CN107392905A - Real-time pattern identifying system - Google Patents
Real-time pattern identifying system Download PDFInfo
- Publication number
- CN107392905A CN107392905A CN201710668493.XA CN201710668493A CN107392905A CN 107392905 A CN107392905 A CN 107392905A CN 201710668493 A CN201710668493 A CN 201710668493A CN 107392905 A CN107392905 A CN 107392905A
- Authority
- CN
- China
- Prior art keywords
- pattern
- image
- equipment
- sheet
- pixel
- 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
- 238000003909 pattern recognition Methods 0.000 claims abstract description 51
- 238000001914 filtration Methods 0.000 claims description 38
- 230000002708 enhancing effect Effects 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 230000006872 improvement Effects 0.000 claims description 6
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims 1
- 238000005728 strengthening Methods 0.000 claims 1
- 229920000742 Cotton Polymers 0.000 description 7
- 239000004744 fabric Substances 0.000 description 6
- 230000008859 change Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000002156 mixing Methods 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 239000004753 textile Substances 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004061 bleaching Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000009940 knitting Methods 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005517 mercerization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 235000014347 soups Nutrition 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
- 238000009941 weaving Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The present invention relates to a kind of sheet pattern recogni-tion system in real time, including sheet conveyer belt, pattern recognition device, pattern match equipment and Realtime Alerts equipment, the sheet conveyer belt is used to transmit sheet to be tested in real time, the pattern recognition device is used to identify the real-time pattern on sheet to be tested, the pattern match equipment is connected with the pattern recognition device, for receiving the real-time pattern, and by the real-time pattern compared with preset reference pattern, the Realtime Alerts equipment is connected with the pattern match equipment, corresponding alarm strategy is determined for the output based on the pattern match equipment.By means of the invention it is possible to the wrongly typed pattern on sheet is found in time.
Description
Technical field
The present invention relates to sheet field, more particularly to a kind of real-time pattern identifying system.
Background technology
The fabric features of sheet are that breadth, pattern and flower-shape change are flexible, have pure cotton and blending two by raw materials used difference
Class.Pure cotton sheet gas permeability, good hygroscopicity, comfortable feel is soft, abundant wear-resisting.All it is that the title yarn of single thread knits sheet through weft yarn,
All it is the title all fronts sheet of strand, yarns interwoven makees warp thread with strand, single thread makees the title half line sheet of weft yarn.Blending sheet has
Cotton/dimension, cotton/wash with the product such as cotton/fiber crops, have the advantages that it is quick-drying washable, very scrape, be strong wear-resisting.
The length and width of sheet is fixed according to the size of bed, there is Chinese style and Western-style differentiation.Chinese-style bedsheet is typically long
Spend for 210~228 centimetres, width is 100~200 centimetres.Fabric generally use re-organized, alternative construction or united organization, matter
Ground is thicker.The general length of western style bed sheet is 108 inch, width have 72,80,90 inches etc. it is a variety of.Typically using plain weave or
Twill-weave, fabric texture is relatively thin, and flower pattern is completely to dissipate flower mostly.Some products pass through napping, have good feel and guarantor
Warm property.The designs and varieties of sheet have complete white, plain color, grid, stamp, jacquard weave, napping etc..All-white bed sheet white appearance, is typically adopted
With grey cotton weaving yarns, then through scouringing and bleaching and adding white arrangement.Pastel-coloured sheet, which is that openpore is dyed, to be formed.Grid sheet is with dyed yarn (line)
It is made into.Same tone and the different title plain color grid of the depth, different tones for colored grid, by satin weave and other weavy grain intervals
Title satin bar satin lattice.The flower pattern of art ticking have colored side, middle flower, strip flower, to corner piece, dissipate flower in flower, corner and (be commonly called as four dishes one
Soup) etc..The floral designs of fancy bed sheet are according to design requirement dobbies or jacquard woven.Sheet has after mercerization finish
The advantages of glossy good, washing shrinkage is small and color is rich and gaudy.
However, often occur the situation of sheet pattern printing mistake in the prior art, once such defective product is promoted
To in the market, the use of purchase personnel is not only have impact on, more it is essential that having severely impacted the letter of sheet manufacturer
Reputation.
The content of the invention
In order to solve the above problems, the invention provides a kind of sheet pattern recogni-tion system in real time, using sheet conveyer belt
For transmitting sheet to be tested in real time, using targetedly, high-precision pattern recognition device be used for identify sheet to be tested
On real-time pattern, using pattern match equipment be used for by the real-time pattern compared with preset reference pattern, also use
Realtime Alerts equipment is used for the output based on the pattern match equipment and determines corresponding alarm strategy, particular, it is important that figure
In case identification equipment, handled based on the predetermined pattern gray threshold scope from the black level and identified in image and be partitioned into figure
Case subgraph, and the real-time pattern on sheet to be tested is determined based on the pattern subgraph, so as to improve the inspection of sheet pattern
The real-time and accuracy of survey.
According to an aspect of the present invention, there is provided a kind of sheet pattern recogni-tion system in real time, the system pass including sheet
Send band, pattern recognition device, pattern match equipment and Realtime Alerts equipment, the sheet conveyer belt is used to transmitting in real time to be tested
Sheet, the pattern recognition device are used to identify the real-time pattern on sheet to be tested, the pattern match equipment and the figure
Case identification equipment connects, for receiving the real-time pattern, and by the real-time pattern compared with preset reference pattern, institute
State Realtime Alerts equipment to be connected with the pattern match equipment, determined for the output based on the pattern match equipment corresponding
Alarm strategy.
More specifically, in the sheet pattern recogni-tion system in real time, in addition to:Flash memory device, it is pre- for prestoring
If reference pattern;Wherein, the flash memory device is connected with the pattern match equipment.
More specifically, in the sheet pattern recogni-tion system in real time:The pattern recognition device, the pattern match are set
Standby and described flash memory device is all disposed within the control cabinet of sheet conveyer belt side;Wherein, in the pattern match equipment, institute is worked as
When stating real-time pattern and preset reference pattern match degree and being more than or equal to preset matching threshold value, pattern match pass signal is sent, when
When the real-time pattern is less than preset matching threshold value with preset reference pattern match degree, pattern match failure signal is sent;It is described
Realtime Alerts equipment performs corresponding alarm operation when receiving the pattern match failure signal.
More specifically, in the sheet pattern recogni-tion system in real time, in addition to:Contour detecting equipment, exported with image
Equipment connects, and for receiving processed image, and judges the objective contour in the processed image;Shape judges equipment, with
The contour detecting equipment connection, for receiving the objective contour in the processed image, and judges the processed image
In objective contour corresponding to contour shape;Stencil-chosen equipment, judge that equipment is connected with the shape, for based on the wheel
Profile shape determines medium filtering template;The degree of correlation judges equipment, for receiving processed image, and judges the processed image
In the degree of correlation grade between pixel two-by-two;Adaptive-filtering equipment, respectively with the stencil-chosen equipment and the degree of correlation
Judge that equipment connects, using each pixel in the processed image as object pixel, based on the medium filtering template
It is determined that the medium filtering window centered on the object pixel, by the phase in the medium filtering window with the object pixel
After pass degree grade is more than or equal to filtering of the average of the pixel value of all pixels of predetermined level threshold value as the object pixel
Pixel value;Filtered pixel value output adaptive filtering figure of the adaptive-filtering equipment based on all object pixels
Picture.
More specifically, in the sheet pattern recogni-tion system in real time, in addition to:
Multilayer strengthens equipment, is connected with adaptive-filtering equipment, for receiving adaptive-filtering image, based on goal-selling
Gray threshold scope determines whether each pixel in the adaptive-filtering image belongs to object pixel, will be described adaptive
All object pixels composition preliminary aim region in filtering image, improve the institute in preliminary region in the adaptive-filtering image
The gray value grade for having pixel improves image to obtain contrast, strengthens the highlights region in the contrast raising image, together
When reduce the contrast and improve dark portion region in image, to obtain targets improvement image, the targets improvement image is entered
Row picture smooth treatment strengthens image to obtain multilayer;
Video capture device, for the sheet to be tested that is transmitted in real time on sheet conveyer belt is carried out video data acquiring with
Obtain each target image frame in prefixed time interval;Definition detection device, it is connected, is used for the video capture device
Each target image frame is received, and determines the definition of each target image frame;Image compares equipment, respectively with the flash memory
Equipment connects with the definition detection device, for obtaining the clear of each target image frame and each target image frame
Degree, one or more target images that definition is less than or equal to default clarity threshold are removed from each target image frame
Frame is to obtain each alternate image frame;
Image output device, equipment connects compared with the flash memory device and described image respectively, each standby for receiving
With picture frame, and remove signal to noise ratio from each alternate image frame and be less than or equal to the one or more standby of default fractional threshold
Picture frame carries out image averaging processing to obtain each final image frame, to each final image frame and located with obtaining and exporting
Manage image;Region division equipment, it is connected with multilayer enhancing equipment, for receiving multilayer enhancing image, multilayer enhancing image is drawn
Be divided into multiple fringe regions, include a boundary curve in each fringe region, boundary curve by multiple pixel values for 0 it is black
Level pixel forms;
Equipment for area detection equipment, it is connected with the region division equipment, for black for each in multilayer enhancing image
Level pixel, the fringe region where it is determined, measures it to the distance of boundary curve core-wire using as boundary curve distance,
The black level pixel that boundary curve distance is more than or equal to pre-programmed curve distance replaces with white level pixel, by boundary curve distance
Black level pixel less than pre-programmed curve distance is left black level pixel;Image output device, by each black level pixel quilt
Multilayer enhancing image after processing is as black level processing image output;
Wherein, the pattern recognition device is connected with described image output equipment and the flash memory device respectively, for connecing
Black level processing image is received, is handled based on the predetermined pattern gray threshold scope from the black level in image and is identified and split
Go out pattern subgraph, and the real-time pattern on sheet to be tested is determined based on the pattern subgraph.
More specifically, in the sheet pattern recogni-tion system in real time:The flash memory device, which is used to prestore, to be preset clearly
Clear degree threshold value and default fractional threshold.
More specifically, in the sheet pattern recogni-tion system in real time:Boundary curve core-wire is on the curve of corresponding edge
The curve curve that each central point is formed in the radial direction.
More specifically, in the sheet pattern recogni-tion system in real time:The flash memory device is additionally operable to store predetermined pattern
Gray threshold scope;Wherein, the predetermined pattern gray threshold scope includes pattern gray scale upper limit threshold and pattern gray scale lower limit
Threshold value.
Brief description of the drawings
Embodiment of the present invention is described below with reference to accompanying drawing, wherein:
Fig. 1 is the block diagram of the real-time sheet pattern recogni-tion system according to embodiment of the present invention.
Reference:1 sheet conveyer belt;2 pattern recognition devices;3 pattern match equipment;4 Realtime Alerts equipment
Embodiment
The embodiment of the real-time sheet pattern recogni-tion system of the present invention is described in detail below with reference to accompanying drawings.
One of sheet, the textile on bed, also referred to as coverlet, quilt cover.It is typically good using wealthy soft warmth retention property
Fabric.Sheet is used as the broad fabrics of bed surface paving decorations.Using pure cotton or scribbled as raw material, using plain weave, twill, change group
Knit or figured texture weave, in the only width of the Looms system of knitting.There are complete white, plain color, colour bar, color lattice, stamp, jacquard weave, etching, embroidery etc..
Flower pattern is attractive in appearance, and cloth cover is smooth, and feel is very refreshing, strong durable, is to have practicality and ornamental textile concurrently.
Currently, that sheet is misprinted be present, but lack corresponding wrong version sheet detection pattern.In order to overcome it is above-mentioned not
Foot, it is as follows that the present invention has built a kind of sheet pattern recogni-tion system, specific embodiment in real time.
Fig. 1 is the block diagram of real-time sheet pattern recogni-tion system according to embodiment of the present invention, the system
System includes sheet conveyer belt, pattern recognition device, pattern match equipment and Realtime Alerts equipment.
Wherein, the sheet conveyer belt is used to transmit sheet to be tested in real time, and the pattern recognition device is treated for identification
The real-time pattern on sheet is examined, the pattern match equipment is connected with the pattern recognition device, described real-time for receiving
Pattern, and by the real-time pattern compared with preset reference pattern, the Realtime Alerts equipment is set with the pattern match
Standby connection, corresponding alarm strategy is determined for the output based on the pattern match equipment.
Then, continue that the concrete structure of the real-time sheet pattern recogni-tion system of the present invention is further detailed.
The sheet pattern recogni-tion system in real time can also include:
Flash memory device, for prestoring preset reference pattern;
Wherein, the flash memory device is connected with the pattern match equipment.
In the sheet pattern recogni-tion system in real time:
The pattern recognition device, the pattern match equipment and the flash memory device are all disposed within sheet conveyer belt side
Control cabinet in;
Wherein, in the pattern match equipment, when the real-time pattern and preset reference pattern match degree are more than or equal in advance
If during matching threshold, sending pattern match pass signal, preset when the real-time pattern is less than with preset reference pattern match degree
During matching threshold, pattern match failure signal is sent;
Wherein, the Realtime Alerts equipment performs corresponding alarm behaviour when receiving the pattern match failure signal
Make.
The sheet pattern recogni-tion system in real time can also include:
Contour detecting equipment, is connected with image output device, for receiving processed image, and judges the processed figure
Objective contour as in;
Shape judges equipment, is connected with the contour detecting equipment, for receiving the target wheel in the processed image
Exterior feature, and judge contour shape corresponding to the objective contour in the processed image;
Stencil-chosen equipment, judge that equipment is connected with the shape, for determining medium filtering based on the contour shape
Template;
The degree of correlation judges equipment, for receiving processed image, and judges in the processed image between pixel two-by-two
Degree of correlation grade;
Adaptive-filtering equipment, judge that equipment is connected with the stencil-chosen equipment and the degree of correlation respectively, by described in
Each pixel in processed image as object pixel, based on the medium filtering template determine using the object pixel as
The medium filtering window at center, the degree of correlation grade in the medium filtering window with the object pixel is more than or equal to default
Filtered pixel value of the average of the pixel value of all pixels of grade threshold as the object pixel;The adaptive filter
Filtered pixel value output adaptive filtering image of the wave device based on all object pixels.
The sheet pattern recogni-tion system in real time can also include:
Multilayer strengthens equipment, is connected with adaptive-filtering equipment, for receiving adaptive-filtering image, based on goal-selling
Gray threshold scope determines whether each pixel in the adaptive-filtering image belongs to object pixel, will be described adaptive
All object pixels composition preliminary aim region in filtering image, improve the institute in preliminary region in the adaptive-filtering image
The gray value grade for having pixel improves image to obtain contrast, strengthens the highlights region in the contrast raising image, together
When reduce the contrast and improve dark portion region in image, to obtain targets improvement image, the targets improvement image is entered
Row picture smooth treatment strengthens image to obtain multilayer;
Video capture device, for the sheet to be tested that is transmitted in real time on sheet conveyer belt is carried out video data acquiring with
Obtain each target image frame in prefixed time interval;
Definition detection device, it is connected with the video capture device, for receiving each target image frame, and determines every
The definition of one target image frame;
Image compares equipment, is connected respectively with the flash memory device and the definition detection device, each for obtaining
The definition of target image frame and each target image frame, removal definition is less than or equal to from each target image frame
One or more target image frames of default clarity threshold are to obtain each alternate image frame;
Image output device, equipment connects compared with the flash memory device and described image respectively, each standby for receiving
With picture frame, and remove signal to noise ratio from each alternate image frame and be less than or equal to the one or more standby of default fractional threshold
Picture frame carries out image averaging processing to obtain each final image frame, to each final image frame and located with obtaining and exporting
Manage image;
Region division equipment, it is connected with multilayer enhancing equipment, for receiving multilayer enhancing image, multilayer enhancing image is drawn
Be divided into multiple fringe regions, include a boundary curve in each fringe region, boundary curve by multiple pixel values for 0 it is black
Level pixel forms;
Equipment for area detection equipment, it is connected with the region division equipment, for black for each in multilayer enhancing image
Level pixel, the fringe region where it is determined, measures it to the distance of boundary curve core-wire using as boundary curve distance,
The black level pixel that boundary curve distance is more than or equal to pre-programmed curve distance replaces with white level pixel, by boundary curve distance
Black level pixel less than pre-programmed curve distance is left black level pixel;
Image output device, multilayer of each black level pixel after processed is strengthened into image and handles image as black level
Output;
Wherein, the pattern recognition device is connected with described image output equipment and the flash memory device respectively, for connecing
Black level processing image is received, is handled based on the predetermined pattern gray threshold scope from the black level in image and is identified and split
Go out pattern subgraph, and the real-time pattern on sheet to be tested is determined based on the pattern subgraph.
In the sheet pattern recogni-tion system in real time:
The flash memory device is used to prestore default clarity threshold and default fractional threshold.
In the sheet pattern recogni-tion system in real time:
Boundary curve core-wire is by the corresponding edge curve upper curve curve that each central point forms in the radial direction.
In the sheet pattern recogni-tion system in real time:
The flash memory device is additionally operable to store predetermined pattern gray threshold scope;
Wherein, the predetermined pattern gray threshold scope includes pattern gray scale upper limit threshold and pattern gray scale lower threshold.
In addition, image filtering, i.e., press down under conditions of image detail feature is retained as far as possible to the noise of target image
System, is indispensable operation in image preprocessing, and the quality of its treatment effect will directly influence successive image processing and divide
The validity and reliability of analysis.
Due to the imperfection of imaging system, transmission medium and recording equipment etc., digital picture is in its formation, transmission log mistake
Often polluted in journey by a variety of noises.In addition, some links in image procossing when the picture object inputted and are not so good as pre-
Also noise can be introduced when thinking in result images.These noises often show as one on image and cause the isolated of stronger visual effect
Pixel or block of pixels.Typically, noise signal it is uncorrelated to the object to be studied it occur with useless message form, upset figure
The observable information of picture.For data image signal, psophometer is either large or small extreme value, and these extreme values are acted on by plus-minus
On the true gray value of image pixel, the interference of bright, dim spot is caused to image, greatly reduces picture quality, influence image restoration,
The progress of the follow-up work such as segmentation, feature extraction, image recognition.A kind of wave filter for effectively suppressing noise is constructed to must take into consideration
Two basic problems:The noise in target and background can effectively be removed;Meanwhile can protect well image object shape,
Size and specific geometry and topological features.
One kind in conventional image filtering pattern is nonlinear filter, it is, in general, that when signal spectrum and noise frequency
Such as the noise as caused by mission nonlinear or non-gaussian be present and make an uproar when composing aliasing or when containing nonadditivity noise in signal
Sound etc.), traditional linear filter technology, such as Fourier conversion, while noise is filtered out, always blurred picture is thin in some way
Section (such as edge) and then the extraction property reduction for causing the positioning precision and feature as linear character.And nonlinear filter is
Based on a kind of Nonlinear Mapping relation to input signal, often a certain specific noise approx can be mapped as zero and retained
Signal wants feature, thus it can overcome the weak point of linear filter to a certain extent.
Using the real-time sheet pattern recogni-tion system of the present invention, for the sheet None- identified of wrong patterns in the prior art
Technical problem, by existing sheet manufacture system, add customization pattern recognition device be used for identify it is to be tested
Real-time pattern on sheet, it is used for using pattern match equipment by the real-time pattern compared with preset reference pattern, with
Determine sheet current in sheet manufacture system whether pattern printing mistake, so as to solve above-mentioned technical problem.
It is understood that although the present invention is disclosed as above with preferred embodiment, but above-described embodiment and it is not used to
Limit the present invention.For any those skilled in the art, without departing from the scope of the technical proposal of the invention,
Many possible changes and modifications are all made to technical solution of the present invention using the technology contents of the disclosure above, or are revised as
With the equivalent embodiment of change.Therefore, every content without departing from technical solution of the present invention, the technical spirit pair according to the present invention
Any simple modifications, equivalents, and modifications made for any of the above embodiments, still fall within the scope of technical solution of the present invention protection
It is interior.
Claims (8)
1. a kind of sheet pattern recogni-tion system in real time, including sheet conveyer belt, pattern recognition device, pattern match equipment and in real time
Warning device, the sheet conveyer belt are used to transmit sheet to be tested in real time, and the pattern recognition device is to be tested for identifying
Real-time pattern on sheet, the pattern match equipment is connected with the pattern recognition device, for receiving the real-time pattern,
And by the real-time pattern compared with preset reference pattern, the Realtime Alerts equipment connects with the pattern match equipment
Connect, corresponding alarm strategy is determined for the output based on the pattern match equipment.
2. sheet pattern recogni-tion system in real time as claimed in claim 1, it is characterised in that also include:
Flash memory device, for prestoring preset reference pattern;
Wherein, the flash memory device is connected with the pattern match equipment.
3. sheet pattern recogni-tion system in real time as claimed in claim 2, it is characterised in that:
The pattern recognition device, the pattern match equipment and the flash memory device are all disposed within the control of sheet conveyer belt side
In case processed;
Wherein, in the pattern match equipment, when the real-time pattern and preset reference pattern match degree are more than or equal to default
During with threshold value, pattern match pass signal is sent, when the real-time pattern and preset reference pattern match degree are less than preset matching
During threshold value, pattern match failure signal is sent;
Wherein, the Realtime Alerts equipment performs corresponding alarm operation when receiving the pattern match failure signal.
4. sheet pattern recogni-tion system in real time as claimed in claim 3, it is characterised in that also include:
Contour detecting equipment, is connected with image output device, for receiving processed image, and judges in the processed image
Objective contour;
Shape judges equipment, is connected with the contour detecting equipment, for receiving the objective contour in the processed image, and
Judge contour shape corresponding to the objective contour in the processed image;
Stencil-chosen equipment, judge that equipment is connected with the shape, for determining medium filtering template based on the contour shape;
The degree of correlation judges equipment, for receiving processed image, and judges in the processed image phase between pixel two-by-two
Pass degree grade;
Adaptive-filtering equipment, judge that equipment is connected with the stencil-chosen equipment and the degree of correlation respectively, located described
Each pixel in image is managed as object pixel, is determined based on the medium filtering template centered on the object pixel
Medium filtering window, the degree of correlation grade in the medium filtering window with the object pixel is more than or equal to predetermined level
Filtered pixel value of the average of the pixel value of all pixels of threshold value as the object pixel;The adaptive-filtering is set
The standby filtered pixel value output adaptive filtering image based on all object pixels.
5. sheet pattern recogni-tion system in real time as claimed in claim 4, it is characterised in that also include:
Multilayer strengthens equipment, is connected with adaptive-filtering equipment, for receiving adaptive-filtering image, based on goal-selling gray scale
Threshold range determines whether each pixel in the adaptive-filtering image belongs to object pixel, by the adaptive-filtering
All object pixels composition preliminary aim region in image, improve all pictures in preliminary region in the adaptive-filtering image
The gray value grade of element improves image to obtain contrast, strengthens the highlights region in the contrast raising image, subtracts simultaneously
Few contrast improves the dark portion region in image, and to obtain targets improvement image, figure is carried out to the targets improvement image
As smoothing processing with obtain multilayer enhancing image;
Video capture device, for carrying out video data acquiring to the sheet to be tested transmitted in real time on sheet conveyer belt to obtain
Each target image frame in prefixed time interval;
Definition detection device, it is connected with the video capture device, for receiving each target image frame, and determines each
The definition of target image frame;
Image compares equipment, is connected respectively with the flash memory device and the definition detection device, for obtaining each target
The definition of picture frame and each target image frame, definition is removed from each target image frame and is less than or equal to preset
One or more target image frames of clarity threshold are to obtain each alternate image frame;
Image output device, equipment connects compared with the flash memory device and described image respectively, for receiving each standby figure
One or more alternate images of the signal to noise ratio less than or equal to default fractional threshold are removed as frame, and from each alternate image frame
Frame carries out image averaging processing to obtain and export processed figure to obtain each final image frame, to each final image frame
Picture;
Region division equipment, it is connected with multilayer enhancing equipment, for receiving multilayer enhancing image, multilayer enhancing image is divided into
Multiple fringe regions, include a boundary curve in each fringe region, boundary curve by multiple pixel values for 0 black level
Pixel forms;
Equipment for area detection equipment, it is connected with the region division equipment, for strengthening each black level in image for multilayer
Pixel, the fringe region where it is determined, it is measured to the distance of boundary curve core-wire using as boundary curve distance, by side
The black level pixel that edge curve distance is more than or equal to pre-programmed curve distance replaces with white level pixel, and boundary curve distance is less than
The black level pixel of pre-programmed curve distance is left black level pixel;
Image output device, it is defeated as black level processing image that multilayer of each black level pixel after processed is strengthened into image
Go out;
Wherein, the pattern recognition device is connected with described image output equipment and the flash memory device respectively, black for receiving
Level handles image, is handled based on the predetermined pattern gray threshold scope from the black level and is identified in image and be partitioned into figure
Case subgraph, and determine based on the pattern subgraph real-time pattern on sheet to be tested.
6. sheet pattern recogni-tion system in real time as claimed in claim 5, it is characterised in that:
The flash memory device is used to prestore default clarity threshold and default fractional threshold.
7. sheet pattern recogni-tion system in real time as claimed in claim 6, it is characterised in that:
Boundary curve core-wire is by the corresponding edge curve upper curve curve that each central point forms in the radial direction.
8. the real-time sheet pattern recogni-tion system as described in claim 5-7 is any, it is characterised in that:
The flash memory device is additionally operable to store predetermined pattern gray threshold scope;
Wherein, the predetermined pattern gray threshold scope includes pattern gray scale upper limit threshold and pattern gray scale lower threshold.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710668493.XA CN107392905B (en) | 2017-08-08 | 2017-08-08 | Real-time pattern identifying system |
CN201711377279.5A CN108053399B (en) | 2017-08-08 | 2017-08-08 | Real-time pattern recognition system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710668493.XA CN107392905B (en) | 2017-08-08 | 2017-08-08 | Real-time pattern identifying system |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711377279.5A Division CN108053399B (en) | 2017-08-08 | 2017-08-08 | Real-time pattern recognition system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107392905A true CN107392905A (en) | 2017-11-24 |
CN107392905B CN107392905B (en) | 2018-06-12 |
Family
ID=60345063
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710668493.XA Active CN107392905B (en) | 2017-08-08 | 2017-08-08 | Real-time pattern identifying system |
CN201711377279.5A Active CN108053399B (en) | 2017-08-08 | 2017-08-08 | Real-time pattern recognition system |
Family Applications After (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711377279.5A Active CN108053399B (en) | 2017-08-08 | 2017-08-08 | Real-time pattern recognition system |
Country Status (1)
Country | Link |
---|---|
CN (2) | CN107392905B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109011654A (en) * | 2018-09-05 | 2018-12-18 | 浙江大丰实业股份有限公司 | Peoperty walking identification mechanism |
CN109238238A (en) * | 2018-09-05 | 2019-01-18 | 浙江大丰实业股份有限公司 | Stage performer automatic station-keeping system |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090148033A1 (en) * | 1990-11-16 | 2009-06-11 | David Alumot | Optical inspection apparatus for substrate defect detection |
CN104616003A (en) * | 2015-03-06 | 2015-05-13 | 侯苏 | System for identifying type of foreign matters on power line |
CN105352480A (en) * | 2015-04-01 | 2016-02-24 | 郑海雁 | Electric transmission line foreign matter kind detection method |
CN106192352A (en) * | 2016-07-14 | 2016-12-07 | 上海和鹰机电科技股份有限公司 | A kind of stamp method of cutting out of intelligence cutter |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6332044B1 (en) * | 1997-01-21 | 2001-12-18 | Xerox Corporation | System and method for enhancement of image contour fidelity |
CN102262093A (en) * | 2010-05-24 | 2011-11-30 | 张爱明 | Machine vision-based on-line detection method for printing machine |
CN103018254A (en) * | 2012-12-04 | 2013-04-03 | 东南大学 | Automatic detection device based on image identification technology |
CN104537390B (en) * | 2015-01-15 | 2017-07-07 | 刘宁 | A kind of intelligent fabric tissue type detection method |
CN105181708A (en) * | 2015-08-27 | 2015-12-23 | 李红军 | Qualification detection platform of sewing needles in batches |
CN106162076A (en) * | 2016-06-27 | 2016-11-23 | 刘杰杰 | Big data image gray processing processing means |
-
2017
- 2017-08-08 CN CN201710668493.XA patent/CN107392905B/en active Active
- 2017-08-08 CN CN201711377279.5A patent/CN108053399B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090148033A1 (en) * | 1990-11-16 | 2009-06-11 | David Alumot | Optical inspection apparatus for substrate defect detection |
CN104616003A (en) * | 2015-03-06 | 2015-05-13 | 侯苏 | System for identifying type of foreign matters on power line |
CN105352480A (en) * | 2015-04-01 | 2016-02-24 | 郑海雁 | Electric transmission line foreign matter kind detection method |
CN106192352A (en) * | 2016-07-14 | 2016-12-07 | 上海和鹰机电科技股份有限公司 | A kind of stamp method of cutting out of intelligence cutter |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109011654A (en) * | 2018-09-05 | 2018-12-18 | 浙江大丰实业股份有限公司 | Peoperty walking identification mechanism |
CN109238238A (en) * | 2018-09-05 | 2019-01-18 | 浙江大丰实业股份有限公司 | Stage performer automatic station-keeping system |
CN109011654B (en) * | 2018-09-05 | 2020-05-29 | 浙江大丰实业股份有限公司 | Stage property walking identification mechanism |
CN109238238B (en) * | 2018-09-05 | 2020-12-11 | 浙江大丰实业股份有限公司 | Automatic positioning system for stage performer |
Also Published As
Publication number | Publication date |
---|---|
CN108053399A (en) | 2018-05-18 |
CN107392905B (en) | 2018-06-12 |
CN108053399B (en) | 2020-02-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kang et al. | Automatic recognition of fabric weave patterns by digital image analysis | |
CN114820627B (en) | Textile quality detection method based on optical means | |
CN107392905B (en) | Real-time pattern identifying system | |
CN109211918B (en) | Fabric bow weft detection method based on weft trend | |
CN116843688A (en) | Visual detection method for quality of textile | |
US6987867B1 (en) | Process for evaluating data from textile fabrics | |
CN109594319B (en) | Intelligent detection device and method for warp and weft density of fabric | |
CN115861261A (en) | Defect identification method for medical non-woven fabric | |
CN116805312B (en) | Knitted fabric quality detection method based on image processing | |
CN107184031A (en) | sheet | |
CN107643297B (en) | A kind of method of real-time monitoring quality of textile products | |
CN106408533B (en) | A kind of card image extracting method and system | |
CN107841816A (en) | A kind of only paper web manufacturing process of big jacquard weave | |
CN107374209A (en) | The shared sleeping apparatus that slide fastener automatically controls | |
CN116894840B (en) | Spinning proofing machine product quality detection method and system | |
CN208023291U (en) | A kind of perching machine detecting device of clothes processing | |
CN103938343B (en) | A kind ofly design the method that coloured silk knits yarn twist and fabric compactness | |
TW381136B (en) | Inspecting apparatus | |
CN109448010A (en) | A kind of grain pattern automatic generation method that continues in all directions based on content characteristic | |
CN112281462A (en) | Shirt fabric typesetting and cutting method | |
CN108221339A (en) | A kind of perching machine detecting device of clothes processing | |
Das et al. | Defect detection of jute fabric using image processing | |
CN109410202B (en) | Method for evaluating digital printing definition of silk fabric | |
US2089070A (en) | Blanket fabric | |
CN112070723A (en) | Automatic identification method for density of plain woven fabric |
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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Luo Xiaoming Inventor before: Bo Fenglei |
|
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20180510 Address after: 528000 Foshan, Guangdong Province, Nanhai District, Guangdong Town, Luo Shan, Guangdong new light source industrial base of the core area D District 11, three floor. Applicant after: Guangdong Chuangda Automation Equipment Co Ltd Address before: 361008 108, room 22, two day watching day, software park, Xiamen, Fujian. Applicant before: Bo Fenglei |
|
GR01 | Patent grant | ||
GR01 | Patent grant |