CN116612110A - Intelligent quality assessment method for gradual change printing and dyeing effect - Google Patents
Intelligent quality assessment method for gradual change printing and dyeing effect Download PDFInfo
- Publication number
- CN116612110A CN116612110A CN202310861609.7A CN202310861609A CN116612110A CN 116612110 A CN116612110 A CN 116612110A CN 202310861609 A CN202310861609 A CN 202310861609A CN 116612110 A CN116612110 A CN 116612110A
- Authority
- CN
- China
- Prior art keywords
- detected
- gradient
- region
- area
- dyeing
- 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
- 230000008859 change Effects 0.000 title claims abstract description 149
- 238000004043 dyeing Methods 0.000 title claims abstract description 84
- 230000000694 effects Effects 0.000 title claims abstract description 61
- 238000001303 quality assessment method Methods 0.000 title claims description 9
- 238000000034 method Methods 0.000 claims abstract description 38
- 239000004744 fabric Substances 0.000 claims abstract description 23
- 239000004753 textile Substances 0.000 claims abstract description 17
- 238000010606 normalization Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 16
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 239000003086 colorant Substances 0.000 description 5
- 230000007547 defect Effects 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000013441 quality evaluation Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000000007 visual effect Effects 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
The application relates to the field of image processing, in particular to a quality intelligent evaluation method for a gradient printing and dyeing effect, which comprises the steps of obtaining an HSV image of a gradient printing and dyeing textile fabric, dividing the HSV image into a plurality of areas to be detected based on tone components by utilizing an area growing algorithm, and projecting each area to be detected onto a plane formed by an H channel and an S channel to obtain the gradient path length of the area to be detected; according to the length of the gradual change path, the H channel value of each pixel point and the adjacent pixel points of the pixel points is obtained, and the color change intensity of each pixel point in the area to be detected is obtained; obtaining the gradient satisfaction degree of the region to be detected according to the probability of the color change intensity of each pixel point in the region to be detected and the distance between the adjacent pixel points with the same color change intensity as the pixel point; and evaluating the dyeing effect of the gradient dyeing textile fabric by utilizing the gradient satisfaction degree, wherein the method is intelligent, and an accurate evaluation result is obtained.
Description
Technical Field
The application relates to the field of image processing, in particular to a quality intelligent evaluation method for gradual change printing and dyeing effects.
Background
The gradual change printing and dyeing is a manually made printing and dyeing mode of immersing the fabric in the dye, so that the color can be displayed on the fabric from deep to light, or changed from one color to another color, which is also called as a process of immersing and dyeing, bleeding or gradual dyeing, the quality of the product is directly influenced by the quality of the gradual change printing and dyeing effect, the gradual change printing and dyeing effect is good, the gradual change effect of the color of the corresponding gradual change printing and dyeing product is uniform and regular, visual aesthetic feeling is given to people, and the quality of the product value is good; the gradual change printing and dyeing effect is poor, the gradual change effect of the colors of the corresponding gradual change printing and dyeing products is randomly distributed, and the product quality is poor.
Therefore, it is necessary to evaluate the quality of the gradient printing and dyeing effect of the gradient printing and dyeing product, pick out the product with poor gradient printing and dyeing effect in time, and analyze the reason to facilitate the subsequent improvement process.
The prior art utilizes the computer vision technology to perform threshold segmentation on the gradual change printing and dyeing fabric image and evaluate the gradual change effect according to the segmented image, but the method has the defect that the gradual change effect evaluation of the gradual change printing and dyeing fabric is inaccurate due to the fact that the difference between pixel points in gradual change colors is less obvious and the threshold segmentation result is affected.
Disclosure of Invention
Aiming at the problem that the gradient effect evaluation of the gradient printing and dyeing fabric is not accurate enough, the application provides a quality intelligent evaluation method for the gradient printing and dyeing effect, which comprises the following steps:
acquiring an HSV space image of the gradient printing and dyeing textile fabric;
dividing an HSV image into a plurality of areas to be detected based on component values of an H channel, and acquiring gradual change path length of each area to be detected;
according to the gradient path length of the to-be-detected area, obtaining the color change intensity of each pixel point in the to-be-detected area;
obtaining gradual change satisfaction degree of the region to be detected according to the probability of the color change intensity of each pixel point in the region to be detected and the distance between adjacent pixel points with the same color change intensity as the pixel point;
and evaluating the dyeing effect of the gradient dyeing textile fabric by utilizing the gradient satisfaction degree of the region to be detected.
