CN106093052B - A kind of broken yarn detection method - Google Patents
A kind of broken yarn detection method Download PDFInfo
- Publication number
- CN106093052B CN106093052B CN201610393696.8A CN201610393696A CN106093052B CN 106093052 B CN106093052 B CN 106093052B CN 201610393696 A CN201610393696 A CN 201610393696A CN 106093052 B CN106093052 B CN 106093052B
- Authority
- CN
- China
- Prior art keywords
- region
- yarn
- extracted
- frame
- character
- 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
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000012806 monitoring device Methods 0.000 claims abstract description 9
- 239000000463 material Substances 0.000 claims abstract description 8
- 238000012946 outsourcing Methods 0.000 claims description 17
- 238000001914 filtration Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 9
- 239000000284 extract Substances 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 4
- 239000006002 Pepper Substances 0.000 claims description 3
- 230000002146 bilateral effect Effects 0.000 claims description 2
- 230000003628 erosive effect Effects 0.000 claims description 2
- 230000001788 irregular Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 230000003287 optical effect Effects 0.000 claims description 2
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 238000012423 maintenance Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 101100328886 Caenorhabditis elegans col-2 gene Proteins 0.000 description 2
- 101100328884 Caenorhabditis elegans sqt-3 gene Proteins 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000005530 etching Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- 235000008534 Capsicum annuum var annuum Nutrition 0.000 description 1
- 240000008384 Capsicum annuum var. annuum Species 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- 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
- G01N2021/8893—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 providing a video image and a processed signal for helping visual decision
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses a kind of broken yarn detection methods, are related to automation control area, can go out broken yarn with lower buying, maintenance cost accurate detection.The present invention includes: that control holder is moved along guide rail, CCD camera is installed on the holder, the CCD camera is in the captured in real-time vision signal along guide rail moving process;Frame is extracted from the vision signal according to preset gap periods, and broken yarn has been detected whether according to extracted frame;If detecting broken yarn according to extracted frame, the picture material in specified region is extracted from the frame comprising broken yarn, Sign Board is set in the specified region;Mark character represented by the Sign Board in the specified region is matched and identified by preset image template, and the mark character identified is sent to monitoring device.The present invention is suitable for broken yarn detection on twisting machine.
Description
Technical field
The present invention relates to automation control area more particularly to a kind of broken yarn detection methods.
Background technique
Twisting thread is important link in fabrication processes, in the process it sometimes appear that broken yarn phenomenon, twists line process and cause
A degree of influence.Current broken yarn detection is mainly by artificial detection, labor intensity height, low efficiency and vulnerable to human factor shadow
It rings.In the relatively high some factories of the degree of automation, using mechanical device and it is aided with corresponding detection circuit and realizes broken yarn
Detection, but every covering device can only detect whether it is broken for a yarn, if production scale is larger, need to spend many funds
Configure many covering devices.
In order to solve the problems, such as to detect inaccuracy vulnerable to environment and operating condition interference in traditional artificial detection method, at present
Some scholars propose fabric broken yarn on-line checking scheme based on computer vision, closely arrange mainly for detection of yarn
Fabric.But it then will lead to testing result inaccuracy when spacing is larger between adjacent two yarns on twisting machine.Also some is based on machine
Due to the offering question of imaging sensor, can only detect specific several one threads in camera coverage is the detection method of device vision
No fracture is not suitable on twisting machine a large amount of yarns and needs the case where detecting of moving in circles.
Summary of the invention
The embodiment of the present invention provides a kind of broken yarn detection method, can accurate detection go out broken yarn, and cost is relatively low and
It is easy to maintain, to meet for placing the needs detected in workshop for broken yarn on twisting machine on a large scale.
In order to achieve the above objectives, the embodiment of the present invention adopts the following technical scheme that
Control holder is moved along guide rail, CCD camera is installed on the holder, the CCD camera is moved along guide rail
Captured in real-time vision signal in the process;Frame is extracted from the vision signal according to preset gap periods, and according to extracted
Frame has detected whether broken yarn;If detecting broken yarn according to extracted frame, specified region is extracted from the frame comprising broken yarn
Sign Board is arranged in the specified region in picture material;It is matched and is identified in the specified region by preset image template
Sign Board represented by mark character, and by the mark character identified to monitoring device send pass through preset image
Template matching simultaneously identifies mark character represented by the Sign Board in the specified region, and the mark character that will be identified
It is matched to monitoring device transmission by preset image template and identifies mark represented by the Sign Board in the specified region
Character, and the mark character identified is matched to monitoring device transmission by preset image template and identifies the finger
Determine mark character represented by the Sign Board in region, and the mark character identified is sent to monitoring device.
Broken yarn detection method provided in an embodiment of the present invention is moved by control holder along guide rail, so that installing on holder
CCD camera in the captured in real-time vision signal along guide rail moving process;Believe according to preset gap periods from the video
Number frame is extracted, and broken yarn has been detected whether according to extracted frame;If detecting broken yarn according to extracted frame, from comprising disconnected
The picture material in specified region is extracted in the frame of yarn, and Sign Board is set in the specified region;Pass through preset image template again
Match and identify mark character represented by the Sign Board in the specified region, and by the mark character identified to prison
Equipment is controlled to send.Scheme in compared with the existing technology, the embodiment of the present invention pass through the hands such as detection frame by frame and image template matching
Section, can accurate detection go out broken yarn, especially accurately detect broken yarn when spacing is larger between adjacent two yarns.And this
The composition of equipment needed for inventive embodiments is relatively simple, is relatively low cost and easy to safeguard, to meet for extensive placement vehicle
Between on twisting machine broken yarn detect needs.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to needed in the embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ability
For the those of ordinary skill of domain, without creative efforts, it can also be obtained according to these attached drawings other attached
Figure.
Fig. 1 is the flow diagram of broken yarn detection method provided in an embodiment of the present invention;
Fig. 2 is a kind of structural schematic diagram of Yarn break checkout gear provided in an embodiment of the present invention;
Fig. 3, Fig. 4 are the schematic diagram of the specific example of broken yarn detection method provided in an embodiment of the present invention.
Specific embodiment
Technical solution in order to enable those skilled in the art to better understand the present invention, with reference to the accompanying drawing and specific embodiment party
Present invention is further described in detail for formula.Embodiments of the present invention are described in more detail below, the embodiment is shown
Example is shown in the accompanying drawings, and in which the same or similar labels are throughly indicated same or similar element or has identical or class
Like the element of function.It is exemplary below with reference to the embodiment of attached drawing description, for explaining only the invention, and cannot
It is construed to limitation of the present invention.Those skilled in the art of the present technique are appreciated that unless expressly stated, odd number shape used herein
Formula " one ", "one", " described " and "the" may also comprise plural form.It is to be further understood that specification of the invention
Used in wording " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that
In the presence of or add other one or more features, integer, step, operation, element, component and/or their group.It should be understood that
When we say that an element is " connected " or " coupled " to another element, it can be directly connected or coupled to other elements, or
There may also be intermediary elements.In addition, " connection " used herein or " coupling " may include being wirelessly connected or coupling.Here make
Wording "and/or" includes one or more associated any cells for listing item and all combinations.The art
Technical staff is appreciated that unless otherwise defined all terms (including technical terms and scientific terms) used herein have
Meaning identical with the general understanding of the those of ordinary skill in fields of the present invention.It should also be understood that such as general
Those terms, which should be understood that, defined in dictionary has a meaning that is consistent with the meaning in the context of the prior art, and
Unless defined as here, it will not be explained in an idealized or overly formal meaning.
The embodiment of the present invention provides a kind of broken yarn detection method, as shown in Figure 1, comprising:
S1, control holder are moved along guide rail.
In the present embodiment, the structural schematic diagram of a kind of Yarn break checkout gear as shown in Figure 2, installs CCD on holder
Video camera, the CCD camera is in the captured in real-time vision signal along guide rail moving process.Wherein, CCD camera is along guide rail
The vision signal that the pal mode containing yarn is constantly acquired in moving process, is converted vision signal by TVP5150 Video Decoder
At BT.656 standard video signal transmission to DSP carry out image procossing.It should be noted that employed in the present embodiment
" holder " specifically can be a kind of connecting bracket for fixing CCD camera and for controlling CCD camera shooting stability,
One end of connecting bracket can be fixed on guide rail by slide construction, and be moved along guide rail.
Specifically, being controlled described in the holder guidance during CCD camera acquires the vision signal
The optical axis center line of CCD camera is vertical with yarn plane always.
S2, frame is extracted from the vision signal according to preset gap periods, and has been detected whether according to extracted frame
Broken yarn.
Such as: as shown in Figure 4, described according to preset gap periods, extracting the specific of frame from the vision signal can
To be embodied as following below scheme: successively from the 5i frame extracted in the vision signal in video sequence, wherein i is positive integer.According to
The secondary 5i frame in video sequence carries out image procossing as source images, whether has broken yarn in detection image, carries out if having
It handles in next step, otherwise handles next frame picture.
If S3, detecting broken yarn according to extracted frame, out of, specified region is extracted in the frame comprising broken yarn image
Hold, Sign Board is set in the specified region.
Wherein it is possible to the region comprising indicating the rectangular number board of broken yarn serial number is obtained by formulating area-of-interest, and
Image procossing is carried out to image section in this region, broken yarn serial number is then obtained by the method for template matching.
S4, it is matched by preset image template and identifies identifier word represented by the Sign Board in the specified region
Symbol, and the mark character identified is sent to monitoring device.
Wherein, mark character is for indicating that broken yarn serial number, monitoring device can be the upper control machine of twisting machine, Huo Zheji
The mobile terminal of art maintenance personnel.
In the present embodiment, the specific decision procedure of broken yarn is detected whether according to extracted frame, comprising:
From the frame extracted in vision signal, the row coordinate section where yarn is identified, and extract in the image in this section
Hold and is used as region containing yarn.It wherein, can be to collected before being handled 5i (n=1,2,3,4 ...) frame picture
Anticipate a frame picture by many experiments obtain image meduim yarn where rough row coordinate section, processing 5i (n=1,2,3,
4 ...) when frame picture, the image section (i.e. region containing yarn) only extracted in this section is handled, to improve processing speed.
And first kind processing is carried out to the region containing yarn, comprising: the green pepper in the region containing yarn is removed by median filtering
Salt noise, and contain yarn using the contrast in the histogram equalization enhancing region containing yarn, then by the way that Threshold segmentation removal is described
The background pixel in region, and using preset square structure member by connecting thread segment, the side among erosion removal broken yarn
The width of shape structural elements is greater than the width of connection thread segment and is less than the width of normal yarn, and the spiced salt in the region containing yarn is made an uproar
Sound is irregular distribution, discrete noise pixel in image.
If there are connection yarns as shown in Figure 3 for connection among broken yarn, also pass through corruption using preset square structure member
Except connection thread segment among broken yarn, the width of the square structure member is greater than the width of connection thread segment and is less than just etching off
The width of normal yarn.The second class processing is carried out to the region containing yarn again, comprising: extract by the described of first kind processing
The edge of all objects in region containing yarn, and according to the length filtration noise edge at extracted edge, connection region is obtained, then
The area in connection region is calculated.Specifically, removing the salt-pepper noise in the extracted region containing yarn using median filtering, then benefit
Remove most of background pixel with the contrast in histogram equalization enhancing region containing yarn, then by Threshold segmentation, and make yarn with
The pixel value of a small amount of background pixel is 0, and the pixel value of other pixels is 255, then by the second class of etching away broken yarn
Between thin coupling part, followed by the edge of all objects in Canny operator extraction image, and according to the length for extracting edge
Degree, filters out too short noise edge, obtains several connection regions, and calculate the area in connection region.
Whether the area for detecting the connection region again is greater than threshold value, connection of the threshold value between adjacent two non-broken yarns
The approximation of the area in logical region determines exist in the connection region if the area in the connection region is greater than the threshold value
Broken yarn.Such as: the area in the connection region between adjacent two yarns (wherein, without broken yarn among adjacent two yarns) can be set
Approximation is threshold value 1 (wherein, the approximation of the area in connection region is bigger than normal than the area being actually calculated), then area is greater than
There is broken yarn in the connection region of the threshold value, the column coordinate of the Far Left pixel and rightmost pixel that record the connection region is respectively
Col1 and col2.
In the present embodiment, the picture material that the specified region is matched by preset image template, and identify
Represented by Sign Board in the specified region identify character specific embodiment include:
Digit plate region is extracted in the picture material in the specified region, and obtains the row coordinate area where digit plate
Between, wherein the Sign Board is the digit plate for being placed in the lower section of every yarn, and the digit plate of the lower section of a yarn is about described one
Straight line bilateral symmetry, all digit plates are located at same level height where root yarn.
