number of the pile edges on the contour line or the protruding degree is reflected, and the characteristics of the yarns can be objectively described.
(5) Comparing the currently acquired numerical descriptors RtWith the value descriptor R of the previous acquisitiont-1: when Rt-Rt-1If the | is greater than or equal to a preset threshold value K, judging that the yarn is in a motion state; when Rt-Rt-1And if the | is smaller than a preset threshold value K, judging that the yarn is in a static state.
According to the degree of similarity R when the yarn is stationaryt-Rt-1And judging according to the principle that | is close to zero.
Claims (4)
1. The yarn state detection method based on contour line analysis is characterized in that a U-shaped shell is arranged, an electronic control device is arranged in the shell and comprises a power circuit for providing a power supply, a processor for performing operation processing, an infrared emission unit and an image sensor, the infrared emission unit and the image sensor are connected with the processor, an infrared filter is arranged on the image sensor, the infrared emission unit is arranged right above the image sensor, and yarns penetrate through the lower part of the infrared emission unit and are projected onto the image sensor, and the yarn state detection method based on contour line analysis is characterized in that: the yarn state detection method is arranged in the processor, can detect a static state or a moving state under a slight yarn moving state, and comprises the following steps:
(1) every fixed period T, the processor collects the image data output by the image sensorf t(x, y), x = 1-M, y = 1-N, wherein M is the maximum pixel number in the x-axis direction, and N is the maximum pixel number in the y-axis direction;
(2) adopting binary algorithm to make the described image dataf t(x, y) performing binarization processing to obtain a binary functiony t(x, y), and the projected area of the yarny t(x, y) =1, non-projection areay t(x,y)=0；
(3) Extracting a binary functiony t(x, y) ofContour line yt(x,y)；
(4) Extracting the contour line y ″tNumerical descriptor R of (x, y)t；
(5) Comparing the currently acquired numerical descriptors RtWith the value descriptor R of the previous acquisitiont-1: when Rt-Rt-1If the | is greater than or equal to a preset threshold value K, judging that the yarn is in a motion state; when Rt-Rt-1And if the | is smaller than a preset threshold value K, judging that the yarn is in a static state.
2. The contour analysis-based yarn state detecting method as claimed in claim 1, wherein: in the step (3), a binary function is extractedy tContour line y' of (x, y)tThe method of (x, y) is: when in usey t(x,y)-y t(x-1, y) =1, y ″t(x, y) = 1; otherwise, y ″t(x,y)=0，x=2~M。
3. The contour analysis-based yarn state detecting method as claimed in claim 1, wherein: in the step (3), a binary function is extractedy tContour line y' of (x, y)tThe method of (x, y) is: when in usey t(x,y)-y t(x +1, y) =1, y ″t(x, y) = 1; otherwise, y ″t(x,y)=0，x=1~M-1。
4. The contour analysis-based yarn state detecting method as claimed in claim 1, wherein: in the step (4), the contour line y' is extractedtNumerical descriptor R of (x, y)tThe method comprises the following steps: rt=
。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911333961.3A CN111088597B (en) | 2019-12-23 | 2019-12-23 | Contour line analysis-based yarn state detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911333961.3A CN111088597B (en) | 2019-12-23 | 2019-12-23 | Contour line analysis-based yarn state detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111088597A true CN111088597A (en) | 2020-05-01 |
| CN111088597B CN111088597B (en) | 2021-08-13 |
Family
ID=70396589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911333961.3A Active CN111088597B (en) | 2019-12-23 | 2019-12-23 | Contour line analysis-based yarn state detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111088597B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101127085A (en) * | 2006-07-28 | 2008-02-20 | 索尼株式会社 | Image processing method and image processing device |
| CN102495026A (en) * | 2011-11-23 | 2012-06-13 | 天津大学 | Acquiring method of optical zone central line used in linear laser scanning vision measurement system |
| CN103065124A (en) * | 2012-12-24 | 2013-04-24 | 成都国科海博计算机系统有限公司 | Smoke detection method, device and fire detection device |
| CN103336962A (en) * | 2013-07-16 | 2013-10-02 | 慈溪思达电子科技有限公司 | Image judgment method of yarn status sensor |
| CN103352283A (en) * | 2013-07-19 | 2013-10-16 | 慈溪思达电子科技有限公司 | Identification method for judging fine motion sate of image with yarn-state sensor |
| CN105526887A (en) * | 2016-02-23 | 2016-04-27 | 东华大学 | Non-contact type fabric surface roughness test method and test device |
| CN105628603A (en) * | 2016-03-10 | 2016-06-01 | 上海工程技术大学 | Fabric wrinkle analyzing equipment and fabric wrinkle analyzing method |
| CN106897724A (en) * | 2015-12-18 | 2017-06-27 | 南京财经大学 | A kind of plant leaf identification method based on contour line shape facility |
-
2019
- 2019-12-23 CN CN201911333961.3A patent/CN111088597B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101127085A (en) * | 2006-07-28 | 2008-02-20 | 索尼株式会社 | Image processing method and image processing device |
| CN102495026A (en) * | 2011-11-23 | 2012-06-13 | 天津大学 | Acquiring method of optical zone central line used in linear laser scanning vision measurement system |
| CN103065124A (en) * | 2012-12-24 | 2013-04-24 | 成都国科海博计算机系统有限公司 | Smoke detection method, device and fire detection device |
| CN103336962A (en) * | 2013-07-16 | 2013-10-02 | 慈溪思达电子科技有限公司 | Image judgment method of yarn status sensor |
| CN103352283A (en) * | 2013-07-19 | 2013-10-16 | 慈溪思达电子科技有限公司 | Identification method for judging fine motion sate of image with yarn-state sensor |
| CN106897724A (en) * | 2015-12-18 | 2017-06-27 | 南京财经大学 | A kind of plant leaf identification method based on contour line shape facility |
| CN105526887A (en) * | 2016-02-23 | 2016-04-27 | 东华大学 | Non-contact type fabric surface roughness test method and test device |
| CN105628603A (en) * | 2016-03-10 | 2016-06-01 | 上海工程技术大学 | Fabric wrinkle analyzing equipment and fabric wrinkle analyzing method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111088597B (en) | 2021-08-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103336962B (en) | The image determinant method of yarn conditions sensor | |
| St-Charles et al. | Improving background subtraction using local binary similarity patterns | |
| CN103352283A (en) | Identification method for judging fine motion sate of image with yarn-state sensor | |
| CN109697400B (en) | Image detection method and image detection device for judging posture of user | |
| CN111088597B (en) | Contour line analysis-based yarn state detection method | |
| CN111005152B (en) | Yarn detection method based on graph similarity comparison | |
| Ruchay et al. | Impulsive noise removal from color video with morphological filtering | |
| Yoo et al. | A 213.7-$\mu $ W Gesture Sensing System-On-Chip With Self-Adaptive Motion Detection and Noise-Tolerant Outermost-Edge-Based Feature Extraction in 65 nm | |
| JP7403562B2 (en) | Method for generating slap/finger foreground masks | |
| CN111058182A (en) | Yarn state detection method based on projection area statistics | |
| CN112760802A (en) | Yarn state discrimination method based on feature two-dimensional description | |
| CN111058131A (en) | Method for monitoring yarns of spinning machine based on moving distance analysis | |
| CN110895707A (en) | Depth discrimination method for underwear types of washing machine under strong shielding condition | |
| CN111141748A (en) | Yarn state detection method based on selvedge analysis | |
| CN111058270A (en) | Yarn state detection method based on gravity center analysis | |
| KR100751467B1 (en) | Image processing device for recognizing outline of moving target and method therefor | |
| CN111139580A (en) | Method for monitoring yarns of spinning machine based on longitudinal histogram analysis | |
| Abdusalomov et al. | Review on various widely used shadow detection methods to identify a shadow from images | |
| CN111139582A (en) | Textile machine yarn monitoring method based on edge projection analysis | |
| CN111058183B (en) | Yarn detection method based on image form recognition | |
| CN111139579A (en) | Method for monitoring yarns of spinning machine based on longitudinal width distribution | |
| TWI419057B (en) | Method and system for detecting blur fingerprint images | |
| KR20140042551A (en) | Method of extracting feature for human detection and apparatus for performing the same | |
| Mahendran et al. | Object tracking system based on invariant features | |
| CN111139581A (en) | Method for monitoring yarns of spinning machine based on characteristic point position analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210723 Address after: 247299 No. 118, Meicheng Road, Yaodu Town, Dongzhi County, Chizhou City, Anhui Province Applicant after: ANHUI YAOYU INTELLIGENT SOCK INDUSTRY Co.,Ltd. Address before: 310013 no.256, 6th floor, building 2, Huahong building, 248 Tianmushan Road, Xihu District, Hangzhou City, Zhejiang Province Applicant before: HANGZHOU JINGYI INTELLIGENT SCIENCE & TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Yarn state detection method based on contour analysis Effective date of registration: 20220425 Granted publication date: 20210813 Pledgee: Anhui Dongzhi Rural Commercial Bank Co.,Ltd. Pledgor: ANHUI YAOYU INTELLIGENT SOCK INDUSTRY Co.,Ltd. Registration number: Y2022980004736 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20230420 Granted publication date: 20210813 Pledgee: Anhui Dongzhi Rural Commercial Bank Co.,Ltd. Pledgor: ANHUI YAOYU INTELLIGENT SOCK INDUSTRY Co.,Ltd. Registration number: Y2022980004736 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Yarn state detection method based on contour analysis Effective date of registration: 20230423 Granted publication date: 20210813 Pledgee: Anhui Dongzhi Rural Commercial Bank Co.,Ltd. Pledgor: ANHUI YAOYU INTELLIGENT SOCK INDUSTRY Co.,Ltd. Registration number: Y2023980038793 |