The method for acquiring the gradual change satisfaction degree of the area to be detected comprises the following steps:
taking the product of the probability of occurrence of the color change intensity of each pixel point in the region to be detected and the reciprocal of the distance between adjacent pixel points with the same color change intensity as the pixel point as the gradient satisfaction degree of each pixel point of the region to be detected; and taking the average value of the gradual change satisfaction degree of all the pixel points in the region to be detected as the gradual change satisfaction degree of the region to be detected.
The method for acquiring the color change intensity of each pixel point in the region to be detected comprises the following steps:
and taking the ratio of the difference value of the H channel value of each pixel point in the region to be detected and the adjacent pixel points and the gradient path length of the region to be detected as the color change intensity of each pixel point in the region to be detected.
The method for dividing the HSV image into a plurality of areas to be detected based on the component values of the H channel by using the area growth algorithm comprises the following steps:
setting a tone component growth rule, selecting a pixel point with tone components smaller than or equal to those of a central seed point near the seed pixel point, dividing the pixel point and the central seed point into the same area, taking the pixel point as the central seed point for growth of the next area, carrying out iterative growth until the growth rule is not satisfied, obtaining a plurality of areas, and taking each area as an area to be detected.
The gradual change satisfaction degree of the area to be detected also needs to be normalized so as to be between 0 and 1.
The method for acquiring the gradual change path length of each region to be detected comprises the following steps:
and projecting each region to be detected on a plane formed by the H channel and the S channel to obtain an arc, and taking the arc length of the arc as the gradual change path length of the region to be detected.
The method for evaluating the dyeing effect of the gradient dyeing textile fabric by utilizing the gradient satisfaction degree of the region to be detected comprises the following steps:
setting a first satisfaction threshold and a second satisfaction threshold;
if the gradual change satisfaction degree of the area to be detected is larger than the first satisfaction degree threshold value, the printing and dyeing quality of the area to be detected is excellent;
if the gradual change satisfaction degree of the area to be detected is smaller than or equal to the first satisfaction degree threshold value and larger than or equal to the second satisfaction degree threshold value, the printing and dyeing quality of the area to be detected is common;
if the gradual change satisfaction degree of the area to be detected is smaller than the second satisfaction degree threshold value, the printing and dyeing quality of the area to be detected is unqualified.
The beneficial effects of the application are as follows:
the method comprises the steps of dividing an HSV image of the gradual change printing and dyeing textile fabric into a plurality of areas to be detected based on tone components by using an area growing algorithm; according to the method, the image is divided into a plurality of small areas by partitioning the image, the characteristics of the gradual change areas are identified in the small areas, the integral calculation of the image is avoided, and the calculated amount is reduced; according to the H channel value of each pixel point and the adjacent pixel points in the region to be detected, calculating the color change intensity of the pixel points in the region to be detected; the gradual change effect is a regular change, in a color space, the gradual change color effect is shown to change from one color position to another color position, other pixel points are uniformly distributed between the two color positions, and the slight change accumulation among the pixel points forms the gradual change effect, so that the change degree of the H channel value can be calculated by combining the difference of the H channel values of the pixel points at different positions and the distance among the pixel points at different positions, and the change degree is used as color change intensity, so that the distribution characteristic of the pixel points in the gradual change area in the color space can be reflected; according to the method, the gradual change satisfaction degree of the region to be detected is obtained according to the probability of the color change intensity of each pixel point in the region to be detected and the distance between adjacent pixel points with the same color change intensity of the pixel point; evaluating the dyeing effect of the gradient dyeing textile fabric by utilizing the gradient satisfaction degree of the region to be detected; the closer the distance between the pixel points with the same color change intensity is, the more uniform the pixel point change in the region to be detected is indicated under the condition that the distance measurement value is certain and the probability of the color change intensity is higher, if two adjacent pixel points with the same color change intensity in the color space are mapped to the corresponding two pixel points in the image, the more random the printing and dyeing effect shape of the region to be detected is indicated and the printing and dyeing quality is poorer; if two adjacent pixel points with the same color change intensity in the color space are mapped to the corresponding two pixel points in the image, the smaller the distance between the two pixel points is, the printing and dyeing effect of the region to be detected is uniform, the printing and dyeing quality is good, so that the gradient satisfaction degree of the region to be detected is calculated, the shape characteristics of the gradient region in the image can be represented, the characteristics of the gradient region in the color space and the characteristics of the image are comprehensively analyzed, and the accuracy and objectivity of the quality evaluation result of the gradient printing and dyeing region are improved.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a schematic flow chart of a quality intelligent evaluation method for gradual printing and dyeing effect.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
An embodiment of a method for intelligently evaluating quality of a gradual change printing and dyeing effect according to the present application, as shown in fig. 1, includes:
step one: acquiring an HSV space image of the gradient printing and dyeing textile fabric; dividing an HSV image into a plurality of areas to be detected based on component values of an H channel, and acquiring gradual change path length of each area to be detected;
the method comprises the steps of obtaining an image of a gradient printing and dyeing textile fabric, preprocessing, dividing the image into areas according to an area growth algorithm method to obtain a plurality of areas to be detected, and obtaining the gradient path length of each area to be detected by utilizing projection.
The method for acquiring the HSV image of the gradient printing and dyeing textile fabric comprises the following steps of:
the application scene of the application is a textile fabric printing and dyeing detection scene, the original image to be detected is acquired through the cameras arranged on the production line, the image to be detected is denoised through median filtering, and the influence on the judgment result of the pixel points in the gradual change region of the sample points caused by noise introduced in the subsequent clustering process is avoided; and the image is formed byColor space conversion into->The color space is used for obtaining a corresponding HSV image;
the method for dividing the HSV image into a plurality of areas to be detected based on the component values of the H channel comprises the following steps:
in the present application, since the region growing algorithm is inThe color space, so that the growth should be according to +.>The variation of the hue component values (i.e. the component values of the H-channel) in the color space is grown, in particular:
first, at the center seed pointNearby selected pixel point +.>If->The hue component is [>Within the range, will->It is marked in the center seed point->Region (1)>Is->Is>For the empirical value, in the present application +.>10, the specific implementation person can adjust the device according to the textile production process requirement;
then, byFor a new seed point, iterative growth is performed until the tone component of the pixel point near the seed point is not [ -degree>Ending the growth when the growth is within the range;
finally, the region growing algorithm grows the pixel points with similar tone components near the seed points into the same region, and finally the HSV image is divided into a plurality of regions to be detected.
It should be noted that, because of the tone component between the pixel points in the gradation effectThe difference is small, so the tone component between the pixel points in the gradient color area is +.>Are all near the hue value of the center seed point, i.e. [ ->In the range, therefore, the region growing algorithm cannot stop growing from the inside of the gradual change region alone, but only at the tone component of the pixel pointThe range is greater than [ ]>And finishing region growth when the range is reached, wherein the tone component of the pixel point has obvious edges after exceeding the range, so that the region growth is finished at obvious edge positions, and the region to be detected obtained by a region growth algorithm may contain the region with the gradual change effect or the region without the gradual change effect.
The reason why the region growth is performed is that there are many gradient regions in the acquired image, and the whole image formed by printing and dyeing is relatively complex, so that the image needs to be divided into regions, and the characteristics of the gradient regions are identified in small regions, so that the problem that the calculation amount is excessively large due to the fact that the whole image is judged is avoided.
The method for acquiring the gradual change path length of each region to be detected comprises the following steps:
projecting each region to be detected on a plane formed by the H channel and the S channel to obtain an arc, and taking the arc length of the arc as the gradual change path length of the region to be detected;
at the position ofIn the color space, different tone changes are made by the tone component H, so each region to be detectedSpatially projecting to +.>Plane, i.e. projection of the area to be detected on the plane formed by the H-channel and S-channel, if the area to be detected is +.>Is the area where the gradient effect is present, then the area to be detected +.>After passing through the projection of the pixel points in the color space, this is then +.>The plane forms an arc, i.e. the hue component H of the pixel point in the area to be detected A is +.>The plane forms an arc of a circle,
representing the change of the tone component of the region to be detected, taking the arc length of the arc as the region to be detectedA gradient path in the color space, the path length being L; three channels H, S and V in the HSV color space are in an inverted cone shape, and the center of the bottom surface of the cone is a point o; for the convenience of calculation, uniformly prescribe the gradual change effect to be from +.>Position start to->Finally, the two colors can be changed with each other, the direction is not fixed, thus the color tone component +.>Is used to determine the path direction.
It should be noted that, the gradient effect is a regular change, in the color space, the gradient color effect often appears from one color position to another color position, and other pixels are uniformly distributed between the two color positions, and the subtle changes between the pixels are accumulated to form the gradient effect, so that the gradient path needs to be confirmed first to locate the color information of the gradient effect.
Step two: according to the gradient path length of the to-be-detected area, obtaining the color change intensity of each pixel point in the to-be-detected area;
the purpose of this step is to calculate the color change intensity of each pixel point in the region to be detected according to the pixel point distribution characteristics of the region to be detected in the color space.
The method for acquiring the color change intensity of each pixel point in the region to be detected comprises the following steps:
taking the ratio of the difference value of the H channel value of each pixel point in the region to be detected and the adjacent pixel points and the gradient path length of the region to be detected as the color change intensity of each pixel point in the region to be detected;
the specific formula is as follows:
in the method, in the process of the application,for the color change intensity of the ith pixel point in the area A to be detected, +.>For the H channel value of the ith pixel point in the area to be detected A,/H>Is the +.>Tone component value of pixel dot +.>，/>For the area to be detectedIs a gradual path length of (a);
in the formula, the first is selectedThe pixel is due to the fact that the hue component H of the pixel in the area A to be detected is +.>The method comprises the steps that a plane forms an arc, each point on the arc represents a tone component value, the arc is taken as a gradual change path, the arc length is taken as a gradual change path length, and adjacent pixel points of the selected pixel points are based on the tone component value on the gradual change path;
firstly, selecting the ith pixel point in a region A to be detected, and finding out the corresponding tone component value on an arcThen, based on the size of the tone component value on the gradient path, the adjacent pixel point of the ith pixel point, i.e. the (i+1) th pixel point is acquired by the following steps: selecting a neighborhood pixel with a tone component value larger than that of the ith pixel from the neighborhood pixel of the ith pixel, if one pixel exists, taking the pixel as the (i+1) th pixel, if a plurality of pixels exist, taking the pixel with the smallest tone component value as the (i+1) th pixel, namely selecting a neighborhood pixel with the smallest tone component value difference from the (i) th pixel, and then according to the difference of tone component values corresponding to the (i) th pixel and the adjacent (i+1) th pixel on a gradual change path, namely>And->Calculating the color change intensity of the ith pixel point;
the method for selecting the adjacent pixel points of the ith pixel point can select the adjacent pixel points which accord with the gradual change characteristics on the gradual change path, and calculate the color change intensity based on the pixel points which accord with the gradual change characteristics;
in the formula (i),representing the change degree of the tone component values between the ith pixel and the adjacent pixel for the difference between tone component values of the two adjacent pixels, and indicating that the greater the difference is, the greater the tone component value change between the ith pixel and the adjacent pixel is;
is the ratio of the difference between the tone component values of two adjacent pixels to the gradient path length of the gradient region, the larger the ratio is, the more pixels are represented>The larger the change of the tone component value between the pixel points adjacent to the tone component value, the larger the intensity of the gradual change effect;
by the way, byTone component of color space->Intensity of color change is performed->The calculation of (2) can clearly show the change between different colors, and simultaneously avoid the increase of calculation amount caused by the participation of three components in calculation, and the gradual change effect is characterized by tone components between pixel points>The intensity of the change is determined, and therefore, the pixel point +.>Intensity of color variation in color space +.>So as to measure the intensity characteristics of the gradual change effect; by calculating the intensity of color change of the ith pixel point in the color space>The support of the region to be detected in the color space characteristic is provided for the subsequent screening of the gradual change region through clustering.
For example, the color change intensity sequence of a certain two regions is:，from the color gamut characteristics, it can be deduced +.>The gradual effect of the zones is more uneven.
Step three: obtaining gradual change satisfaction degree of the region to be detected according to the probability of the color change intensity of each pixel point in the region to be detected and the distance between adjacent pixel points with the same color change intensity as the pixel point;
the method comprises the steps of analyzing distribution characteristics of pixel points in an image space in a region to be detected, and obtaining gradient satisfaction degree of the region to be detected as a comprehensive evaluation index of printing and dyeing effects of the region to be detected by combining the distribution characteristics of the pixel points in a color space.
The method for acquiring the gradual change satisfaction degree of the area to be detected comprises the following steps:
(1) Taking the product of the probability of occurrence of the color change intensity of each pixel point in the area to be detected and the reciprocal of the distance between adjacent pixel points with the same color change intensity as the pixel point as the gradient satisfaction degree of each pixel point in the area to be detected, wherein the specific formula is as follows:
in the formula (i),for the gradient satisfaction degree of the ith pixel point in the area A to be detected, +.>Intensity of color change for the ith pixel point in the area to be detected A +.>Probability of occurrence in the area to be detected A, < >>Is the abscissa of the position of the ith pixel,/>Is the ordinate of the position of the ith pixel,/>Is the adjacent pixel point with the same color change intensity as the ith pixel point, namely +.>The abscissa of the position of the individual pixels, < >>Is the adjacent pixel point with the same color change intensity as the ith pixel point, namely +.>Ordinate of the positions of the individual pixel points;
in the formula (i),：
region(s)I-th pixel point of (a)>Color change of (2)Intensity of transformation->Is->Is pixel dot +.>Color change intensity +.>Is +.>Occupy the area to be detected->The ratio of the number of the pixel points contained represents the color change intensity of the ith pixel point +.>In the area to be detected->The larger the value of this formula indicates a certain point +.>Color variation intensity of (2)The more the number of occurrences, the more uniform the variation in hue component values between representing pixel points; />The dyeing effect of the gradual change dyeing area is evaluated in terms of a color space, and the judgment result in the color space is more unilateral;
excellent gradual change printing and dyeing areaTwo adjacent pixels in color space with color variation intensityShould be the same, in->Two pixel points in the image should be adjacent, the gradual change effect of the representative area is even, and the printing and dyeing quality is good; but in the area of the actual fabric product in +.>Two adjacent pixels in the color space with color change intensity +.>Not necessarily the same, in->The two pixel points in the image are not necessarily adjacent, the gradual change effect of the representative area is not uniform, and the printing and dyeing quality is poor; therefore, judgment from airspace characteristics is needed, firstly, the gradient satisfaction degree of each pixel point in the area A is analyzed, and then the area +.>Is satisfied by the gradual change of (1)>The evaluation standard of the color space is linked with the spatial domain information of the image, and the gradual change printing and dyeing area is comprehensively evaluated through the linked multielement indexes;
the reciprocal distance between the pixels with the same color change intensity in the image represents the distance measurement between the pixels, and the larger the value is, the closer the distance distribution between the pixels with the same color change intensity in the image is;
weighting the distance between pixels by the probability of color change intensityThe degree of tightness between the pixel points of the image area is indicated;
in the case of a certain distance measure, the greater the probability, the description of the region to be detectedThe more uniform the pixel point changes; if the color change intensity of two adjacent pixels in the color space is +.>The same, but the too large distance of two pixel points that map to the picture, demonstrate the area prints the effect shape to be relatively random, represent the area prints the quality to be poor;
the shape and dyeing effect of the region with abnormal dyeing are randomly changed and cannot be eliminated by human factors, and the color change intensity is calculatedOnly the features in the color space are used for judging, which still causes unreasonable judging effect, so that the color change intensity of the color space is required to be +.>The method is integrated with the information of the image, so that the characteristics of the gradual change region are comprehensively represented, the diversification of the gradual change region printing and dyeing effect evaluation is achieved, and the evaluation result is more accurate and objective;
another difference between the designed gradient printing areas and the gradient areas caused by the printing defects is that the designed gradient printing areas are more regular in shape, the designed printing areas usually achieve a certain pattern design purpose through the intensity and the shape of gradient colors, and the areas with the printing defects are more random in shape, so that pixel points need to be calculatedIn area->Inner gradient satisfaction->And evaluating the shape characteristics of the gradient color region.
(2) Taking the average value of the gradual change satisfaction degree of all pixel points of the area to be detected as the gradual change satisfaction degree of the area to be detected, and normalizing:
in the method, in the process of the application,for a progressive satisfaction of the area to be detected a, +.>For the gradient satisfaction of the ith pixel point in area a, +.>For the number of pixels in area A, < +.>For normalization function, all +.>Gradient satisfaction degree of individual pixels>Mean value of (2) by->Normalization of the function allows the data to be classified as +.>And the interval is convenient for subsequent printing and dyeing quality evaluation.
The step is to calculate the regionIs satisfied by the gradual change of (1)>Make area->The color space features and the image space features are integrated, so that the evaluation indexes can be evaluated according to various features, and the problems of unsatisfactory evaluation effect and inaccurate evaluation result caused by evaluating by a single index are avoided.
Step four: and evaluating the dyeing effect of the gradient dyeing textile fabric by utilizing the gradient satisfaction degree of the region to be detected.
The purpose of this step is to determine whether the current area is a gradient color area meeting the standard by using the gradient satisfaction degree of the area to be detected.
The specific method for evaluating the dyeing effect of the gradient dyeing textile fabric by utilizing the gradient satisfaction degree of the region to be detected comprises the following steps:
according to experience settingFor the first satisfaction threshold value, the value is +.>，/>For the second satisfaction threshold value, the value is 0 +.>The method comprises the steps of carrying out a first treatment on the surface of the Will gradually change the satisfaction->Greater than or equal to->Is used as printing area with excellent quality, and the satisfaction degree is gradually changedLess than->And is greater than or equal to->Is used as a quality standard of the printing area, the degree of satisfaction is graded +.>Less thanAs a gradual change printing and dyeing area which does not meet the standard, the evaluation standard of gradual change printing and dyeing quality is obtained;
further, according to the obtained evaluation standard of the gradual change printing and dyeing quality, according to a preset machine standard, screening the fabric to be detected by controlling related machine equipment, and passing through a common printing and dyeing area meeting excellent quality and meeting design standard; and eliminating the gradual change area which does not meet the design standard.
The application considers that the pixel value difference between the pixel points of the gradient color area is smaller, and the gradient effect is the area characteristic formed by accumulating the pixel points. The designed gradient printing and dyeing pattern is more regular in shape than the printing and dyeing defect position, and gradient color impression is more full, so that the gradient region is judged from airspace characteristics and color gamut characteristics of the gradient color region;
according to the application, through the distribution characteristics of the pixel points in the color space, the color change intensity of the pixel points is obtained, the airspace characteristics on the image are synthesized, and the gradient satisfaction degree of the region is calculated; the method has the advantages that the connection among the features is introduced in the judging process, so that the judgment of the printing and dyeing quality of the region can be more intelligent, and the defect that the connection among a plurality of features cannot be expressed due to the fact that the common threshold segmentation means is usually used for judging through a single feature in a color space or an image is avoided; since the region where the gradation printing effect exists is an effect of accumulating gradation by the pixel points whose pixel value components are constantly changing slightly. Therefore, the conventional fixed threshold segmentation means cannot obtain the edge of the complete gradual change region, so that the printing quality of the region cannot be further evaluated. Therefore, the application combines the change characteristics of the pixel value components with the spatial domain characteristics of the image to analyze and evaluate so as to improve the accuracy and objectivity of the quality evaluation result of the printing and dyeing area.
The foregoing description of the preferred embodiments of the application is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the application.
Claims (7)
1. The intelligent quality assessment method for the gradual printing and dyeing effect is characterized by comprising the following steps of:
acquiring an HSV space image of the gradient printing and dyeing textile fabric;
dividing an HSV image into a plurality of areas to be detected based on component values of an H channel, and acquiring gradual change path length of each area to be detected;
according to the gradient path length of the to-be-detected area, obtaining the color change intensity of each pixel point in the to-be-detected area;
obtaining gradual change satisfaction degree of the region to be detected according to the probability of the color change intensity of each pixel point in the region to be detected and the distance between adjacent pixel points with the same color change intensity as the pixel point;
and evaluating the dyeing effect of the gradient dyeing textile fabric by utilizing the gradient satisfaction degree of the region to be detected.
2. The intelligent quality assessment method for gradient printing and dyeing effects according to claim 1, wherein the method for obtaining the gradient satisfaction degree of the region to be detected is as follows:
taking the product of the probability of occurrence of the color change intensity of each pixel point in the region to be detected and the reciprocal of the distance between adjacent pixel points with the same color change intensity as the pixel point as the gradient satisfaction degree of each pixel point of the region to be detected; and taking the average value of the gradual change satisfaction degree of all the pixel points in the region to be detected as the gradual change satisfaction degree of the region to be detected.
3. The intelligent quality assessment method for gradient printing and dyeing effects according to claim 1, wherein the method for obtaining the color change intensity of each pixel point in the region to be detected is as follows:
and taking the ratio of the difference value of the H channel value of each pixel point in the region to be detected and the adjacent pixel points and the gradient path length of the region to be detected as the color change intensity of each pixel point in the region to be detected.
4. The intelligent quality assessment method for gradient printing and dyeing effects according to claim 1, wherein the method for dividing the HSV image into a plurality of areas to be detected based on the component values of the H channel by using the area growth algorithm is as follows:
setting a tone component growth rule, selecting a pixel point with tone components smaller than or equal to those of a central seed point near the seed pixel point, dividing the pixel point and the central seed point into the same area, taking the pixel point as the central seed point for growth of the next area, carrying out iterative growth until the growth rule is not satisfied, obtaining a plurality of areas, and taking each area as an area to be detected.
5. The intelligent quality assessment method for gradient printing and dyeing effects according to claim 1, wherein the gradient satisfaction degree of the region to be detected further requires normalization operation to be between 0 and 1.
6. The intelligent quality assessment method for gradient printing and dyeing effects according to claim 1, wherein the method for obtaining the gradient path length of each region to be detected is as follows:
and projecting each region to be detected on a plane formed by the H channel and the S channel to obtain an arc, and taking the arc length of the arc as the gradual change path length of the region to be detected.
7. The intelligent quality assessment method for gradient printing and dyeing effects according to claim 1, wherein the method for assessing the printing and dyeing effects of the gradient printing and dyeing textile fabric by utilizing the gradient satisfaction degree of the region to be detected is as follows:
setting a first satisfaction threshold and a second satisfaction threshold;
if the gradual change satisfaction degree of the area to be detected is larger than the first satisfaction degree threshold value, the printing and dyeing quality of the area to be detected is excellent;
if the gradual change satisfaction degree of the area to be detected is smaller than or equal to the first satisfaction degree threshold value and larger than or equal to the second satisfaction degree threshold value, the printing and dyeing quality of the area to be detected is common;
if the gradual change satisfaction degree of the area to be detected is smaller than the second satisfaction degree threshold value, the printing and dyeing quality of the area to be detected is unqualified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310861609.7A CN116612110B (en) | 2023-07-14 | 2023-07-14 | Intelligent quality assessment method for gradual change printing and dyeing effect |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310861609.7A CN116612110B (en) | 2023-07-14 | 2023-07-14 | Intelligent quality assessment method for gradual change printing and dyeing effect |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116612110A true CN116612110A (en) | 2023-08-18 |
| CN116612110B CN116612110B (en) | 2023-10-24 |
Family
ID=87682120
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310861609.7A Active CN116612110B (en) | 2023-07-14 | 2023-07-14 | Intelligent quality assessment method for gradual change printing and dyeing effect |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116612110B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152159A (en) * | 2023-11-01 | 2023-12-01 | 江苏龙达纺织科技有限公司 | Method and system for detecting printing flaws of complex cloth |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015072542A1 (en) * | 2013-11-15 | 2015-05-21 | 富士フイルム株式会社 | Color conversion table creation device and method, program, and recording medium |
| WO2016037422A1 (en) * | 2014-09-11 | 2016-03-17 | 刘鹏 | Method for detecting change of video scene |
| JP2016048904A (en) * | 2013-11-15 | 2016-04-07 | 富士フイルム株式会社 | Color conversion table creation device and method, and program |
| CN109410202A (en) * | 2018-10-31 | 2019-03-01 | 嘉兴学院 | A kind of evaluation method of silk fabric digit printing clarity |
| US20190230295A1 (en) * | 2018-01-24 | 2019-07-25 | Motorola Mobility Llc | Digital Image Color Space Channel Blending |
| JP2019218636A (en) * | 2018-06-15 | 2019-12-26 | 株式会社ミマキエンジニアリング | Method for manufacturing dyed product, dyeing adjusting inkjet ink and dyeing adjusting inkjet ink set |
| CN115294116A (en) * | 2022-10-08 | 2022-11-04 | 南通梦洁家纺有限公司 | Method, device and system for evaluating dyeing quality of textile material based on artificial intelligence |
| CN115311286A (en) * | 2022-10-12 | 2022-11-08 | 南通佳布鲁服装有限公司 | Dyeing defect identification method for dyed textiles |
| CN115880297A (en) * | 2023-03-01 | 2023-03-31 | 深圳市富安娜艺术家居有限公司 | Quilt cover dyeing quality evaluation method based on machine vision |
| US20230186430A1 (en) * | 2021-12-13 | 2023-06-15 | Mitsubishi Electric Research Laboratories, Inc. | Systems and Methods for Image Transformation using Distance Field Procedures |
-
2023
- 2023-07-14 CN CN202310861609.7A patent/CN116612110B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015072542A1 (en) * | 2013-11-15 | 2015-05-21 | 富士フイルム株式会社 | Color conversion table creation device and method, program, and recording medium |
| JP2016048904A (en) * | 2013-11-15 | 2016-04-07 | 富士フイルム株式会社 | Color conversion table creation device and method, and program |
| WO2016037422A1 (en) * | 2014-09-11 | 2016-03-17 | 刘鹏 | Method for detecting change of video scene |
| US20190230295A1 (en) * | 2018-01-24 | 2019-07-25 | Motorola Mobility Llc | Digital Image Color Space Channel Blending |
| JP2019218636A (en) * | 2018-06-15 | 2019-12-26 | 株式会社ミマキエンジニアリング | Method for manufacturing dyed product, dyeing adjusting inkjet ink and dyeing adjusting inkjet ink set |
| CN109410202A (en) * | 2018-10-31 | 2019-03-01 | 嘉兴学院 | A kind of evaluation method of silk fabric digit printing clarity |
| US20230186430A1 (en) * | 2021-12-13 | 2023-06-15 | Mitsubishi Electric Research Laboratories, Inc. | Systems and Methods for Image Transformation using Distance Field Procedures |
| CN115294116A (en) * | 2022-10-08 | 2022-11-04 | 南通梦洁家纺有限公司 | Method, device and system for evaluating dyeing quality of textile material based on artificial intelligence |
| CN115311286A (en) * | 2022-10-12 | 2022-11-08 | 南通佳布鲁服装有限公司 | Dyeing defect identification method for dyed textiles |
| CN115880297A (en) * | 2023-03-01 | 2023-03-31 | 深圳市富安娜艺术家居有限公司 | Quilt cover dyeing quality evaluation method based on machine vision |
Non-Patent Citations (4)
| Title |
|---|
| 吴锡生;严旭东;: "基于概率分析的稀疏表示算法及在布料印染检测中的应用", 计算机应用研究, no. 07 * |
| 李媛;陈昭炯;叶东毅;: "注意力引导的交互式工笔花卉上色算法", 模式识别与人工智能, no. 07 * |
| 李永刚;殷海明;龚迅炜;乐光学;: "一种基于直方图特性的颜色量化方法", 计算机系统应用, no. 07 * |
| 赵勃;黄从玲;: "计算机印染测色配色技术的应用――评《计算机测色配色应用技术》", 染整技术, no. 09 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152159A (en) * | 2023-11-01 | 2023-12-01 | 江苏龙达纺织科技有限公司 | Method and system for detecting printing flaws of complex cloth |
| CN117152159B (en) * | 2023-11-01 | 2024-01-26 | 江苏龙达纺织科技有限公司 | Method and system for detecting printing flaws of complex cloth |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116612110B (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10565479B1 (en) | Identifying and excluding blurred areas of images of stained tissue to improve cancer scoring | |
| CN114494259B (en) | Cloth defect detection method based on artificial intelligence | |
| CN110046673A (en) | No reference tone mapping graph image quality evaluation method based on multi-feature fusion | |
| CN116612110B (en) | Intelligent quality assessment method for gradual change printing and dyeing effect | |
| CN113554629A (en) | Strip steel red rust defect detection method based on artificial intelligence | |
| CN115797342B (en) | Industrial control capacitive touch LCD display assembly defect detection method | |
| US9330337B2 (en) | Color analytics for a digital image | |
| US20180211368A1 (en) | Method and device for adjusting contrast | |
| CN116092015B (en) | Road construction state monitoring method | |
| CN115294116B (en) | Method, device and system for evaluating dyeing quality of textile material based on artificial intelligence | |
| CN115082451B (en) | Stainless steel soup ladle defect detection method based on image processing | |
| CN117152159B (en) | Method and system for detecting printing flaws of complex cloth | |
| CN116148265B (en) | Flaw analysis method and system based on synthetic leather high-quality image acquisition | |
| CN115880297B (en) | Quilt cover dyeing quality assessment method based on machine vision | |
| CN115311286A (en) | Dyeing defect identification method for dyed textiles | |
| US8913829B2 (en) | Automatic processing scale estimation for use in an image process | |
| CN115147410A (en) | Multi-color block packaging film covering defect detection method | |
| CN113744326A (en) | Fire detection method based on seed region growth rule in YCRCB color space | |
| GB2426903A (en) | Image segmentation and boundary establishment | |
| CN117372420B (en) | Textile printing quality visual detection method in dyeing and finishing process | |
| US8655099B2 (en) | Relationship maintenance in an image process | |
| CN118037732B (en) | Fuzhuan tea flowering dynamic detection method based on artificial intelligence | |
| CN111366560A (en) | Method for detecting and characterizing visual definition of printed matter | |
| CN116645368B (en) | Online visual detection method for edge curl of casting film | |
| CN117934456B (en) | Packaging box printing quality detection method based on image processing |
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 |