The digit plate region is smoothed using self-adaptive smooth filtering, and by described in Threshold segmentation removal
The background pixel in digit plate region, then extract the edge of all numerical characters and digit plate frame in image, and according to being extracted
Edge length filtration noise edge.Such as: it is right before carrying out image procossing to 5i (i=1,2,3,4 ...) frame picture
Collected any one frame picture obtains the row coordinate section in source images where digit plate by many experiments, only extracts row and sits
It is marked in this section and image section (i.e. digit plate region) of the column coordinate in section [col1, col2] is handled, to improve
Processing speed.And digit plate region is carried out smoothly using self-adaptive smooth filtering, then pass through Threshold segmentation and remove most of back
Scene element, then using the edge of all numerical characters and digit plate frame in Canny operator extraction image, and according to extraction side
The length filtration of edge falls too long noise edge, to make the pixel value 255 of numerical character, the pixel value of other objects is 0.
The outsourcing rectangle of numerical character is marked off from the digit plate region again, and extracts the figure in each outsourcing rectangle
As part, if the column coordinate difference of the top left corner pixel of two neighboring outsourcing rectangle is less than preset value, determine described two outer
Packet rectangle belongs to the same digit plate, and matches according to preset image template and identify the number in each outsourcing rectangle
Character, the preset image template are individual digit character picture identical with numerical character font in digit plate.Specifically,
It can be by finding the outsourcing rectangle of each numerical character, and the image section in each rectangle is extracted, given threshold 2, if adjacent
The column coordinate difference of the top left corner pixel of two outsourcing rectangles is less than threshold value 2, then this two character belongs to the same digit plate, otherwise
Adhere to two different digit plates separately;
In the preferred embodiment of the present embodiment, the picture of the numerical character for the 0-9 that the template is 24 × 48.Wherein, exist
In the preset image template, every width digital picture is divided into 4 × 4 pieces of regions, and 16 average values of each character save
For 16 dimensional vectors, the average value is the pixel average in 4 × 4 pieces of regions region Zhong Meikuai, and wherein average value can be as accurate as
A position.
In the present embodiment, described to be matched according to preset image template and identify the numeric word in the digit plate region
Symbol, comprising:
It is 24 × 48 by the size normalization of the numerical character in each outsourcing rectangle, and is divided into 4 × 4 pieces of areas
Domain, wherein 16 average values of each character save as 16 dimensional vectors, and the average value is 4 × 4 pieces of regions region Zhong Meikuai
Pixel average.
By the successively numeric word with the 0-9 in the preset image template of the numerical character in each outsourcing rectangle
The corresponding region average value of the picture of symbol asks variance to be matched, and is determined as matching result for variance yields is the smallest, and described
The corresponding numerical character of image template with result is the numerical character being identified as in the outsourcing rectangle, wherein each number
The sequential combination of several numerical character matching results is markup character represented by digit plate in board.The embodiment of the present invention provides
Broken yarn detection method, moved by control holder along guide rail, so that the CCD camera installed on holder is moved through along guide rail
Captured in real-time vision signal in journey;Frame is extracted from the vision signal according to preset gap periods, and according to extracted frame
Broken yarn is detected whether;If detecting broken yarn according to extracted frame, the figure in specified region is extracted from the frame comprising broken yarn
As content, Sign Board is set in the specified region;It is matched and is identified in the specified region by preset image template again
Sign Board represented by mark character, and by the mark character identified to monitoring device send.Relative to existing skill
Scheme in art, the embodiment of the present invention by frame by frame detection and image template matching etc. means, can accurate detection go out broken yarn,
Especially broken yarn is accurately detected when spacing is larger between adjacent two yarns.And equipment needed for the embodiment of the present invention is constituted
It is relatively simple, it is relatively low cost and easy to safeguard, broken yarn on twisting machine is detected for being placed in workshop on a large scale to meet
Needs.
All the embodiments in this specification are described in a progressive manner, same and similar portion between each embodiment
Dividing may refer to each other, and each embodiment focuses on the differences from other embodiments.Especially for equipment reality
For applying example, since it is substantially similar to the method embodiment, so describing fairly simple, related place is referring to embodiment of the method
Part explanation.The above description is merely a specific embodiment, but protection scope of the present invention is not limited to
This, anyone skilled in the art in the technical scope disclosed by the present invention, the variation that can readily occur in or replaces
It changes, should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the protection model of claim
Subject to enclosing.
Claims (3)
1. a kind of broken yarn detection method characterized by comprising
Control holder is moved along guide rail, CCD camera is installed on the holder, the CCD camera is along guide rail moving process
Middle captured in real-time vision signal;
Frame is extracted from the vision signal according to preset gap periods, and broken yarn has been detected whether according to extracted frame;
If detecting broken yarn according to extracted frame, the picture material in specified region is extracted from the frame comprising broken yarn, it is described
Sign Board is set in specified region;
Match and identify mark character represented by the Sign Board in the specified region by preset image template, and by institute
Identify that obtained mark character is sent to monitoring device;
The control holder is moved along guide rail, comprising: during the CCD camera acquires the vision signal, control
The holder guides the optical axis center line of the CCD camera vertical with yarn plane always;
It is described according to preset gap periods, extracting frame from the vision signal includes: successively to extract from the vision signal
5i frame in video sequence, wherein i is positive integer;
It is described to have detected whether that broken yarn includes: according to extracted frame
From the frame extracted in vision signal, the row coordinate section where yarn is identified, and extract the work of the picture material in this section
For region containing yarn;
First kind processing is carried out to the region containing yarn, comprising: the salt-pepper noise in the region containing yarn is removed by median filtering,
And enhance the contrast in the region containing yarn using histogram equalization, then the back in the region containing yarn is removed by Threshold segmentation
Scene element, and using preset square structure member by connecting thread segment, the square structure member among erosion removal broken yarn
Width be greater than the width of connection thread segment and be less than the width of normal yarn, the salt-pepper noise in the region containing yarn is image
Middle irregular distribution, discrete noise pixel;
Second class processing is carried out to the region containing yarn, comprising: extract in the region containing yarn by first kind processing
The edge of all objects, and according to the length filtration noise edge at extracted edge, connection region is obtained, then connection is calculated
The area in logical region;
Whether the area for detecting the connection region is greater than threshold value, connection region of the threshold value between adjacent two non-broken yarns
Area approximation, if the connection region area be greater than the threshold value if determine that there are broken yarns in the connection region;
It is described that mark character represented by the Sign Board in the specified region, packet are matched and identified by preset image template
It includes:
Digit plate region is extracted in the picture material in the specified region, and obtains the row coordinate section where digit plate,
In, the Sign Board is the digit plate for being placed in the lower section of every yarn, and the digit plate of the lower section of a yarn is about a yarn
Place straight line bilateral symmetry, all digit plates are located at same level height;
The digit plate region is smoothed using self-adaptive smooth filtering, and the number is removed by Threshold segmentation
The background pixel in board region, then the edge of all numerical characters and digit plate frame in image is extracted, and according to extracted side
The length filtration noise edge of edge;
The outsourcing rectangle of numerical character is marked off from the digit plate region again, and extracts the image portion in each outsourcing rectangle
Point, if the column coordinate difference of the top left corner pixel of two neighboring outsourcing rectangle is less than preset value, determine described two outsourcing squares
Shape belongs to the same digit plate;
And it is matched according to preset image template and identifies the numerical character in each outsourcing rectangle, the preset image
Template is individual digit character picture identical with numerical character font in digit plate.
2. the method according to claim 1, wherein the template is the figure of the numerical character of the 0-9 of 24x48
Piece;
In the preset image template, every width digital picture is divided into 4x4 block region, 16 average values of each character
16 dimensional vectors are saved as, the average value is the pixel average in the 4x4 block region region Zhong Meikuai.
