CN107945165B - Textile flaw detection method based on peak value coverage values and areal calculation - Google Patents
Textile flaw detection method based on peak value coverage values and areal calculation Download PDFInfo
- Publication number
- CN107945165B CN107945165B CN201711188164.1A CN201711188164A CN107945165B CN 107945165 B CN107945165 B CN 107945165B CN 201711188164 A CN201711188164 A CN 201711188164A CN 107945165 B CN107945165 B CN 107945165B
- Authority
- CN
- China
- Prior art keywords
- map grid
- value
- peak value
- index
- calculates
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/20081—Training; Learning
-
- 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)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The present invention provides a kind of textile flaw detection method based on peak value coverage values and areal calculation, this method analyzes the Pixel of Digital Image grayscale information based on textile surface flat under lighting source, divide the image into the grid not overlapped, the area of each grid is calculated, according to area distribution automatic positioning textile surface flaw.The present invention is especially suitable for the textile surface flaws being automatically identified in the textile flat surfaces gray-scale image acquired under steady illumination light source.
Description
Technical field
The present invention relates to textile Defect Detection technical fields, more particularly to one kind based on peak value coverage values and area
The textile flaw detection method of calculation.
Background technique
Traditional textile flaw manual identified accuracy rate only have 60-75% (referring to document: K.Srinivasan,
P.H.Dastoor, P.Radhakrishnaiah, et al..FDAS:a knowledge-based framework for
Analysis of defects in woven textiles tructures, J.Text.Inst.83 (1992) 431-
448.), the method for machine automatic identification textile flaw has practical application request.The digital picture of flat textile surface is adopted
Sample (hereinafter referred to as textile images) belongs to 2 d texture, and 2 d texture has been demonstrated can be according to 17 kinds of wallpaper group (wallpaper
Group the pattern arrangement method) defined generates (referring to document: H.Y.T.Ngan, G.K.H.Pang, N.H.C.Yung.Motif-
Based defect detection for patterned fabric, Pattern Recognit. (2008) 1878-
1894.), for generate the pattern of 2 d texture be known as map grid (1attice) (referring to: https: //en.wikipedia.org/
Wiki/Wallpaper_group), pattern is known as motif inside map grid.Most textile flaw automatic detection methods can only be located
Manage wallpaper group in p1 type textile images (referring to document: H.Y.T.Ngan, G.K.H.Pang,
N.H.C.Yung.Automated fabric defect detection-A review, Image and Vision
Computing 29 (7) (2011) 442-458.), only a few methods can handle other than p1 type textile images (referring to
Document: H.Y.T.Ngan, G.K.H.Pang, N.H.C.Yung.Motif-based defect detection for
Patterned fabric, Pattern Recognit. (2008) 1878-1894.), such as the benchmark based on wavelet pretreatment
Image difference method (wavelet-pre-processed golden image subtraction, hereinafter referred to as WGIS) (ginseng
See document: H.Y.T.Ngan, G.K.H.Pang, N.H.C.Yung, et al., Wavelet based methods on
Patterned fabric defect detection, Pattern Recognit.38 (4) (2005) 559-576.), symbiosis
Matrix method is (referring to document: C.J.Kuo, T.Su, Gray relational analysis for recognizing
Fabric defects, Text.Res.J.73 (5) (2003) 461-465.), cloth forest belt method (Bollinger bands, with
Lower abbreviation BB) (referring to document: H.Y.T.Ngan, G.K.H.Pang, Novel method for patterned fabric
Inspection using bollinger bands, Opt.Eng.45 (8) (2006) 087202-1-087202-15.), rule
Band method (regular bands, hereinafter referred to as RB) is (referring to document: H.Y.T.Ngan, G.K.H.Pang, Regularity
Analysis for patterned texture inspection, IEEE Trans.Autom.Sci.Eng.6 (1) (2009)
131-144.), Elo appraisal procedure (Elo rating method, hereinafter referred to as ER) (referring to document: C.S.C.Tsang,
H.Y.T.Ngan, G.K.H.Pang, Fabric inspection based on the Elo rating method,
Pattern Recognit.51 (2016) 378-394.) etc..Although these methods can handle the textile images other than p1,
But their calculation method is built upon on the pattern (hereinafter referred to as map grid) of the similar lattice based on artificial selection more.Such as
WGIS requires the size and texture of artificial selection map grid, and BB, RB and ER require the size of Manual definition's map grid.These priori knowledges
The degree of automation of machine recognition textile flaw is reduced to a certain extent.
Summary of the invention
The technical problems to be solved by the present invention are: in order to improve the degree of automation of machine recognition textile flaw, this
Invention provides a kind of textile flaw detection method based on peak value coverage values and areal calculation, and main includes designing one kind automatically
Segmentation textile images are the method for map grid and design a kind of flaw recognition methods based on map grid and map grid areal calculation.
It is cheer and bright to make to state, existing centralized definition partial symbols according to the present invention and concept.
Indicate Positive Integer Set.
Indicate the integer set including zero.
Indicate the positive real number set including zero.
Indicate the real number set including zero.
Indicate that element number isReal vector.
Indicate plural number set.
Indicate that element number isComplex vector.
T representing matrix or vector transposition.
Indicate the real matrix of n × m size, wherein
Indicate k × n × m size real matrix, wherein
IfAndThen AI:The i-th row of representing matrix A, A:, jThe jth of representing matrix A arranges.
IfAndThen AL::Indicate the l layer matrix that size is n × m in A,
AL, i:Indicate the i-th row of the l layer matrix that size is n × m in A, AL:, jIndicate the of the l layer matrix that size is n × m in A
J column.
Indicate ratioSmall maximum integer, such as
{aiIndicate by index i determine by element aiThe set or multiset of composition.
| S | indicate the element number in set S, if S is vector, | S | indicate element number contained by vector, | S | it is known as
Vector length.
Avg (S) or mean (S): the mean value of set of computations or multiset S, the element of S are real number.
Std (S): the standard deviation of set of computations or multiset S, the element of S are real number.
Med (S): the median of set of computations or multiset S, the element of S are real number.
Mod (S): the mode of multiset S is calculated, the element of S is real number.
Set or the element maximum value of multiset S, such as max (I are found out in max (S) expressionc) represent IcThe maximum of middle pixel
Gray value.
Max (s " condition) indicates to find out qualifiedMaximum value.
Set or the element minimum value of multiset S, such as min (I are found out in min (S) expressionc) represent IcThe minimum of middle pixel
Gray value.
args∈S(C (s)) indicates the value of s when condition C is true.
arg maxsF (s) is indicated in the value range of the domain internal variable s of function f, so that function f (s) takes maximum
The s of value.
arg minsF (s) is indicated in the value range of the domain internal variable s of function f, so that function f (s) takes minimum
The s of value.
arg maxsf1(s), f2(s) it indicates in function f1And f2Domain intersection internal variable s value range in so that
Function f1(s) and f2(s) s being maximized.
argF (s) indicates the domain internal variable s in function f (s)1And s2Value range in so that function f
(s) s being maximized1And s2。
arg modi({ai) indicate corresponding multiset { aiMode mod ({ ai) index.
dimx(I) total line number of two-dimensional image I, dim are indicatedy(I) total columns of I is indicated.
Image origin: the position that pixel column column index starts in image, the hypothesis on location is in the image upper left corner and value is
(1,1).
I (x, y) indicates the pixel value with ranks index (x, y) in two-dimensional image I.Line indexBy image original
Point starts to be incremented by downwards with 1 for step-length, 1≤x≤dimx(I);Column indexBy image origin with 1 for step-length to the right
It is incremented by, 1≤y≤dimy(I)。
Image boundary: there is line index dimx(I) row and column indexes dimy(I) column.
Textile images cartoon ingredient Ic: to the textile images I of a width gray processing, using opposite total variance
(relative total variation, hereinafter referred to as RTV) model (Xu L., Yan Q., Xia Y., Jia J.,
Structure Extraction from Texture via Relative Total Variation, ACM
31 (6) 2012Article 139 of Transactions on Graphics) to generate the edge clear based on I but texture fuzzy
Gray level image Ic, IcReferred to as textile images cartoon ingredient.
Binaryzation textile images Itc: use Bradley method (Bradley D., Roth G., Adaptive
12 (2) 200713- of Thresholding Using the Integral Image, Journal of Graphics Tools
21) binaryzation IcAnd noise reduction, the two-value obtained after two value object of suppressing exception area are carried out according to Ic of the step 1.1 to binaryzation
Image, wherein foreground pixel value is 1, background pixel value 0.
Two value object mass centers: ItcIn the included foreground pixel image line index of two value objects average value and column index it is flat
Mean value.
It indicates to be linked in sequence by operand and generates vector, such as scalar v1=1 and vector v2=[2 3]T, For scalar s1=8, s2=1, s3=5,For vector v1
=[2 3]T, v2=[5 0 4]T,
It indicates by element vector multiplication, such as vector v1=[5 0.9 4]T, v2=[1 0 1]T, then
Wherein
Map grid indexes (ir, ic): after image segmentation is nonoverlapping map grid, according to the arrangement position of map grid in the picture,
Each map grid has unique map grid line index irWith unique map grid column index ic, in image upper left corner map grid index for (1,
1) it is, (1,2) close to the right side map grid index of the map grid, is (2,1) close to the downside map grid index that index is (1,1) map grid,
The rest may be inferred.Indicate that map grid index is (ir, ic) map grid, wherein L1,1Referred to as first map grid.
Map grid pixel index: map grid is made of pixel, therefore map grid is a sub-picture, image origin and pixel column column index
Definition be also applied for map grid pixel index.
Map grid size: number of lines of pixels and columns contained by map grid.
Map grid texture type: the type of map grid texture is generated based on map grid segmentation and textile gray level image.
Map grid matrix: the matrix as unit of map grid, i.e., each element is a map grid in matrix.
Eigenmatrix: using feature extracting method calculate map grid matrix in each element feature vector, with feature to
Amount is that unit forms matrix, i.e., each element is the feature vector of a map grid in matrix, and element index is right with it in matrix
Index of the map grid answered in map grid matrix is identical.
Training sample set: N sub-picture I1, I2...INResolution ratio it is identical, all images according to map grid segmentation generate figure
It is flawless image that check, which manages type and its all identical training sample of quantity, and training sample set only includes flawless image, and flawless
Image is also only present in training sample concentration.
Test sample collection: similar with training sample set, all image resolution ratios are identical, and the figure generated according to map grid segmentation
Check manages type and its quantity is all identical, consistent described in arrangement mode and the training sample set definition of each image map grid,
Unlike training sample set, the image that test sample is concentrated contains position at random and texture is not belonging to map grid texture type
Irregular area, the region are defined as flaw.The image that test sample is concentrated is known as test sample, and test sample is to have flaw figure
Picture, what test sample concentration included is all to have flaw image.
Feature extracting method title ordered set T: feature extracting method f is indicated1, f2...f|T|Name set, such as T
={ HOG, LBP }, then | T |=2 and f1Indicate HOG method, f2Indicate LBP method.
On the basis of being as defined above, the technical solution adopted by the present invention to solve the technical problems is: one kind being based on peak
It is worth the textile flaw detection method of coverage values and areal calculation, including two stages: training stage and test phase.Training rank
Section calculates map grid segmentation according to a series of training sample set being made of indefectible textile images (hereinafter referred to as flawless image)
And flaw identifies required parameter;The parameter that test phase is obtained according to the training stage carries out map grid point to a secondary textile images
It cuts and judges whether map grid includes flaw, finally label contains map grid defective.Training stage includes three steps: step 1 figure
Lattice partitioning parameters calculate, the segmentation of step 2 training sample map grid, the flawless area interval computation of step 3.Test phase includes two steps
It is rapid: the segmentation of step 4 test sample map grid, the identification of step 5 flaw.Inventive method assumes that textile images have a characteristic that
Relative to the row and column of textile images, map grid is transversely arranged according to the direction of image line, and by the direction longitudinal arrangement of column;In Ic
In, part map grid have geometry and and background pixel there were significant differences in gray scale.
Step 1 calculates map grid partitioning parameters.The step includes three sub-steps, i.e. step 1.1 background pixel projects, step
1.2 calculate peak value coverage values and step 1.3 calculating map grid ideal dimensions.
Step 1.1 calculates the cartoon ingredient of textile gray level image I according to RTV model, using Bradley method binaryzation
Cartoon ingredient is tracked by morphological erosion and expansive working to binaryzation cartoon ingredient noise reduction using Mo0re-Neighbor
Algorithm obtains binaryzation IcIn two value objects, calculate binaryzation cartoon ingredient in two-value object area, delete the area area Bu
Between ((1- α) ma, (1+ α) ma) in two value object (wherein maFor two-value object area median,And 0 < α <
1) binaryzation textile images I is obtainedtc.Calculate ItcMiddle each row and column background pixel number arranges every row background picture by line index ascending order
Prime number obtains the projection of background pixel rowThe projection of background pixel row is obtained by column index ascending order arrangement each column background pixel number
Step 1.2 calculates peak value coverage values.Calculate the projection of textile gray level image I background pixel rowPeak value, by peak
Value by itsIn index ascending order arrange to obtain peak value sequenceFor prIn
A peak valueIt calculates according to the following formulaCoverage values
Similarly, it calculatesPeak value sequenceIt calculatesWherein1≤ipc;Meter
Calculate prThe ordered set of middle peak value coverage values Descending arranges middle element by size;ForIn first of element Meet in peak value sequence'sOrdered set is known as l grades of peak values
Element in l grades of peak values by itsIn index ascending order arrangement;For l grades of peak values, it is previous with it to calculate each peak value
Peak value existsIn index difference absolute value, calculate the median of these absolute valuesAnd its frequency of occurrence Composition set Composition set Middle element value composition setSimilarly, according toIt calculates and meets with pc'sOrdered set " the l ' grade peak value "
Front and back element in the l ' grade peak value is calculated to existIn index difference absolute value and its medianGo out occurrence with median
Number Form multiset Form multiset Middle element value composition set
Step 1.3 calculates map grid ideal dimensions.To the I of training sample set1, I2...INIn i-th
Training sample Ii, I is calculated according to step 1.2i'sWith It calculatesValue setIiIdeal line numberIt is defined by the formula.
Wherein, δ is Dirac delta function (Dirac delta function).I.e. m isIn an element,
IiIdeal columnsCalculate withIt is similar, i.e., the item with subscript r in above formula is replaced with into the correspondence with subscript c
, such asIt replaces withMap grid ideal dimensions are defined asMedianWithMedian
I of the step 2 to training sample set1, I2...INCarry out map grid segmentation.For i-th of training sample Ii, the step packet
Include three sub-steps: the projection of step 2.1 background pixel, step 2.2 calculates initial segmentation position and step 2.3 calculates final segmentation
Position.
The calculating process of step 2.1 includes step 1.1 and step 1.2.
Step 2.2 calculates initial segmentation position.For i-th of training sample Ii, it is calculated according to step 2.1WithIt calculates defined in step 1.2WithAndWithRoot
It is calculated according to step 1.3WithIt is calculated as followsThere is most frequentGrade peak value
Similarly, it can calculateThere is most frequentGrade peak value, i.e., replace with the item in above formula with subscript r
Respective items with subscript c, such asIt replaces withAssuming that theThere are a string of continuous peak values in grade peak value
And each peak value and previous peak value existIn index difference absolute value it is closeThen this string peak value existsIn index definition
For row initial segmentation position Sr, this string peak value is theIndex in grade peak value meets following formula definition.
Wherein dj+kIndicate theGrade peak value in index be j+k and j+k-1 two peak values itsThe difference of middle index
Absolute value,And 0 < β < 1 be parameter.Column initial segmentation position ScIt is relevantWithDefinition withWithIt is similar,
The item with subscript r in above formula is replaced with into the respective items with subscript c, such asIt replaces withAnd dj+kIs indicated at this timeGrade peak value in index be j+k and j+k-1 two peak values itsThe difference of middle index
Absolute value.Parameter beta pairWithCalculating it is general.
Step 2.3 calculates final division position, at once division positionWith column split positionFor i-th of trained sample
This Ii,WithInitial value be respectively step 2.2 calculate IiRow initial segmentation position SrWith column initial segmentation position Sc。
It willIn element by size ascending order arrange, find out least member thereinAnd greatest memberIt is calculated as follows four
Predicted positionWith
I is obtained by step 1.1iBinaryzation textile imagesAnd it is updated by following three kinds of situationsWith
The first situation: ifIt calculatesMiddle line index x meetsTwo
The average value of value object mass centerAndMiddle line index x meetsTwo value object mass centers it is flat
Mean valueThenIt is added toNew element and becomeIt is recalculated according to definitionWith
Second situation: ifIt calculatesMiddle line index x meetsTwo
The average value of value object mass centerThenIt is added toNew element and becomeIt is recalculated according to definition
The third situation: ifThen terminate calculating.
Repeat the calculating of above-mentioned three kinds of situations untilWithUntil being no longer changed.Similarly, it presses
Three kinds of situations are stated to updateWith
The first situation: ifIt calculatesMiddle line index x meets
Two value object mass centers average valueAndMiddle line index x meetsTwo value object mass centers
Average valueThenIt is added toNew element and becomeIt is counted again according to definition
It calculatesWith
Second situation: ifIt calculatesMiddle line index x meetsTwo value object mass centers average valueThenIt is added toNew element and becomeIt is recalculated according to definition
The third situation: ifThen terminate calculating.
Repeat the calculating of above-mentioned three kinds of situations untilWithUntil being no longer changed, at this timeMeter
Terminate.Calculating it is similarIt willIn element by size ascending order arrange, find out least member thereinMost
Big elementAccording toWithThree kinds of situations being related to are updated to updateWithI.e. by three kinds of situations
The superscript r of middle items replaces with c, such asIt replaces withThe x in inequality and formula is replaced with into y simultaneously, such asIt replaces withAccording toWithThree kinds of situations being related to are updated to updateWith
Superscript r every in three kinds of situations is replaced with into c, such asIt replaces withSimultaneously by the x in inequality and formula
Y is replaced with, such asIt replaces withAccording toWithThe row and column index separately included, by IiBy these indexes
The row and column at place is split, and dividing resulting rectangular area is map grid, is defined as follows.
WhereinWith Indicate the index of map grid arrangement position in I.
The flawless area interval computation of step 3.If setting training sample I binaryzation cartoon ingredient ItcBackground pixel value be 0, then
Map gridArea aI, jIt is defined asThe number of included foreground pixel, wherein
AndThat is:
For training sample set I1, I2...IN, map grid segmentation is carried out to each image and calculates map grid area, gained area
Minimum value and maximum value be denoted as a respectively0(i) and a1(i), then the lower bound a in flawless area section0With upper bound a1Determined by following formula
Justice.
WhereinWithRespectively indicate a0(i) and a1(i) linear order collection (linearly ordered set), wherein i
=1,2...N, i.e.,WithIn element according to value size ascending order arrangement, l andRespectivelyWithElement index,
The segmentation of step 4 test sample map grid.To a secondary given test sample, the meter of step 2.1 to step 2.3 is repeated
It calculates, distinguishes the training sample involved in being to calculate and replace with test sample, finally obtain the row division position of test sampleWith column split positionAnd according toWithTest sample is divided into map grid.
The identification of step 5 flaw.Test sample I secondary for one, carries out map grid segmentation and calculates map grid area, calculate map grid face
Product histogramT is enabled to indicateHorizontal axis scale, i.e. the value range of map grid area, h (t) indicatesLongitudinal axis scale, i.e.,
A in II, jFor t'sNumber, calculate separately notch value t ' and cliff of displacement value t " according to the following formula.
If t ' exists, t ' is set as a0, otherwise see that t " whether there is, set t " then if it exists as a0.For I, any map grid face
Product is less than a0Or it is greater than a1Map grid be labeled as flaw.
The beneficial effects of the present invention are: a kind of textile flaw based on peak value coverage values and areal calculation provided by the invention
Defect detection method, this method are analyzed the Pixel of Digital Image grayscale information based on textile surface flat under lighting source, will be schemed
As being divided into the grid not overlapped, the area of each grid is calculated, according to area distribution automatic positioning textile surface flaw.
The present invention is especially suitable for be automatically identified in the textile flat surfaces gray-scale image acquired under steady illumination light source
Textile surface flaw.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is main-process stream schematic diagram of the invention;
Fig. 2 is the background pixel projection flow diagram of step 1.1 of the invention;
Fig. 3 is the flow diagram of the calculating column initial segmentation position of step 1.2 of the invention;
Fig. 4 is that the calculating of step 1.4 of the invention arranges the flow diagram of final division position;
Fig. 5 is step 1.1 background pixel projection algorithm flow diagram of the invention;
Fig. 6 is that step 1.2 of the invention calculates peak value coverage values algorithm flow chart;
Fig. 7 is that step 1.3 of the invention calculates map grid ideal dimensions algorithm flow chart;
Fig. 8 is that step 2.1 of the invention calculates background pixel projection and coverage values algorithm flow chart;
Fig. 9 is that step 2.2 of the invention calculates initial segmentation position algorithm flow chart;
Figure 10 is that step 2.3 of the invention calculates final division position algorithm flow chart;
Figure 11 is step 4 test sample map grid flow chart of segmentation algorithm of the invention;
Figure 12 is step 5 flaw recognizer flow chart of the invention.
Specific embodiment
Presently in connection with attached drawing, the present invention is described in detail.This figure is simplified schematic diagram, is only illustrated in a schematic way
Basic structure of the invention, therefore it only shows the composition relevant to the invention.
The embodiment of calculation method of the present invention is completed by writing computer program, and specific implementation process is related to customized
Algorithm is described by pseudocode.Program input is the textile images of gray processing, and program output is the map grid set containing flaw.This hair
Bright embodiment includes five steps, first three step is the training stage, and latter two steps are test phase.
The training stage the following steps are included:
Step 1: parameter needed for map grid is divided is calculated according to a series of flawless images, to determine map grid ideal dimensions;
Step 2: according to the map grid ideal dimensions obtained in step 1, map grid segmentation being carried out to training sample set, is trained
Sample map grid;
Step 3: the map grid area for the training sample map grid that map grid segmentation generates in step 2 is calculated, to obtain trained sample
This concentrates the flawless area section of flawless image;
The test phase the following steps are included:
Step 4: the segmentation of test sample map grid, to a secondary given test sample, according to the method for step 2 to test sample
Map grid segmentation is carried out, test sample map grid is obtained;
Step 5: calculating the map grid area of test sample according to the method for step 3, and by calculated result and flawless image
Map grid area is compared, to identify map grid defective.
The sequence and logical relation of this method are detailed in Fig. 1.
Explanation is unfolded to this five steps individually below.
1, the training stage
Training stage calculates parameter needed for map grid is divided according to a series of flawless textile gray level images first, then to nothing
Flaw image carries out map grid segmentation and calculates parameter needed for test phase.Training stage includes three steps: step 1: calculating map grid
Partitioning parameters, step 2: the segmentation of training sample map grid, the flawless area interval computation of step 3.Map grid segmentation side proposed by the present invention
The parameter that method is obtained according to step 1.3 divides map grid by step 2.1 to step 2.3.
For step 1 for calculating map grid partitioning parameters, which specifically includes three sub-steps, i.e. step 1.1: background pixel
Projection;Step 1.2: calculating peak value coverage values;Step 1.3: calculating map grid ideal dimensions.
Step 1.1, visible Fig. 2 of detailed process.For a width textile gray level image I, according to RTV model calculate cartoon at
Divide Ic, I is obtained by Bradley methodcBianry image, Fig. 2 illustrates in binarization and is calculated by Bradley method
Pixel threshold schematic diagram, i.e. IcMesh figure gray plane, this method to each pixel calculate a local threshold, according to
Pixel local threshold binaryzation I obtains the I of binaryzationc.The I of binaryzationcNoise reduction is realized by morphological erosion and expansive working,
Then using Moore-Neighbor track algorithm, (Moore-Neighbor tracing algorithm, comes from document Jia
L., Liang J., Fabric defect inspection based on isotropic lattice segmentation,
Journal of the Franklin Institute 354 (13) (2017) 5694-5738) obtain binaryzation I after noise reductioncIn
Two value objects, i.e., 8 connection foreground pixel regions, calculate two value objects area, i.e. the foreground pixel number of two value objects.
It is distributed according to two-value object area, obtains area median ma, by all areas not in section ((1- α) ma, (1+ α) ma)
Two interior value objects are from binaryzation IcMiddle deletion obtains binaryzation textile images Itc,For the parameter being manually specified, take
Value range is 0≤α≤1, and this method takes α=0.6.Calculate ItcIn every row background pixel number and arrange to obtain by line index ascending order
The projection of background pixel rowCalculate ItcThe background pixel number of middle each column simultaneously is arranged to obtain background pixel column throwing by column index ascending order
ShadowOne-dimensional waveform in Fig. 2 isWithStep 1 algorithm flow is detailed in Fig. 5.
Step 1.2 part process is detailed in Fig. 3, and for two-dimentional textile gray level image, initial segmentation position includes that row is initial
Division position and column initial segmentation position, Fig. 3 show only the conceptional flowchart for calculating column initial segmentation position, row initial segmentation
The calculating process of position is similar therewith.According toCalculate peak value (i.e.From increasing to subtracting, or from the value for reducing to increasing, as Fig. 2 is one-dimensional
The dark dot of waveform, and pressThe index ascending order of middle peak value arranges to obtain peak value sequenceFor pr
InA peak valueIt calculatesCoverage valuesIt is defined as follows.
It is conceptive,It indicates in prIn fromTwo sides start to prIt moves, is greater than not encountering end to endPeak
The number of passed through peak value before being worth, as shown in Fig. 3, the peak value with identical coverage values is indicated with the triangle of same color.
Similarly, it calculatesPeak value sequenceAnd it calculatesWherein
For prOr pc, coverage values often take limited integer value, p as shown in Figure 3cValue is 0,1,2,4,11 and 27.
Coverage values are arranged in descending order, obtain coverage values value setSuch as attached drawing 3According to
First of coverage values valueCoverage values in pcPeak valueReferred to as l grades of peak values, l grades of peaks
Value by itsIn index ascending order arrangement.Adjacent peak in l grades of peak values is calculated to existIn (the i.e. each peak index spacing d
Value exists with previous peak valueIn index difference absolute value), the median of computation index spacingAnd its frequency of occurrenceForIn each element, all exist it is adjacent index spacing median and its frequency of occurrence, these medians
Value then forms setSimilarly, it calculatesWithStep 1.2 algorithm flow is detailed in Fig. 6.
Step 1.3 calculates map grid ideal dimensions.The training sample I concentrated according to training sample1, I2...IN, i-th can be calculated
It is a Sample Ii'sWithThen IiIdeal line numberIt is defined as follows.
Wherein δ is Dirac delta function (Dirac delta function).The ideal columns of IDefinition withClass
Seemingly, only need byItem with subscript r in definition replaces with the respective items with subscript c, such asReplacement
ForMap grid ideal dimensions are defined asMedianWithMedian
Step 1.3 algorithm flow is detailed in Fig. 7.
The calculating process of step 2.1 includes step 1.1 and step 1.2.Step 2.1 algorithm flow is detailed in Fig. 8.
Step 2.2 calculates initial segmentation position, and process is detailed in Fig. 3.For i-th of training sample Ii, calculated according to step 2.1
It arrivesWithIt calculates defined in step 1.2WithAnd
WithIt is calculated according to step 1.3WithIt is calculated as followsThere is most frequentGrade peak value
WhereinWithIt respectively indicates and is projected according to background pixel rowPeak value sequence counted
The coverage values value set of calculation, l grades of peak values index spacing medians, l grade peak values index spacing median frequency of occurrence with
All rank peak values (The corresponding peak value of all elements) median value sequence.Calculating process withIt is similar, only
Needing willItem with subscript r in definition replaces with the respective items with subscript c, such asIt replaces with
Assuming that theThere is a string of continuous peak values and each peak value in grade peak value to exist with previous peak valueIn index difference
Absolute value is closeThen this string peak value existsIn index be defined as row initial segmentation position Sr, this string peak value is theGrade peak
Index in value meets following formula definition.
Wherein dj+kIndicate theGrade peak value in index be j+k and j+k-1 two peak values itsThe difference of middle index it is exhausted
To value,And 0 < β < 1 be parameter, this method takes β=0.1.Column initial segmentation position ScIt is relevantWithDefinition
WithWithIt is similar, i.e., the item with subscript r in above formula is replaced with into the respective items with subscript c, such asIt replaces withAnd dj+kIs indicated at this timeGrade peak value in index be j+k and j+k-1 two peak values its
?The absolute value of the difference of middle index.Parameter beta pairWithCalculating it is general.Step 2.2 algorithm flow is detailed in Fig. 9.
Step 2.3 process is detailed in Fig. 4, which, which shows only, calculates column split positionConceptional flowchart, row framing bits
It setsCalculating process it is similar therewith.Due to the interference of the factors such as flaw and noise, usual SrAnd ScCover only image portion subregion
Domain (S at oncerMinimum and maximum value between image line index account for 80% or less or S of all image line indexcMinimum with
Image column index between maximum value accounts for the 80% of all image column indexes, does not either way include 80%), so needing to expand
Open up SrAnd Sc.For i-th of training sample Ii,And ScInitial value be respectively step 2.2 calculate IiSrAnd Sc.It willIn
Element by size ascending order arrange, find out least member thereinAnd greatest memberWithDeviate S for step size computation1
And S∞And close to the row predicted position of image boundary, that is, four predicted positions are calculated as followsWith
I is obtained by step 1.1iBinaryzation textile imagesAnd it is updated by following three kinds of situationsWith
The first situation: ifIt calculatesMiddle column index y meetsTwo
The average value of value object mass centerAndMiddle column index y meetsTwo value object mass centers it is flat
Mean valueThenIt is added toNew element and becomeIt is recalculated according to definitionWith
Second situation: ifIt calculatesMiddle column index y meetsTwo
The average value of value object mass centerThenIt is added toNew element and becomeIt is recalculated according to definition
The third situation: ifThen terminate calculating.
Repeat the calculating of above-mentioned three kinds of situations untilWithUntil being no longer changed.Similarly, it presses
Three kinds of situations are stated to updateWith
The first situation: ifIt calculatesMiddle column index y meetsTwo value object mass centers average valueAndMiddle column index y meets
Two value object mass centers average valueThenIt is added toNew element and become
It is recalculated according to definitionWith
Second situation: ifIt calculatesMiddle column index y meetsTwo value object mass centers average valueThenIt is added toNew element and becomeIt is recalculated according to definition
The third situation: ifThen terminate calculating.
Repeat the calculating of above-mentioned three kinds of situations untilWithUntil being no longer changed, at this timeMeter
Terminate.Calculating it is similarIt willIn element by size ascending order arrange, find out least member thereinMost
Big elementAccording toWithThree kinds of situations being related to are updated to updateWithI.e. by three kinds of situations
The superscript c of middle items replaces with r, such asIt replaces withThe y in inequality and formula is replaced with into x simultaneously, such asIt replaces withAccording toWithThree kinds of situations being related to are updated to updateWith
Superscript c every in three kinds of situations is replaced with into r, such asIt replaces withSimultaneously by the y in inequality and formula
X is replaced with, such asIt replaces withAccording toWithThe row and column index separately included, by IiBy these indexes
The row and column at place is split, and dividing resulting rectangular area is map grid, is defined as follows.
WhereinWith Indicate the index of map grid arrangement position in I.Such as 2 lower left corner legend of attached drawing, the legend
Middle upper left corner map grid is denoted as L1,1, L1,1The adjacent map grid in right side is L1,2, L1,1The adjacent map grid in downside is L2,1, and so on.Figure
LatticeBy including in IRow, and comprisingColumn determine map grid boundary.Step 2.3 algorithm stream
Journey is detailed in Figure 10.
The flawless area interval computation of step 3.If setting training sample I binaryzation cartoon ingredient ItcBackground pixel value be 0, that
Map gridArea aI, jIt is defined asThe number of included foreground pixel, wherein
AndThat is:
The map grid area that training sample is concentrated is often similar, therefore there are the section of a flawless map grid area, this areas
Between be known as flawless area section.If the area of a map grid is not in flawless area section, which may be to have flaw figure
Lattice (map grid comprising flaw).For training sample set I1, I2...IN, map grid segmentation is carried out to each image and calculates map grid face
Product, the minimum value and maximum value of gained area are denoted as a respectively0(i) and a1(i), then the lower bound a in flawless area section0The upper bound and
a1It is defined by the formula:
WhereinWithRespectively indicate a0(i) and a1(i) linear order collection (1inearly ordered set), wherein i
=1,2...N, i.e.,WithIn element according to value size ascending order arrangement, l andRespectivelyWithElement index,
2, test phase
On the parameter basis that the training stage obtains, test phase carries out flaw inspection to the sub-picture that test sample is concentrated
It surveys and positions.Test phase includes two steps: the segmentation of step 4 test sample map grid and the identification of step 5 flaw.
The segmentation of step 4 test sample map grid.To a secondary given test sample, the meter of step 2.1 to step 2.3 is repeated
It calculates, distinguishes the training sample involved in being to calculate and replace with test sample, finally obtain the row division position of test sampleWith column split positionAnd according toWithTest sample is divided into map grid.
The identification of step 5 flaw.Test sample I secondary for one, carries out map grid segmentation and calculates map grid area, calculate map grid face
Product histogramT is enabled to indicateHorizontal axis scale, i.e. the value range of map grid area, h (t) indicatesLongitudinal axis scale, i.e.,
A in II, jFor t'sNumber, calculate separately notch value t ' and cliff of displacement value t " according to the following formula.
If t ' exists, t ' is set as a0, otherwise see that t " whether there is, set t " then if it exists as a0.For I, any map grid face
Product is less than a0Or it is greater than a1Map grid be labeled as flaw.
High efficiency of the invention experiments have shown that:
Use the industry of Hong Kong University's Electrical and Electronic engineering department automatic in the Defect Detection recruitment evaluation of the method for the present invention
Change the 56 width pixel sizes that laboratory provides as 256 × 256 24 color textile product images, these images are turned in an experiment
It is changed to 8 gray level images.These images include a kind of pattern: box-shaped image.Box-shaped image includes 30 indefectible and 26 width
There is flaw image.Box-shaped image includes 5 kinds of flaw types: the broken ends of fractured bone (broken end), hole (hole), reticulate pattern (netting
Multiple), cord (thick bar) and stria (thin bar), see Table 1 for details for the particular number of every kind of flaw type
First row.All flaw images have the flaw reference map (ground-truth image) of same size, and flaw reference map is 2
It is worth image, wherein 1 indicates flaw, 0 indicates background.Algorithm for comparing includes WGIS, BB, RB and ER, the ginseng of these algorithms
Number setting and document (Jia L., Liang J., Fabric defect inspection based on isotropic
Lattice segmentation, Journal of the Franklin Institute 354 (13) (2017) 5694-
5738) identical.
Index for assessment includes true positives (true positive, hereinafter referred to as TP), false positive
(positiverate, hereinafter referred to as FPR), true positive rate (truepositiverate, hereinafter referred to as TPR), false positive rate
(positiverate, hereinafter referred to as FPR), positive predictive value (positivepredictivevalue, hereinafter referred to as PPV) and
Negative predictive value negativepredictivevalue, hereinafter referred to as NPV).TPR, which is measured, indicates flaw in flaw reference map
Pixel is correctly demarcated as the ratio of flaw by algorithm, and FPR, which is measured, indicates the pixel of background by algorithmic error mark in flaw reference map
It is set to the ratio of flaw, the flaw proportion in the flaw of PPV measure algorithm output in flaw reference map, NPV measure algorithm
Background proportion in the background of output in flaw reference map.For TPR, PPV and NPV, index value is the bigger the better, for
FPR is then the smaller the better.Related mathematical definition can document (M.K.Ng, H.Y.T.Ngan, X.Yuan, et al.,
Patterned fabric inspection and visualization by the method of image
Decomposition, IEEETrans.Autom.Sci.Eng.11 (3) (2014) 943-947) in find.The method of the present invention,
The index calculating method and document (Jia L., Liang J., Fabric defect inspection of WGIS, BB, RB and ER
Based on isotropic lattice segmentation, Journal ofthe Franklin Institute 354
(13) (2017) 5694-5738) it is identical.Experimental Hardware platform is the CoreTMi7-3610QM of Intel containing processor 230-GHz
With the laptop of 8.00GB memory, software is Windows 10 and Maltab8.4.
Table 1 enumerates box-shaped image Defect Detection as a result, wherein marking every row index value of flaw type is corresponding method
To the index average value of all test sample operation results of the flaw type.According to 1 overview of table, one column, the method for the present invention has most
Excellent global ACC (0.54) and PPV (0.67), NPV (0.99) are very close to optimal value (1.00).For the broken ends of fractured bone and hole type
Flaw, the TPR of the method for the present invention is optimal.TPR (0.28) relatively optimal value of the method for the present invention about reticulate pattern
(0.31).The method of the present invention is time figure of merit about the TPR of cord, and the TPR of stria is lower.The method of the present invention about the broken ends of fractured bone,
The FPR of cord and stria is optimal or suboptimum, and the FPR of hole and reticulate pattern is larger.To sum up, the method for the present invention has reached complete
Office optimal T PR and PPV, overall situation NPV is very close to optimal value, while the method for the present invention is especially suitable for detection box-shaped image
The flaw of broken ends of fractured bone type.
1 box-shaped image Defect Detection result of table
Taking the above-mentioned ideal embodiment according to the present invention as inspiration, through the above description, relevant staff
Various changes and amendments can be carried out without departing from the scope of the present invention completely.The technical scope of this invention is not
The content being confined on specification, it is necessary to which the technical scope thereof is determined according to the scope of the claim.
Claims (5)
1. a kind of textile flaw detection method based on peak value coverage values and areal calculation, it is characterised in that: including training rank
Section and two stages of test phase;A series of training stage, according to indefectible textile gray level images, hereinafter referred to as flawless figure
Picture calculates parameter needed for map grid is divided, and then carries out map grid segmentation to flawless image and calculates needed for the identification of test phase flaw
Parameter;Test phase, the parameter obtained according to the training stage carry out map grid segmentation to a secondary textile images and judge that map grid is
No includes flaw, and finally label contains map grid defective;
The training stage the following steps are included:
Step 1: parameter needed for map grid is divided is calculated according to a series of flawless images, to determine map grid ideal dimensions;
Step 2: according to the map grid ideal dimensions obtained in step 1, map grid segmentation being carried out to training sample set, obtains training sample
Map grid;
Step 3: the map grid area for the training sample map grid that map grid segmentation generates in step 2 is calculated, to obtain training sample set
In flawless image flawless area section;
The test phase the following steps are included:
Step 4: the segmentation of test sample map grid carries out a secondary given test sample according to the method for step 2 to test sample
Map grid segmentation, obtains test sample map grid;
Step 5: the map grid area of test sample is calculated according to the method for step 3, and by the map grid of calculated result and flawless image
Area is compared, to identify map grid defective;
Step 1 specifically includes the following steps:
Step 1.1: background pixel projection calculates the cartoon ingredient of textile gray level image I according to RTV model, using Bradley
Method binaryzation cartoon ingredient, by morphological erosion and expansive working to binaryzation cartoon ingredient noise reduction, using Moore-
Neighbor track algorithm obtains binaryzation IcIn two value objects, calculate binaryzation cartoon ingredient in two-value object area, delete
Except area is not in section ((1- α) ma,(1+α)·ma) in two value objects obtain binaryzation textile images Itc, wherein maFor
Two-value object area median,And 0 < α < 1;Calculate ItcMiddle each row and column background pixel number is arranged by line index ascending order
Every row background pixel number obtains the projection of background pixel rowBackground pixel is obtained by column index ascending order arrangement each column background pixel number
Row projection
Step 1.2: calculating peak value coverage values, calculate the background pixel row projection of textile gray level image IPeak value, by peak value
It is projected by it in background pixel rowIn index ascending order arrange to obtain peak value sequenceFor prInA peak valueIt calculates according to the following formulaCoverage values
It is projected with background pixel rowCoverage valuesCalculation method is identical, and the item of subscript r in above formula is replaced with tool
There are the respective items of subscript c, calculatesPeak value sequenceIt calculatesWherein1
≤ipc;Calculate prThe ordered set of middle peak value coverage valuesDescending arranges middle element by size;ForInIt is a
Element Meet in peak value sequence'sOrdered set is known asGrade peak valueTheGrade peak value in element by itsIn index ascending order arrangement;ForGrade peak
Value, calculates each peak value and its previous peak value existsIn index difference absolute value, calculate the median of these absolute values
And its frequency of occurrence Composition setComposition setMiddle element value composition collection
It closesSimilarly, according toWithIt calculates and meets'sOrdered set " theGrade peak value "Front and back element in the l ' grade peak value is calculated to existIn index difference absolute value and wherein position
ValueWith median frequency of occurrence Form multisetForm multisetMiddle element value composition set
Step 1.3: map grid ideal dimensions are calculated, to the I of training sample set1,I2…INIn i-th
Training sample Ii, I is calculated according to step 1.2i'spr,pc,With It calculatesValue setIiIdeal line numberIt is defined by the formula:
Wherein, δ is Dirac delta function (Dirac delta function),IiIdeal columnsCalculate withIt is similar, i.e., the item with subscript r in above formula is replaced with into the respective items with subscript c;Map grid ideal dimensions are fixed
Justice isMedianWithMedian
2. the textile flaw detection method based on peak value coverage values and areal calculation, feature exist as described in claim 1
In: step 2 specifically includes the following steps:
Step 2.1: background pixel projection, calculating process include step 1.1 and step 1.2;
Step 2.2: initial segmentation position is calculated, for i-th of training sample Ii, it is calculated according to step 2.1With
It calculates defined in step 1.2WithAndWithAccording to
What step 1.3 was calculatedWithIt is calculated as followsThere is most frequentGrade peak value
Similarly, it can calculateThere is most frequentGrade peak value replaces with the item in above formula with subscript r under having
The respective items of footmark c;
Assuming that theThere is a string of continuous peak values and each peak value in grade peak value to exist with previous peak valueIn index difference it is absolute
Value is closeThen this string peak value existsIn index be defined as row initial segmentation position Sr, this string peak value is theIn grade peak value
Index to meet following formula fixed:
Wherein dj+kIndicate theGrade peak value in index be j+k and j+k-1 two peak values itsThe difference of middle index it is absolute
Value,And 0 < β < 1 is parameter;Column initial segmentation position ScIt is relevantWithDefinition withWithIt is similar, i.e., it will be upper
Item with subscript r in formula replaces with the respective items with subscript c, and dj+kIs indicated at this timeIn grade peak value
Index be j+k and j+k-1 two peak values itsThe absolute value of the difference of middle index;
Step 2.3: calculating final division position, at once division positionWith column split positionFor i-th of training sample Ii,WithInitial value be respectively step 2.2 calculate IiRow initial segmentation position SrWith column initial segmentation position Sc;It will
In element by size ascending order arrange, find out least member thereinAnd greatest memberFour predictions are calculated as follows
PositionWith
According toWithThe row and column index separately included, by IiIt is split by the row and column where these indexes, segmentation gained
Rectangular area be map grid, be defined as follows:
Wherein, With Indicate the index of map grid arrangement position in I.
3. the textile flaw detection method based on peak value coverage values and areal calculation, feature exist as claimed in claim 2
In: the flawless area interval computation of step 3 the following steps are included:
If training sample I binaryzation cartoon ingredient ItcBackground pixel value be 0, then map gridArea ai,jIt is defined as
The number of included foreground pixel, wherein ir, AndThat is:
For training sample set I1,I2…IN, map grid segmentation is carried out to each image and calculates map grid area, gained area is most
Small value and maximum value are denoted as a respectively0(i) and a1(i), then the lower bound a in flawless area section0With upper bound a1It is defined by the formula:
WhereinWithRespectively indicate a0(i) and a1(i) linear order collection (linearly ordered set), wherein i=1,
2 ... N, i.e.,WithIn element according to value size ascending order arrangement, l andRespectivelyWithElement index,
4. the textile flaw detection method based on peak value coverage values and areal calculation, feature exist as claimed in claim 3
In: the segmentation of step 4 test sample map grid specifically includes: to a secondary given test sample, repeating step 2.1 to step 2.3
It calculates, distinguishes the training sample involved in being to calculate and replace with test sample, finally obtain the row framing bits of test sample
It setsWith column split positionAnd according toWithTest sample is divided into map grid.
5. the textile flaw detection method based on peak value coverage values and areal calculation, feature exist as claimed in claim 4
In: the identification of step 5 flaw specifically includes: test sample I secondary for one carries out map grid segmentation and calculates map grid area, calculate figure
Lattice area histogramT is enabled to indicateHorizontal axis scale, i.e. the value range of map grid area, h (t) indicatesThe longitudinal axis carve
It spends, i.e. a in Ii,jFor t'sNumber, calculate separately notch value t ' and cliff of displacement value t " according to the following formula:
If t ' exists, t ' is set as a0, otherwise see that t " whether there is, set t " then if it exists as a0;For I, any map grid area is small
In a0Or it is greater than a1Map grid be labeled as flaw.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711188164.1A CN107945165B (en) | 2017-11-24 | 2017-11-24 | Textile flaw detection method based on peak value coverage values and areal calculation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711188164.1A CN107945165B (en) | 2017-11-24 | 2017-11-24 | Textile flaw detection method based on peak value coverage values and areal calculation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107945165A CN107945165A (en) | 2018-04-20 |
CN107945165B true CN107945165B (en) | 2019-10-11 |
Family
ID=61948547
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711188164.1A Active CN107945165B (en) | 2017-11-24 | 2017-11-24 | Textile flaw detection method based on peak value coverage values and areal calculation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107945165B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101419706A (en) * | 2008-12-11 | 2009-04-29 | 天津工业大学 | Jersey wear flokkit and balling up grading method based on image analysis |
CN102930531A (en) * | 2012-09-28 | 2013-02-13 | 中国科学院自动化研究所 | Detection method for repetition structure of building surface image |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106770323B (en) * | 2016-12-15 | 2019-05-28 | 常州大学 | The textile flaw detection method filtered based on hierarchical clustering and Gabor |
CN107274385A (en) * | 2017-05-18 | 2017-10-20 | 常州大学 | Textile flaw detection method based on class grid pattern and its Gabor characteristic |
CN107248152A (en) * | 2017-05-18 | 2017-10-13 | 常州大学 | Textile flaw detection method based on class grid pattern and its area features |
-
2017
- 2017-11-24 CN CN201711188164.1A patent/CN107945165B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101419706A (en) * | 2008-12-11 | 2009-04-29 | 天津工业大学 | Jersey wear flokkit and balling up grading method based on image analysis |
CN102930531A (en) * | 2012-09-28 | 2013-02-13 | 中国科学院自动化研究所 | Detection method for repetition structure of building surface image |
Also Published As
Publication number | Publication date |
---|---|
CN107945165A (en) | 2018-04-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106770323B (en) | The textile flaw detection method filtered based on hierarchical clustering and Gabor | |
Ng et al. | Patterned fabric inspection and visualization by the method of image decomposition | |
Cousty et al. | Hierarchical segmentations with graphs: quasi-flat zones, minimum spanning trees, and saliency maps | |
CN107274385A (en) | Textile flaw detection method based on class grid pattern and its Gabor characteristic | |
CN107248152A (en) | Textile flaw detection method based on class grid pattern and its area features | |
CN107895371A (en) | Textile flaw detection method based on peak value coverage values and Gabor characteristic | |
CN110245593A (en) | A kind of images of gestures extraction method of key frame based on image similarity | |
US20130257888A1 (en) | Method and apparatus for displaying a simulated application of at least one coating to a digital image | |
CN107369131A (en) | Conspicuousness detection method, device, storage medium and the processor of image | |
CN105260995A (en) | Image repairing and denoising method and system | |
CN111862027B (en) | Textile flaw detection method based on low-rank sparse matrix decomposition | |
Sossa-Azuela et al. | Computing the Euler number of a binary image based on a vertex codification | |
CN107945164B (en) | Textile flaw detection method based on peak threshold, rotational alignment and composite character | |
CN107977961B (en) | Textile flaw detection method based on peak value coverage values and composite character | |
Sai Hareesh et al. | Exemplar-based color image inpainting: a fractional gradient function approach | |
CN113744350B (en) | Cabinet structure identification method, device, equipment and medium based on single image | |
CN107945165B (en) | Textile flaw detection method based on peak value coverage values and areal calculation | |
CN109507193A (en) | A kind of fabric defects detection method based on local contrast enhancing and binary pattern | |
Mohanty et al. | Detection and classification of fabric defects in textile using image mining and association rule miner | |
CN107967680B (en) | Textile flaw detection method based on peak threshold and composite character | |
CN113724223B (en) | YOLOv3 data set production method and system based on optical microscope | |
Jiang et al. | Automatic identification of jacquard warp-knitted fabric patterns based on the wavelet transform | |
Liu et al. | Double sparse low rank decomposition for irregular printed fabric defect detection | |
Bragantini et al. | Large-Scale Multi-Hypotheses Cell Tracking Using Ultrametric Contours Maps | |
CN102842129B (en) | Non-standard template image matching method based on tree decomposition |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |