CN106093052A - A kind of broken yarn detection method - Google Patents
A kind of broken yarn detection method Download PDFInfo
- Publication number
- CN106093052A CN106093052A CN201610393696.8A CN201610393696A CN106093052A CN 106093052 A CN106093052 A CN 106093052A CN 201610393696 A CN201610393696 A CN 201610393696A CN 106093052 A CN106093052 A CN 106093052A
- Authority
- CN
- China
- Prior art keywords
- region
- yarn
- broken yarn
- 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.)
- Granted
Links
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 method, relate to automation control area, it is possible to detect broken yarn accurately with relatively low buying, maintenance cost.The present invention includes: controls The Cloud Terrace and moves along guide rail, and described The Cloud Terrace is installed ccd video camera, and described ccd video camera is at captured in real-time video signal along guide rail moving process；Extract frame according to default gap periods from described video signal, and detect whether broken yarn according to the frame extracted；If the frame according to being extracted detects broken yarn, then from the frame comprising broken yarn, extract the picture material specifying region, described appointment region arranges Sign Board；The mark character represented by Sign Board mated by default image template and identify in described appointment region, and will be identified that the mark character obtained sends to monitoring device.The present invention is applicable to broken yarn detection on twisting machine.
Description
Technical field
The present invention relates to automation control area, particularly relate to a kind of broken yarn detection method.
Background technology
Twisting thread is the important step in fabrication processes, during it sometimes appear that broken yarn phenomenon, twist line process and cause
A certain degree of impact.Current broken yarn detection is mainly by manual detection, and labor intensity is high, and efficiency is low and easy by anthropic factor shadow
Ring.In some factories that automaticity is of a relatively high, use machinery and be aided with corresponding testing circuit to realize broken yarn
Detection, but for a yarn, every covering device can only detect whether it ruptures, if production scale is relatively big, then need to spend a lot of funds
Configure a lot of covering device.
In order to solve that traditional manual detection method is easily disturbed by environment and operating mode and detected inaccurate problem, at present
Also there is scholar to propose grey cloth broken yarn on-line checking scheme based on computer vision, closely arrange mainly for detection of yarn
Grey cloth.But, on twisting machine, between adjacent two yarns, spacing then can cause testing result inaccurate time bigger.Also have based on machine
The detection method of device vision is due to the offering question of imageing sensor, and can only detect specific several one threads in camera coverage is
No fracture, not being suitable on twisting machine a large amount of yarn needs the situation about detecting that moves in circles.
Summary of the invention
Embodiments of the invention provide a kind of broken yarn detection method, it is possible to detect broken yarn accurately, and cost is relatively low and
It is easily maintained, thus meets and place in workshop for the needs of broken yarn detection on twisting machine for extensive.
For reaching above-mentioned purpose, embodiments of the invention adopt the following technical scheme that
Controlling The Cloud Terrace to move along guide rail, described The Cloud Terrace is installed ccd video camera, described ccd video camera is moving along guide rail
During captured in real-time video signal；Frame is extracted from described video signal according to default gap periods, and according to being extracted
Frame has detected whether broken yarn；If the frame according to being extracted detects broken yarn, then extract from the frame comprising broken yarn and specify region
Picture material, arranges Sign Board in described appointment region；In being mated by default image template and identifying described appointment region
The mark character represented by Sign Board, and will be identified obtain mark character to monitoring device send by default image
Template matching the mark character represented by Sign Board in identifying described appointment region, and the mark character obtained will be identified
The mark represented by Sign Board being mated by default image template and identifying in described appointment region is sent to monitoring device
Character, and mated identifying that the mark character obtained sends to monitoring device by default image template and identify described finger
Determine the mark character represented by the Sign Board in region, and will be identified that the mark character obtained sends to monitoring device.
The broken yarn detection method that the embodiment of the present invention provides, moves along guide rail by controlling The Cloud Terrace so that install on The Cloud Terrace
Ccd video camera at captured in real-time video signal along guide rail moving process；Believe from described video according to default gap periods
Number extract frame, and detect whether broken yarn according to the frame extracted；If the frame according to being extracted detects broken yarn, then disconnected from comprising
The frame of yarn extracts the picture material specifying region, described appointment region arranges Sign Board；Again by the image template preset
The mark character represented by Sign Board mated and identify in described appointment region, and will be identified that the mark character obtained is to prison
Control equipment sends.Relative to scheme of the prior art, the embodiment of the present invention is by the hands such as detection and image template coupling frame by frame
Section, it is possible to detecting broken yarn accurately, especially spacing accurately detects broken yarn time bigger between adjacent two yarns.And this
Equipment needed for inventive embodiments constitutes relatively simple, is relatively low cost and easy to safeguard, thus meets for extensive placement vehicle
For the needs of broken yarn detection on twisting machine between.
Accompanying drawing explanation
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, below by use required in embodiment
Accompanying drawing is briefly described, it should be apparent that, the accompanying drawing in describing below is only some embodiments of the present invention, for ability
From the point of view of the those of ordinary skill of territory, on the premise of not paying creative work, it is also possible to obtain the attached of other according to these accompanying drawings
Figure.
The schematic flow sheet of the broken yarn detection method that Fig. 1 provides for the embodiment of the present invention；
The structural representation of a kind of Yarn break checkout gear that Fig. 2 provides for the embodiment of the present invention；
The schematic diagram of the instantiation of the broken yarn detection method that Fig. 3, Fig. 4 provide for the embodiment of the present invention.
Detailed description of the invention
For making those skilled in the art be more fully understood that technical scheme, below in conjunction with the accompanying drawings and specific embodiment party
The present invention is described in further detail by formula.Embodiments of the present invention, the showing of described embodiment are described in more detail below
Example is shown in the drawings, and the most same or similar label represents same or similar element or has identical or class
Element like function.The embodiment described below with reference to accompanying drawing is exemplary, is only used for explaining the present invention, and can not
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 " being somebody's turn to do " may also comprise plural form.It is to be further understood that the description of the present invention
The wording of middle use " includes " referring to there is described feature, integer, step, operation, element and/or assembly, but it is not excluded that
Exist or add other features one or more, integer, step, operation, element, assembly and/or their group.It should be understood that
When we claim element to be " connected " or during " coupled " to another element, and it can be directly connected or coupled to other elements, or
Intermediary element can also be there is.Additionally, " connection " used herein or " coupling " can include wireless connections or couple.Here make
Wording "and/or" include one or more any cell listing item being associated and all combinations.The art
Those of skill will appreciate that, unless otherwise defined, all terms used herein (including technical term and scientific terminology) have
With the those of ordinary skill in art of the present invention be commonly understood by identical meaning.Should also be understood that the most general
Those terms defined in dictionary should be understood that have the meaning consistent with the meaning in the context of prior art, and
Unless defined as here, will not explain by idealization or the most formal implication.
The embodiment of the present invention provides a kind of broken yarn detection method, as it is shown in figure 1, include:
S1, control The Cloud Terrace move along guide rail.
In the present embodiment, the structural representation of a kind of Yarn break checkout gear as shown in Figure 2, The Cloud Terrace is installed CCD
Video camera, described ccd video camera is at captured in real-time video signal along guide rail moving process.Wherein, ccd video camera is along guide rail
Moving process constantly gathers the video signal of the pal mode containing yarn, by TVP5150 Video Decoder, video signal is changed
The video signal transmission becoming BT.656 standard carries out image procossing to DSP.It should be noted that employed in the present embodiment
" The Cloud Terrace " can be specifically a kind of for fixing ccd video camera and for controlling the connection support of ccd video camera shooting stability,
The one end connecting support can be fixed on guide rail by slide construction, and moves along guide rail.
Concrete, during described ccd video camera gathers described video signal, control described The Cloud Terrace and guide described
The optical axis center line of ccd video camera is vertical with yarn plane all the time.
S2, extract frame according to default gap periods from described video signal, and detected whether according to the frame extracted
Broken yarn.
Such as: as shown in Figure 4, described according to default gap periods, extract specifically may be used of frame from described video signal
To be embodied as below scheme: extracting the 5i frame in video sequence successively from described video signal, wherein, i is positive integer.Depend on
Secondary 5i frame in video sequence is carried out image procossing as source images, whether detection image having broken yarn, if having, carrying out
Next step processes, and otherwise processes next frame picture.
If S3 detects broken yarn according to the frame extracted, then extract from the frame comprising broken yarn in the image specifying region
Hold, described appointment region arranges Sign Board.
Wherein it is possible to the region comprising the rectangular number board representing broken yarn sequence number by formulating area-of-interest to obtain, and
Image section in this region is carried out image procossing, then obtains broken yarn sequence number by the method for template matching.
S4, the identifier word represented by Sign Board mated by the image template preset and identify in described appointment region
Symbol, and will be identified that the mark character obtained sends to monitoring device.
Wherein, mark character is used for representing broken yarn sequence number, and monitoring device can be the upper control machine of twisting machine, or skill
The mobile terminal of art attendant.
In the present embodiment, detect whether the concrete decision procedure of broken yarn according to the frame extracted, including:
In the frame extracted from video signal, identify that the row-coordinate at yarn place is interval, and extract in the image in this interval
Hold as containing yarn region.Wherein, to 5i (n=1,2,3,4 ...) before frame picture processes, can be to appointing of collecting
It is interval that a frame picture of anticipating obtains the row-coordinate substantially at yarn place in image by many experiments, process 5i (n=1,2,3,
4 ...) frame picture time, only extract the image section in this interval (i.e. the region on yarn) and process, to improve processing speed.
And carry out first kind process to described containing yarn region, and including: remove the described green pepper containing yarn region by medium filtering
Salt noise, and utilize histogram equalization to strengthen the described contrast containing yarn region, then removed described containing yarn by Threshold segmentation
The background pixel in region, and utilize the square structure unit preset by connecting thread segment, described side in the middle of erosion removal broken yarn
The width of shape structural elements is more than connecting the width of thread segment and being less than the width of normal yarn, and the described spiced salt containing yarn region is made an uproar
Sound is irregular distribution in image, discrete noise pixel.
If connecting the connection yarn existed as shown in Figure 3 in the middle of broken yarn, the most also utilize default square structure unit by corruption
Etching off is except connecting thread segment in the middle of broken yarn, and the width of described square structure unit is more than connecting the width of thread segment and less than just
The often width of yarn.Equations of The Second Kind process is carried out containing yarn region again to described, including: extract described in processing through the described first kind
Containing the edge of all objects in yarn region, and according to the length filtration noise edge at the edge extracted, obtain UNICOM region, then
It is calculated the area in UNICOM region.Concrete, utilize medium filtering to remove the salt-pepper noise containing yarn region extracted, then profit
Strengthen containing the contrast in yarn region with histogram equalization, then remove major part background pixel by Threshold segmentation, and make yarn and
The pixel value of a small amount of background pixel is 0, and the pixel value of other pixels is 255, then by etching away Equations of The Second Kind broken yarn
Between thin coupling part, followed by the edge of all objects in Canny operator extraction image, and according to extracting the length at edge
Degree, filters out too short noise edge, obtains some UNICOMs region, and calculate the area in UNICOM region.
Whether the area detecting described UNICOM region again is more than threshold value, and described threshold value is the connection between adjacent two non-broken yarns
The approximation of the area in logical region, if the area in described UNICOM region is more than described threshold value, exists in judging described UNICOM region
Broken yarn.Such as: the area in UNICOM region between adjacent two yarns (wherein, adjacent two yarns in the middle of do not have broken yarn) can be set
Approximation is threshold value 1 (wherein, the approximation of the area in UNICOM region is bigger than normal than the area that Practical Calculation obtains), then area is more than
Having broken yarn in the UNICOM region of this threshold value, the row coordinate of the Far Left pixel and rightmost pixel that record this UNICOM region is respectively
Col1 and col2.
In the present embodiment, the described picture material being mated described appointment region by default image template, and identify
The detailed description of the invention of the mark character represented by the Sign Board in described appointment region includes:
In the picture material in described appointment region, extract digit plate region, and obtain the row-coordinate district at digit plate place
Between, wherein, described Sign Board is the digit plate of the lower section being placed in every yarn, and the digit plate of the lower section of a yarn is about described one
Root yarn place straight line is symmetrical, and all digit plates are positioned at same level height.
Utilize self-adaptive smooth filtering that described digit plate region is smoothed, and removed by Threshold segmentation described
The background pixel in digit plate region, then extract all numerical characters and the edge of digit plate frame in image, and according to being extracted
The length filtration noise edge at edge.Such as: to 5i (i=1,2,3,4 ...) before frame picture carries out image procossing, right
It is interval that any one frame picture collected obtains the row-coordinate at digit plate place in source images by many experiments, only extracts row and sits
In being marked on this interval and row coordinate processes at the image section (i.e. digit plate region) of interval [col1, col2], to improve
Processing speed.And utilize self-adaptive smooth filtering that digit plate region is smoothed, then remove the major part back of the body by Threshold segmentation
Scene element, then utilizes all numerical characters and the edge of digit plate frame in Canny operator extraction image, and according to extracting limit
The length filtration of edge falls long noise edge, so that the pixel value of numerical character is 255, the pixel value of other objects is 0.
From described digit plate region, mark off the outsourcing rectangle of numerical character again, and extract the figure in each outsourcing rectangle
As part, if the row coordinate difference of the top left corner pixel of adjacent two outsourcing rectangles is less than preset value, then judge outside said two
Bag rectangle belongs to same digit plate, and the numeral mated according to default image template and identify in described each outsourcing rectangle
Character, described default image template is the individual digit character picture identical with numerical character font in digit plate.Concrete,
By finding the outsourcing rectangle of each numerical character, and the image section in each rectangle can be extracted, set threshold value 2, if adjacent
The row coordinate difference of the top left corner pixel of two outsourcing rectangles is less than threshold value 2, then this two character belongs to same digit plate, otherwise
Adhere to two different digit plates separately；
In the preferred version of the present embodiment, described template is the picture of the numerical character of the 0-9 of 24 × 48..Wherein, exist
In described default image template, every width digital picture is divided into 4 × 4 pieces of regions, and 16 meansigma methodss of each character preserve
Being 16 dimensional vectors, described meansigma methods is the pixel average in Zhong Meikuai region, 4 × 4 pieces of regions, and wherein meansigma methods can be as accurate as
Individual position.
In the present embodiment, described mate according to default image template and identify the numeric word in described digit plate region
Symbol, including:
It is 24 × 48 by the size normalization of the numerical character in described each outsourcing rectangle, and is divided into 4 × 4 pieces of districts
Territory, wherein, 16 meansigma methodss of each character save as 16 dimensional vectors, and described meansigma methods is Zhong Meikuai region, 4 × 4 pieces of regions
Pixel average.
By the numerical character in described each outsourcing rectangle successively with the numeric word of the 0-9 in described default image template
The corresponding region meansigma methods of picture of symbol asks variance to mate, and by the matching result that is defined as minimum for variance yields, described
The numerical character joining the image template of result corresponding is i.e. identified as the numerical character in described outsourcing rectangle, wherein, each numeral
In board, the sequential combination of several numerical character matching results is the markup character represented by digit plate.The embodiment of the present invention provides
Broken yarn detection method, by control The Cloud Terrace move along guide rail so that on The Cloud Terrace install ccd video camera be moved through along guide rail
Captured in real-time video signal in journey；Frame is extracted from described video signal according to default gap periods, and according to the frame extracted
Detect whether broken yarn；If the frame according to being extracted detects broken yarn, then from the frame comprising broken yarn, extract the figure specifying region
As content, described appointment region arranges Sign Board；In image template by presetting mates and identifies described appointment region again
The mark character represented by Sign Board, and will be identified that the mark character that obtains sends to monitoring device.Relative to existing skill
Scheme in art, the embodiment of the present invention is by the means such as detection and image template coupling frame by frame, it is possible to detect broken yarn accurately,
Especially between adjacent two yarns, spacing accurately detects broken yarn time bigger.And the equipment needed for the embodiment of the present invention is constituted
Relatively simple, it is relatively low cost and easy to safeguard, thus meets and extensive placement in workshop is detected for broken yarn on twisting machine
Needs.
Each embodiment in this specification all uses the mode gone forward one by one to describe, identical similar portion between each embodiment
Dividing and see mutually, what each embodiment stressed is the difference with other embodiments.Real especially for equipment
For executing example, owing to it is substantially similar to embodiment of the method, so describing fairly simple, relevant part sees embodiment of the method
Part illustrate.The above, the only detailed description of the invention of the present invention, but protection scope of the present invention is not limited to
This, any those familiar with the art in the technical scope that the invention discloses, the change that can readily occur in or replace
Change, all should contain within protection scope of the present invention.Therefore, protection scope of the present invention should be with the protection model of claim
Enclose and be as the criterion.
Claims (7)
1. a broken yarn detection method, it is characterised in that including:
Controlling The Cloud Terrace to move along guide rail, described The Cloud Terrace is installed ccd video camera, described ccd video camera is along guide rail moving process
Middle captured in real-time video signal；
Extract frame according to default gap periods from described video signal, and detect whether broken yarn according to the frame extracted；
If the frame according to being extracted detects broken yarn, then from the frame comprising broken yarn, extract the picture material specifying region, described
Specify in region and Sign Board is set；
The mark character represented by Sign Board mated by default image template and identify in described appointment region, and by institute
Identify that the mark character obtained sends to monitoring device.
Method the most according to claim 1, it is characterised in that described control The Cloud Terrace moves along guide rail, including: described
During ccd video camera gathers described video signal, control described The Cloud Terrace and guide the optical axis center line of described ccd video camera to begin
The most vertical with yarn plane.
Method the most according to claim 1, it is characterised in that described according to default gap periods, believes from described video
Number extracting frame includes: extracting the 5i frame in video sequence successively from described video signal, wherein, i is positive integer.
4. according to the method described in any one in claim 1-3, it is characterised in that described detection according to the frame extracted is
No have broken yarn to include:
In the frame extracted from video signal, identify that the row-coordinate at yarn place is interval, and extract the picture material work in this interval
For containing yarn region；
First kind process is carried out containing yarn region to described, including: remove the described salt-pepper noise containing yarn region by medium filtering,
And utilize histogram equalization to strengthen the described contrast containing yarn region, then remove the described back of the body containing yarn region by Threshold segmentation
Scene element, and utilize the square structure unit preset by the middle thread segment that connects of erosion removal broken yarn, described square structure unit
Width more than connecting the width of thread segment and less than the width of normal yarn, the described salt-pepper noise containing yarn region is image
Middle irregular distribution, discrete noise pixel.
Equations of The Second Kind process is carried out containing yarn region to described, including: extract described in processing through the described first kind containing in yarn region
The edge of all objects, and according to the length filtration noise edge at the edge extracted, obtain UNICOM region, then be calculated connection
The area in logical region；
Whether the area detecting described UNICOM region is more than threshold value, and described threshold value is the UNICOM region between adjacent two non-broken yarns
The approximation of area, if the area in described UNICOM region is more than described threshold value, in judging described UNICOM region, there is broken yarn.
Method the most according to claim 1, it is characterised in that described mated by default image template and identify described
Specify the mark character represented by Sign Board in region, including:
In the picture material in described appointment region, extract digit plate region, and the row-coordinate obtaining digit plate place is interval, its
In, described Sign Board is the digit plate of the lower section being placed in every yarn, and the digit plate of the lower section of a yarn is about a described yarn
Place straight line is symmetrical, and all digit plates are positioned at same level height；
Utilize self-adaptive smooth filtering that described digit plate region is smoothed, and remove described numeral by Threshold segmentation
The background pixel in board region, then extract all numerical characters and the edge of digit plate frame in image, and according to the limit extracted
The length filtration noise edge of edge；
From described digit plate region, mark off the outsourcing rectangle of numerical character again, and extract the image portion in each outsourcing rectangle
Point, if the row coordinate difference of the top left corner pixel of adjacent two outsourcing rectangles is less than preset value, then judge said two outsourcing square
Shape belongs to same digit plate；
And the numerical character mating according to default image template and identifying in described each outsourcing rectangle, described default image
Template is the individual digit character picture identical with numerical character font in digit plate.
Method the most according to claim 5, it is characterised in that described template is the figure of the numerical character of the 0-9 of 24x48
Sheet；
In described default image template, every width digital picture is divided into 4x4 block region, 16 meansigma methodss of each character
Saving as 16 dimensional vectors, described meansigma methods is the pixel average in Zhong Meikuai region, 4x4 block region.
Method the most according to claim 6, it is characterised in that described mate according to default image template and identify described
Numerical character in digit plate region, including:
It is 24x48 by the size normalization of the numerical character in described each outsourcing rectangle, and is divided into 4x4 block region, its
In, 16 meansigma methodss of each character save as 16 dimensional vectors, and described meansigma methods is that the pixel in Zhong Meikuai region, 4x4 block region is put down
Average；
By the numerical character in described each outsourcing rectangle successively with the numerical character of the 0-9 in described default image template
The corresponding region meansigma methods of picture asks variance to mate, and minimum for variance yields is defined as matching result, and described coupling is tied
The numerical character that the image template of fruit is corresponding is i.e. identified as the numerical character in described outsourcing rectangle, wherein, in each digit plate
The sequential combination of several numerical character matching results is the 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 true CN106093052A (en) | 2016-11-09 |
| CN106093052B 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) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107328793A (en) * | 2017-06-30 | 2017-11-07 | 航天新长征大道科技有限公司 | A kind of ornaments surface word print flaw detection method and device based on machine vision |
| CN107740232A (en) * | 2017-10-16 | 2018-02-27 | 杭州琦星机器人科技有限公司 | Wire-off detection device for sewing machine, detection method and sewing machine |
| CN111307827A (en) * | 2019-11-25 | 2020-06-19 | 东华大学 | Real-time visual monitoring device for broken chemical fiber filaments |
| CN117670843A (en) * | 2023-12-07 | 2024-03-08 | 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 (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001019714A1 (en) * | 1999-09-15 | 2001-03-22 | Barmag Ag | Method and device for optically inspecting a surface of a yarn bobbin |
| 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 |
-
2016
- 2016-06-03 CN CN201610393696.8A patent/CN106093052B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001019714A1 (en) * | 1999-09-15 | 2001-03-22 | Barmag Ag | Method and device for optically inspecting a surface of a yarn bobbin |
| 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 |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107328793A (en) * | 2017-06-30 | 2017-11-07 | 航天新长征大道科技有限公司 | A kind of ornaments surface word print flaw detection method and device based on machine vision |
| CN107740232A (en) * | 2017-10-16 | 2018-02-27 | 杭州琦星机器人科技有限公司 | Wire-off detection device for sewing machine, detection method and sewing machine |
| 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 |
| CN111307827A (en) * | 2019-11-25 | 2020-06-19 | 东华大学 | Real-time visual monitoring device for broken chemical fiber filaments |
| CN111307827B (en) * | 2019-11-25 | 2020-12-08 | 东华大学 | Real-time visual monitoring device for broken chemical fiber filaments |
| CN117670843A (en) * | 2023-12-07 | 2024-03-08 | 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106093052B (en) | 2019-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104749184B (en) | Automatic optical detection method and system | |
| CN107133969B (en) | A kind of mobile platform moving target detecting method based on background back projection | |
| CN106093052A (en) | A kind of broken yarn detection method | |
| CN105139386A (en) | Image processing method for quickly and automatically detecting soldered dot unsatisfied products of electric connectors | |
| CN109507192A (en) | A kind of magnetic core detection method of surface flaw based on machine vision | |
| CN106599890B (en) | digital instrument recognition algorithm for substation inspection robot | |
| CN104135660A (en) | Detection method of contamination of image pickup module and detection system | |
| CN103018589A (en) | Automatic detection device and automatic detection method for remote controller | |
| CN113658131A (en) | Tour type ring spinning broken yarn detection method based on machine vision | |
| CN106780526A (en) | A kind of ferrite wafer alligatoring recognition methods | |
| CN106228541A (en) | The method and device of screen location in vision-based detection | |
| CN103226829A (en) | Image edge detection method based on edge enhancement operator | |
| CN108171674B (en) | Vision correction method for projector image with any visual angle | |
| CN101702204A (en) | Paper counter | |
| CN110007493A (en) | Broken bright spot detection method in liquid crystal display | |
| CN104749801B (en) | High Precision Automatic optical detecting method and system | |
| CN112967221B (en) | Shield segment production and assembly information management system | |
| CN112016482B (en) | Method and device for distinguishing false face and computer equipment | |
| CN110389130A (en) | Intelligent checking system applied to fabric | |
| CN109378279A (en) | Wafer detection method and wafer detection system | |
| CN101807297B (en) | Medical ultrasonic image line detection method | |
| CN111426693A (en) | Quality defect detection system and detection method thereof | |
| CN117115171B (en) | Slight bright point defect detection method applied to subway LCD display screen | |
| CN110441318A (en) | A kind of chemical fibre spinneret hole defect inspection method based on machine vision | |
| CN106530292B (en) | A kind of steel strip surface defect image Fast Identification Method based on line scan camera |
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 |