3. according to the method described in claim 2, it is characterized in that, described match according to preset image template and identify described
Numerical character in digit plate region, comprising:
It is 24x48 by the size normalization of the numerical character in each outsourcing rectangle, and is divided into 4x4 block region,
In, 16 average values of each character save as 16 dimensional vectors, and the average value is that the pixel in the 4x4 block region region Zhong Meikuai is flat
Mean value;
By the numerical character in each outsourcing rectangle successively with the numerical character of the 0-9 in the preset image template
The corresponding region average value of picture asks variance to be matched, and is determined as matching result for variance yields is the smallest, the matching knot
The corresponding numerical character of the image template of fruit is the numerical character being identified as in the outsourcing rectangle, wherein in each digit plate
The sequential combination of several numerical character matching results is markup character represented by digit plate.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610393696.8A CN106093052B (en) | 2016-06-03 | 2016-06-03 | A kind of broken yarn detection method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610393696.8A CN106093052B (en) | 2016-06-03 | 2016-06-03 | A kind of broken yarn detection method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106093052A CN106093052A (en) | 2016-11-09 |
CN106093052B true CN106093052B (en) | 2019-10-25 |
Family
ID=57447573
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610393696.8A Active CN106093052B (en) | 2016-06-03 | 2016-06-03 | A kind of broken yarn detection method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106093052B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107328793B (en) * | 2017-06-30 | 2019-12-03 | 航天新长征大道科技有限公司 | A kind of jewelry surface word print flaw detection method and device based on machine vision |
CN107740232B (en) * | 2017-10-16 | 2023-02-28 | 琦星智能科技股份有限公司 | Sewing machine broken thread detection device and detection method and sewing machine |
CN111307827B (en) * | 2019-11-25 | 2020-12-08 | 东华大学 | Real-time visual monitoring device for broken chemical fiber filaments |
CN117670843B (en) * | 2023-12-07 | 2024-05-24 | 常州市宏发纵横新材料科技股份有限公司 | Method, device, equipment and storage medium for detecting broken yarn of color yarn |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101923741A (en) * | 2010-08-11 | 2010-12-22 | 西安理工大学 | Paper currency number identification method based on currency detector |
CN101922068A (en) * | 2010-08-13 | 2010-12-22 | 北京经纬纺机新技术有限公司 | Method and system for spinning frame to automatically detect broken yarns |
CN104008384A (en) * | 2013-02-26 | 2014-08-27 | 山东新北洋信息技术股份有限公司 | Character identification method and character identification apparatus |
CN104820986A (en) * | 2015-04-28 | 2015-08-05 | 电子科技大学 | Machine vision-based cable on-line detection method |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE10082757D2 (en) * | 1999-09-15 | 2002-02-28 | Barmag Barmer Maschf | Method and device for the optical control of a surface of a thread spool |
-
2016
- 2016-06-03 CN CN201610393696.8A patent/CN106093052B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101923741A (en) * | 2010-08-11 | 2010-12-22 | 西安理工大学 | Paper currency number identification method based on currency detector |
CN101922068A (en) * | 2010-08-13 | 2010-12-22 | 北京经纬纺机新技术有限公司 | Method and system for spinning frame to automatically detect broken yarns |
CN104008384A (en) * | 2013-02-26 | 2014-08-27 | 山东新北洋信息技术股份有限公司 | Character identification method and character identification apparatus |
CN104820986A (en) * | 2015-04-28 | 2015-08-05 | 电子科技大学 | Machine vision-based cable on-line detection method |
Also Published As
Publication number | Publication date |
---|---|
CN106093052A (en) | 2016-11-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106093052B (en) | A kind of broken yarn detection method | |
CN104749184B (en) | Automatic optical detection method and system | |
WO2020133046A1 (en) | Defect detection method and device | |
CN107133969B (en) | A kind of mobile platform moving target detecting method based on background back projection | |
CN105453153B (en) | Traffic lights detects | |
CN103471512B (en) | A kind of glass plate width detecting system based on machine vision | |
CN108921176A (en) | A kind of pointer instrument positioning and recognition methods based on machine vision | |
CN106599890B (en) | digital instrument recognition algorithm for substation inspection robot | |
CN104749801B (en) | High Precision Automatic optical detecting method and system | |
CN105139384B (en) | The method and apparatus of defect capsule detection | |
CN110675425B (en) | Video frame identification method, device, equipment and medium | |
CN110047063B (en) | Material drop detection method, device, equipment and storage medium | |
CN104103069B (en) | Image processing apparatus, image processing method and recording medium | |
CN112036317A (en) | Face image intercepting method and device and computer equipment | |
CN104376323B (en) | A kind of method and device for determining target range | |
CN103226829A (en) | Image edge detection method based on edge enhancement operator | |
CN105096305A (en) | Method and device for analyzing state of insulators | |
CN103793923A (en) | Method and device for acquiring moving object in image | |
CN110007493A (en) | Broken bright spot detection method in liquid crystal display | |
CN110399831A (en) | A kind of method for inspecting and device | |
CN106228541A (en) | The method and device of screen location in vision-based detection | |
CN108520260A (en) | The recognition methods of visible foreign matters in bottled oral solution | |
CN106650735A (en) | Automatic positioning and recognition method for LED characters | |
CN113780119A (en) | High-precision moving target detection method based on application scene of static camera | |
CN109493293A (en) | A kind of image processing method and device, display equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |