CN115115632B - Analysis method for accompanying phenomenon of textile seam slippage detection - Google Patents
Analysis method for accompanying phenomenon of textile seam slippage detection Download PDFInfo
- Publication number
- CN115115632B CN115115632B CN202211038607.XA CN202211038607A CN115115632B CN 115115632 B CN115115632 B CN 115115632B CN 202211038607 A CN202211038607 A CN 202211038607A CN 115115632 B CN115115632 B CN 115115632B
- Authority
- CN
- China
- Prior art keywords
- gray
- textile
- gray level
- value
- image
- 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
Images
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
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- 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
- G06T2207/20004—Adaptive image processing
-
- 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
- G06T2207/20092—Interactive image processing based on input by user
- G06T2207/20104—Interactive definition of region of interest [ROI]
-
- 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)
- Treatment Of Fiber Materials (AREA)
Abstract
The invention relates to the technical field of material testing and analysis, in particular to an analysis method of a textile seam slippage detection accompanying phenomenon, which comprises the steps of acquiring a textile image when detecting textile seam slippage by using an optical means, wherein the textile image is a visible light image, carrying out material analysis and test on the textile image, and determining an edge contour area of a textile and a suture area of the textile; and determining the accompanying phenomenon type when detecting the textile seam slippage according to the edge contour area and the sewing line area of the textile. The invention can accurately determine the accompanying phenomenon types when detecting the fabric seam slippage by acquiring the visible light images of the fabric when detecting the fabric seam slippage and analyzing and testing the material of the visible light images.
Description
Technical Field
The invention relates to the technical field of material testing and analysis, in particular to an analysis method for accompanying phenomena of textile seam slippage detection.
Background
The seam slippage refers to the ability of the yarn at the sewing position to resist external tension after the fabric is seamed, and is an important index for measuring the seam performance of the fabric. However, the following phenomena often occur in the joint slip test process, which are respectively:
1. the fabric is broken at the seam, which shows that the strength value of the fabric is not very high;
2. the stitches are broken, which shows that the seam slippage performance of the fabric is very good;
3. the fabric is broken, the tensile strength of the fabric is too low, and the seam performance of the fabric is good;
4. the yarns at the seam slip, indicating that the fabric has unacceptable seam slip performance.
In the process of performing the seam slippage test, whether the fabric is torn when the textile seam slips needs to be detected, and what kind of problem needs to be determined. For example, patent application publication No. CN 103245295B discloses a method for measuring the yarn slippage degree of a woven fabric seam based on digital image processing, but the method only uses a digital image to detect the seam slippage degree, but does not analyze the scene appearing during seam slippage. Thus, the prior art does not address the determination of the specific type of phenomena occurring during the performance of the joint slip test.
Disclosure of Invention
The invention aims to provide an analysis method for detecting accompanying phenomena of textile seam slippage, which is used for solving the problem of determining the specific phenomena in the process of performing the seam slippage test.
In order to solve the technical problem, the invention provides an analysis method for detecting accompanying phenomena of textile seam slippage, which comprises the following steps:
acquiring a textile image when detecting textile seam slippage, and preprocessing the textile image to obtain a preprocessed textile image;
constructing sliding windows in the preprocessed textile fabric image, and determining a gray level co-occurrence matrix corresponding to each sliding window according to the gray level value of pixel points in each sliding window;
determining texture information of each sliding window according to the gray level co-occurrence matrix corresponding to each sliding window, and further determining texture information difference corresponding to each sliding window according to the texture information of each sliding window;
determining a problem area in a textile image according to the texture information difference corresponding to each sliding window, and determining an edge contour area of the textile according to the problem area;
acquiring a gradient threshold range matched with the detected textile, and performing edge detection on the preprocessed textile image according to the gradient threshold range to obtain a suture region of the textile;
and determining the accompanying phenomenon type when the textile seam slippage is detected according to the edge contour area and the seam area of the textile.
Further, the acquiring a gradient threshold range matched with the detected textile includes:
acquiring a surface image of a textile fabric of the same type as the detected textile fabric, acquiring a gray level image of the surface image, and further acquiring a gray level histogram of the gray level image;
selecting the gray level with the most frequent occurrence of gray values in the gray histogram, and closing the gray values of other pixel points in the gray image to the gray level with the most frequent occurrence of gray values according to a set proportion, thereby obtaining the closed gray histogram;
acquiring gray values corresponding to different color light sources when the different color light sources irradiate the textile fabrics in the same type as the detected textile fabrics and gray value ranges of shadow parts formed when the different color light sources irradiate the textile fabrics in the same type as the detected textile fabrics;
determining a gray difference range when an edge is formed by a gray image and a shadow part according to the gray level range of the closed gray histogram and the gray value range of the formed shadow part;
determining a gray value corresponding to the optimal color light source when the optimal color light source irradiates on the textile fabrics in the same type as the detected textile fabrics according to the gray difference range, the gray level range of the closed gray histogram and the gray value corresponding to the different color light sources when the different color light sources irradiate on the textile fabrics in the same type as the detected textile fabrics, and determining the gray gradient range of the surface image when the optimal color light source irradiates on the textile fabrics in the same type as the detected textile fabrics;
determining an evaluation function value according to the gray gradient range of the surface image when the optimal color light source irradiates on the textile fabric of the same type as the detected textile fabric, the gray level range of the closed gray level histogram, the gray level range of the formed shadow part and a set proportion, continuously changing the set proportion until the determined evaluation function value is larger than a set evaluation threshold value, and taking the gray gradient range of the surface image when the optimal color light source corresponding to the optimal color light source which is larger than the set evaluation threshold value irradiates on the textile fabric of the same type as the detected textile fabric as the gradient threshold value range matched with the detected textile fabric.
Further, the calculation formula corresponding to the gray values of other pixel points in the gray image being closer to the gray level with the highest occurrence frequency of the gray values according to the set proportion is as follows:
wherein, the first and the second end of the pipe are connected with each other,
for the gray values of other pixel points in the closed gray image, the gray value of the pixel point is greater than or equal to>
Is the gray value of other pixel points in the gray image before closing, is judged>
To set a ratio>
Is the median value of the gray level histogram of the gray level image>
，/>
Is the minimum gray level of the gray histogram of the gray image, is->
The gray level in the gray histogram of the gray image isiThe frequency value of time.
Further, the determining the gray value corresponding to the illumination of the optimal color light source on the textile of the same category as the detected textile includes:
determining the minimum gray value and the maximum gray value corresponding to different color light sources according to the gray level range of the closed gray level histogram and the gray values corresponding to different color light sources when the different color light sources irradiate the textile fabrics in the same category as the detected textile fabrics;
and judging whether the minimum gray value is larger than the maximum and minimum gray difference value in the gray level range of the closed gray histogram and the maximum gray value is smaller than the minimum gray value in the gray difference range, if so, taking the corresponding color light source as the optimal color light source, thereby obtaining the gray value corresponding to the optimal color light source when the optimal color light source irradiates on the textile fabrics in the same category as the detected textile fabrics.
Further, the calculation formula for determining the maximum gray-scale value a and the maximum gray-scale value b corresponding to the light sources with different colors is as follows:
a=min(
,/>
)/>
b=max(
,/>
)
wherein, a is the minimum gray value corresponding to the light sources with different colors, and b is the maximum gray value corresponding to the light sources with different colors
, />
]For the gray level range of the closed gray histogram, in>
For the minimum gray level in the gray level range of the closed gray level histogram, conjunction>
For the maximum gray level in the gray level range of the closed gray level histogram, ->
Irradiating the same kind of textile to be detected by different color light sourcesAnd (3) the corresponding gray values of other textiles, wherein min is a minimum function and max is a maximum function.
Further, the calculation formula corresponding to the evaluation function value is determined as follows:
wherein the content of the first and second substances,
for evaluating the function value, a is the minimum gray value corresponding to the light sources with different colors, b is the maximum gray value corresponding to the light sources with different colors, [ -H [ - ]>
, />
]For the gray level range of the closed gray histogram, the value of the gray histogram is greater than or equal to>
For the minimum gray level in the gray level range of the closed gray level histogram, is selected>
For the maximum gray level in the gray level range of the closed gray level histogram, ->
To set the ratio.
Further, the determining the accompanying phenomenon category when detecting the textile seam slippage comprises:
determining the coordinates of the center point of the edge contour area and the coordinates of the center point of the sewing area according to the edge contour area and the sewing area of the textile fabric, and calculating the distance between the longitudinal coordinates of the two center points;
and judging whether the distance between the vertical coordinates of the two central points is greater than a set distance threshold value, and if so, judging that the accompanying phenomenon when the textile fabric seam slippage is detected is fabric fracture.
Further, the determining the type of the accompanying phenomenon when detecting the textile seam slippage further comprises:
carrying out edge detection on the edge contour area of the textile fabric to obtain each edge line, and determining a target edge line from each edge line;
and judging whether the number of the target edge lines is greater than a set number threshold value or not, and if so, judging that the accompanying phenomenon when the textile fabric seam slippage is detected is that the textile fabric is broken at the seam.
Further, the determining the type of the accompanying phenomenon when detecting the textile seam slippage further comprises:
and judging whether the seam area of the textile fabric at least comprises two parts of areas, and if the seam area of the textile fabric at least comprises two parts of areas, judging that the seam fracture is a concomitant phenomenon when the seam slippage of the textile fabric is detected.
Further, the calculation formula for determining the difference of the texture information corresponding to each sliding window is as follows:
wherein the content of the first and second substances,
for each sliding window corresponding texture information difference, <' > or>
For the contrast in the texture information of each sliding window, <' >>
For energy in the texture information of each sliding window, based on the texture information of the sliding window>
Texture information for all sliding windowsIs based on the mean value of the contrast in (5)>
Is the average of the energies in the texture information for all sliding windows.
The invention has the following beneficial effects: the edge detection is carried out on the preprocessed textile image through the gradient threshold range which is obtained in advance and matched with the detected textile, the stitch area of the textile can be accurately determined, and the influence of textile texture is avoided. Meanwhile, sliding windows are constructed in the preprocessed textile images, and the texture information difference corresponding to each sliding window is determined according to the texture information of each sliding window, so that the edge contour area of the textile can be accurately determined, and the accompanying phenomenon type when the textile seam slippage is detected can be accurately determined according to the edge contour area and the stitch area of the textile. The invention provides a reliable analysis method for detecting the accompanying phenomenon of textile seam slippage, which can accurately determine the type of the accompanying phenomenon when detecting the textile seam slippage by acquiring a visible light image of a textile when detecting the textile seam slippage by an optical means, and carrying out material analysis and test on the visible light image.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of the method for analyzing the accompanying phenomenon of textile seam slippage detection according to the present invention.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the embodiments, structures, features and effects of the technical solutions according to the present invention will be given with reference to the accompanying drawings and preferred embodiments. In the following description, the different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The specific scenes aimed by the invention are as follows: the phenomenon generated when detecting the seam slippage performance of single-layer textile fabrics such as bed sheets, bed covers and the like is analyzed.
The purpose of the invention is as follows: whether the joint slippage performance of single-layer textiles such as a bed sheet, a quilt cover and the like is accompanied or not and specific phenomenon division are detected.
The invention provides an analysis method for detecting accompanying phenomena of textile seam slippage, which is shown in a corresponding flow chart shown in figure 1 and comprises the following steps:
(1) Acquiring a textile image when detecting textile seam slippage, and further acquiring a preprocessed textile image;
(2) Constructing sliding windows in the preprocessed textile fabric images, and determining a gray level co-occurrence matrix corresponding to each sliding window according to the gray level value of pixel points in each sliding window;
(3) Determining texture information of each sliding window according to the gray level co-occurrence matrix corresponding to each sliding window, and further determining texture information difference corresponding to each sliding window according to the texture information of each sliding window;
(4) Determining a problem area in the textile image according to the texture information difference corresponding to each sliding window, and determining an edge contour area of the textile according to the problem area;
(5) Acquiring a gradient threshold range matched with the detected textile, and performing edge detection on the preprocessed textile image according to the gradient threshold range to obtain a stitch area of the textile;
(6) And determining the accompanying phenomenon type when detecting the textile seam slippage according to the edge contour area and the sewing line area of the textile.
The following describes the analysis method of the accompanying phenomenon of textile seam slippage detection in detail with reference to specific steps.
The method comprises the following steps: and acquiring an image and preprocessing the image.
When detecting that the seam slips, applying certain tensile force to the two sides of the seam, placing the color-changeable light source behind the textile, placing the camera in front of the textile, and having ambient light in front of the textile. And carrying out preprocessing operations such as graying, denoising and the like on the obtained image.
Step two: and detecting joint slippage.
Judging whether the textile is torn or not according to the texture information, and analyzing the seam slippage problem under four conditions to distinguish the four seam slippage conditions one by one.
Analysis was performed from the images obtained:
1. image analysis using gray level co-occurrence matrices
In spite of the problems in the background technology, the texture of the image has obvious difference in the problem area, so that a sliding window is constructed, a gray level co-occurrence matrix is constructed in the window, the texture description is obtained through the gray level co-occurrence matrix, and the texture difference between the texture in the sliding window and the texture in other windows is compared to preliminarily determine that the textile has seam slippage accompanying phenomenon.
The size of the sliding window is 20 × 20, and the longitudinal and transverse steps are 10 when the window is slid. Method for judging area abnormity in sliding window by comparing image texture information in sliding window with texture information difference in all sliding windowsY：
Wherein the information is obtained according to the gray level co-occurrence matrixTexture information in the window, obtaining contrast CON and energy ASM,
、/>
the average of the contrast and the energy obtained for all the sliding windows respectively.
Setting the threshold value mu =50, namely when the obtained Y is larger than the threshold value mu, the texture of the region corresponding to the window is considered to be different from the texture of other regions, so that the problem region can be obtained.
2. Image analysis by self-adaptive threshold canny detection method
For seam slippage detection of textiles, it is first necessary to determine the position of the seam. According to the suture analysis, the visible stitches formed by back and forth movement of the needle thread are everywhere on the suture, and according to the characteristic, an edge detection method can be used, so that the detected edge lines are more, and the part with higher density is the approximate suture area.
And (4) carrying out edge detection on the image after preprocessing in the step one by using a canny operator, marking each edge line, and recording the length of each edge line and the position information of the central point. And clustering the detected edge lines by using a density clustering method based on the position information of the central points of the detected edge lines, wherein the region where the edge of the type with the largest number of clustered edges is located is probably the textile sewing region.
According to the invention, as the textile fabric is knitted by warps and wefts, the edges of the knitting yarns can be easily detected during edge detection, so that the difficulty of finding the target edge from the edge image is increased, and the edge detection algorithm of the canny operator with the self-adaptive threshold value is provided for reducing or even eliminating the detected edge.
For a single-layer fabric, the condition that the edge detection is carried out when the condition of gap fracture and the like can occur is the difference between the color of the textile and the color of the background. Therefore, different background colors can be set during detection, so that the gray gradient range obtained by the textile and the background is different from the gray gradient range generated by the texture of the textile and the shadow formed by fold shielding during edge detection. That is, when setting the gradient threshold, the threshold range may be set to be the range, so that all the detected edges are the edges generated by the textile and the background.
In order to ensure that the gray difference generated by the texture of the image is inconsistent with the gray difference range generated by the background of the textile, the gray value of a certain range of gray levels in the image is transformed, a gray histogram of the image is obtained according to the image, firstly, the gray level with the highest occurrence frequency of the gray value is selected according to the gray histogram, and according to the image, the gray values of other pixels are proportioned according to a certain proportion
And closing the gray level, namely performing linear transformation on the gray values of other pixel points to ensure that the gray value of the image is concentrated on the gray level with the maximum occurrence probability of the gray level of the image.
And (3) neglecting the gray scale of the shadow part of the image according to the gray histogram, namely presetting the gray scale range of the shadow part as [0,25], and obtaining the gray scale range [ u, v ] of the gray histogram of the image, wherein the minimum gray scale and the maximum gray scale in the u, v gray histogram are obtained.
Calculating to obtain a gray median e:
the following gray scale conversion method can be obtained according to the above:
wherein G is the original gray value of the pixel point, G is the gray value after transformation,
as the gray level in the gray histogram isiThe value of the time frequency->
For the scaling factor it is ensured that the range of gray levels after a transformation remains in a certain range [ ->
, />
]Interior, or>
、/>
Respectively transformed gray scale ranges.
In order to ensure that the gap gray value is the preset background gray value, the light source is arranged on the other side, and the color of the light source is changed. So that when calculating the gradient, the obtained edge gradient is within a certain range, which is the desired edge of the present invention.
The gray value of the image illuminated by the light sources with different colors is recorded as t. Considering that due to the unevenness of the textile, some textiles may wrinkle for some reasons, which causes the shading on the light to change, and thus forms a shadow on the image. From the gradation values of the shaded portions, a gradation value range [0,25] formed by shading is obtained.
At this time, the gradation difference when the edge is formed by the image and the shadow is [ 2 ]
-25,/>
]The gradient range of gray values [ a, b ] formed by pixel points on the image is made by finding a gray value t of the light source]Wherein:
a=min(
,/>
)
b=max(
,/>
)
and meets the following requirements:
that is, the obtained gray gradient value is greater than the maximum and minimum gray difference value in the image and is smaller than the gradient value formed by any gray value and shadow in the image.
Based on the principle that the original image is modified as little as possible, the gray scale distribution, namely the proportionality coefficient, of the original image is maintained as much as possible
The closer to 0, the better, the preferred value of t is obtained by the above constraint. The evaluation function F, which can be derived from the constraint, is:
i.e. change
Value such that the resulting->
The larger the better. Setting a threshold value D =0.3 when the requested exp-F) Below the threshold D, it can be assumed that a preference has been found>
The value is obtained. According to the result ofPreferably of>
The value of the gradient threshold value range [ a, b ] in canny detection is obtained]。
I.e., only if the gradient values sought are within the selected threshold range, the selected edge can be considered a desired edge for the present invention. Different gradient threshold values can be obtained by analyzing different types of images, but when detecting textile images with similar image contents in the same batch, the threshold value range obtained for the first time can be used all the time without repeated calculation.
3. Determining the kind of seam slippage problem
a) Gap identification
After the image is analyzed by the self-adaptive threshold canny detection method to obtain the suture line area, if the obtained suture line is divided into two parts, the second problem of the seam slippage in the background art, namely the fracture of the suture line, possibly occurs to the textile.
b) Problem area identification
And according to the problem area obtained in the second step, performing edge detection on the image, fitting the obtained edge lines to obtain k edge lines, performing contour fitting on the obtained edge lines to obtain j contour edges, and selecting the edge with the maximum fitted contour for analysis.
c) Positional relationship between problem area and gap
From the obtained contour edge, the coordinates (c 1, d 1) of the center point of the edge contour are calculated, from the obtained suture region, the coordinates (c 2, d 2) of the center point of the suture region are calculated, in this case:
wherein the content of the first and second substances,
distance on the ordinate of the center point.
Setting a threshold value e =125, that is, when the distance ζ between the ordinate of the two center points is greater than the threshold value e, the profile area with the problem is considered to be far away from the gap, and the textile may have a third gap slip problem in the background art, and the textile is broken.
According to image analysis, yarn slippage is similar to the first gap slippage problem, but unlike the first gap slippage problem, some threads can be seen in the image to be connected with the sewing threads, so that the first gap slippage problem can be separated from the fourth gap slippage problem according to the characteristic.
Therefore, edge detection is used for the contour area, each edge line is obtained through detection, most of the detected edge lines are perpendicular to the latitude lines according to the image, so that the edge lines can be restrained according to the characteristic, the edge lines which are not perpendicular to the latitude lines are found, and the number of the edge lines is recorded asl。
Setting the threshold φ =3, i.e. when obtainedlIf the yarn length is more than 3, the defect can be considered as a fourth gap slippage problem in the background technology, namely yarn slippage at the seam; otherwise, this defect is considered to be the first problem of seam slippage in the background art, i.e., fabric breakage at the seam.
It should be noted that: the above-mentioned embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (5)
1. An analysis method for detecting accompanying phenomena of textile seam slippage is characterized by comprising the following steps:
acquiring a textile image when detecting textile seam slippage, and further acquiring a preprocessed textile image;
constructing sliding windows in the preprocessed textile fabric images, and determining a gray level co-occurrence matrix corresponding to each sliding window according to the gray level value of pixel points in each sliding window;
determining texture information of each sliding window according to the gray level co-occurrence matrix corresponding to each sliding window, and further determining texture information difference corresponding to each sliding window according to the texture information of each sliding window;
determining a problem area in the textile image according to the texture information difference corresponding to each sliding window, and determining an edge contour area of the textile according to the problem area;
acquiring a gradient threshold range matched with the detected textile, and performing edge detection on the preprocessed textile image according to the gradient threshold range to obtain a stitch area of the textile;
determining the accompanying phenomenon type when detecting the fabric seam slippage according to the edge contour area and the sewing line area of the fabric;
the acquiring and detecting a gradient threshold range matched with the textile comprises the following steps:
acquiring a surface image of a textile fabric of the same type as the detected textile fabric, acquiring a gray level image of the surface image, and further acquiring a gray level histogram of the gray level image;
selecting a gray level with the most frequent occurrence of gray values in the gray histogram, and closing the gray values of other pixel points in the gray image to the gray level with the most frequent occurrence of gray values according to a set proportion so as to obtain the closed gray histogram;
acquiring gray values corresponding to the different color light sources when the different color light sources irradiate the textile in the same type as the detected textile and gray value ranges of shadow parts formed when the different color light sources irradiate the textile in the same type as the detected textile;
determining a gray difference range when an edge is formed by a gray image and a shadow part according to the gray level range of the closed gray histogram and the gray value range of the formed shadow part;
determining a gray value corresponding to the optimal color light source when the optimal color light source irradiates on the textile fabrics in the same type as the detected textile fabrics according to the gray difference range, the gray level range of the closed gray histogram and the gray value corresponding to the different color light sources when the different color light sources irradiate on the textile fabrics in the same type as the detected textile fabrics, and determining the gray gradient range of the surface image when the optimal color light source irradiates on the textile fabrics in the same type as the detected textile fabrics;
determining an evaluation function value according to the gray gradient range of the surface image when the optimal color light source irradiates on the textile fabric of the same type as the detected textile fabric, the gray level range of the closed gray level histogram, the gray level range of the formed shadow part and a set proportion, continuously changing the set proportion until the determined evaluation function value is larger than a set evaluation threshold value, and taking the gray gradient range of the surface image when the optimal color light source corresponding to the optimal color light source which is larger than the set evaluation threshold value irradiates on the textile fabric of the same type as the detected textile fabric as a gradient threshold value range matched with the detected textile fabric;
and the calculation formula corresponding to the gray values of other pixel points in the gray image being close to the gray level with the highest occurrence frequency of the gray values according to the set proportion is as follows:
wherein the content of the first and second substances,
is the gray value of other pixel points in the closed gray image, and is combined>
Is the gray value of other pixel points in the gray image before closing, is judged>
To set a ratio>
Is the median value of the gray level histogram of the gray level image>
，/>
Is the minimum gray level of the gray histogram of the gray image, is->
The gray level in the gray histogram of the gray image isiA frequency value of time;
the determining the gray value corresponding to the optimal color light source when the optimal color light source irradiates on the textile in the same category as the detected textile comprises the following steps:
determining the minimum gray value and the maximum gray value corresponding to different color light sources according to the gray level range of the closed gray level histogram and the gray values corresponding to different color light sources when the different color light sources irradiate the textile fabrics in the same category as the detected textile fabrics;
judging whether the minimum gray value is larger than the maximum and minimum gray difference value in the gray level range of the closed gray histogram and the maximum gray value is smaller than the minimum gray value in the gray difference range, if so, taking the corresponding color light source as the optimal color light source, thereby obtaining the gray value corresponding to the optimal color light source when the optimal color light source irradiates on the textile fabrics of the same type as the detected textile fabrics;
the calculation formula for determining the maximum gray value a and the maximum gray value b corresponding to the light sources with different colors is as follows:
a=min(
,/>
)
b=max(
,/>
)
wherein, a is the minimum gray value corresponding to the light sources with different colors, and b is the maximum gray value corresponding to the light sources with different colors
, 
]For the gray level range of the closed gray histogram, the value of the gray histogram is greater than or equal to>
For the minimum gray level in the gray level range of the closed gray level histogram, is selected>
For the maximum gray level in the gray level range of the closed gray level histogram, ->
The gray values corresponding to the different color light sources irradiating the textiles of the same type as the detected textiles are obtained, min is a minimum function, and max is a maximum function;
determining a calculation formula corresponding to the evaluation function value as follows:
wherein the content of the first and second substances,
for evaluating the function value, a is the minimum gray value corresponding to different color light sources, b is the maximum gray value corresponding to different color light sources [. Sup. - ]>
,/>
]For the gray level range of the closed gray histogram, the value of the gray histogram is greater than or equal to>
For the minimum gray level in the gray level range of the closed gray level histogram, is selected>
For the maximum gray level in the gray level range of the closed gray level histogram, ->
To set the ratio.
2. The method for analyzing the accompanying phenomenon of textile seam slippage detection according to claim 1, wherein the determining the kind of the accompanying phenomenon in detecting the textile seam slippage comprises:
determining the coordinates of the center point of the edge contour area and the coordinates of the center point of the sewing area according to the edge contour area and the sewing area of the textile fabric, and calculating the distance between the longitudinal coordinates of the two center points;
and judging whether the distance between the vertical coordinates of the two central points is greater than a set distance threshold value, and if so, judging that the accompanying phenomenon when the fabric seam slippage is detected is fabric fracture.
3. The method for analyzing the accompanying phenomenon of textile seam slippage detection according to claim 2, wherein the determining the kind of the accompanying phenomenon in detecting the textile seam slippage further comprises:
performing edge detection on the edge contour area of the textile fabric to obtain each edge line, and determining a target edge line from each edge line;
and judging whether the number of the target edge lines is greater than a set number threshold value or not, and if so, judging that the accompanying phenomenon when the textile fabric seam slippage is detected is that the textile fabric is broken at the seam.
4. The method for analyzing the accompanying phenomenon of textile seam slippage detection according to claim 2, wherein the determining the kind of the accompanying phenomenon in detecting the textile seam slippage further comprises:
and judging whether the seam area of the textile fabric at least comprises two parts of areas, and if so, judging that the accompanying phenomenon when the seam slippage of the textile fabric is detected is seam breakage.
5. The method for analyzing the accompanying phenomenon of textile seam slippage detection according to claim 1, wherein the calculation formula for determining the texture information difference corresponding to each sliding window is as follows:
wherein the content of the first and second substances,
for each sliding window corresponding texture information difference, <' > or>
For the contrast in the texture information of each sliding window, <' >>
For each slidingThe energy in the texture information of the window->
Is the mean of the contrast in the texture information of all sliding windows, < >>
Is the average of the energies in the texture information for all sliding windows. />
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211038607.XA CN115115632B (en) | 2022-08-29 | 2022-08-29 | Analysis method for accompanying phenomenon of textile seam slippage detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211038607.XA CN115115632B (en) | 2022-08-29 | 2022-08-29 | Analysis method for accompanying phenomenon of textile seam slippage detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115115632A CN115115632A (en) | 2022-09-27 |
| CN115115632B true CN115115632B (en) | 2023-04-07 |
Family
ID=83335844
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211038607.XA Active CN115115632B (en) | 2022-08-29 | 2022-08-29 | Analysis method for accompanying phenomenon of textile seam slippage detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115115632B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109191459A (en) * | 2018-09-30 | 2019-01-11 | 东北大学 | The automatic identification and ranking method of continuous casting billet macrostructure center segregation defect |
| CN112712512A (en) * | 2021-01-05 | 2021-04-27 | 余波 | Hot-rolled strip steel scab defect detection method and system based on artificial intelligence |
| CN112884708A (en) * | 2021-01-15 | 2021-06-01 | 深圳市悦创进科技有限公司 | Method for detecting burrs of circular injection molding piece |
| CN113838035A (en) * | 2021-09-27 | 2021-12-24 | 佛山市南海区广工大数控装备协同创新研究院 | Pipeline weld groove contour extraction method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109658381B (en) * | 2018-11-16 | 2023-01-06 | 华南理工大学 | Method for detecting copper surface defects of flexible IC packaging substrate based on super-pixels |
| CN114842027A (en) * | 2022-04-24 | 2022-08-02 | 南通真馨家纺有限公司 | Fabric defect segmentation method and system based on gray level co-occurrence matrix |
| CN114882044B (en) * | 2022-07-12 | 2022-09-06 | 山东汇通工业制造有限公司 | Metal pipe surface quality detection method |
-
2022
- 2022-08-29 CN CN202211038607.XA patent/CN115115632B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109191459A (en) * | 2018-09-30 | 2019-01-11 | 东北大学 | The automatic identification and ranking method of continuous casting billet macrostructure center segregation defect |
| CN112712512A (en) * | 2021-01-05 | 2021-04-27 | 余波 | Hot-rolled strip steel scab defect detection method and system based on artificial intelligence |
| CN112884708A (en) * | 2021-01-15 | 2021-06-01 | 深圳市悦创进科技有限公司 | Method for detecting burrs of circular injection molding piece |
| CN113838035A (en) * | 2021-09-27 | 2021-12-24 | 佛山市南海区广工大数控装备协同创新研究院 | Pipeline weld groove contour extraction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115115632A (en) | 2022-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huang et al. | Woven fabric analysis by image processing: Part I: Identification of weave patterns | |
| Kang et al. | Automatic recognition of fabric weave patterns by digital image analysis | |
| CN114820627B (en) | Textile quality detection method based on optical means | |
| JP6117398B1 (en) | Steel plate surface defect inspection apparatus and surface defect inspection method | |
| US7718912B2 (en) | Outer surface-inspecting method and outer surface-inspecting apparatus | |
| US7865011B2 (en) | Outer surface-inspecting method and outer surface-inspecting apparatus | |
| JP6027295B1 (en) | Surface defect inspection apparatus and surface defect inspection method for hot dip galvanized steel sheet | |
| Iglesias et al. | Automatic recognition of hematite grains under polarized reflected light microscopy through image analysis | |
| CN109211918B (en) | Fabric bow weft detection method based on weft trend | |
| CN114529550A (en) | Textile color fastness detection method and system based on image processing | |
| CN115131353B (en) | Flat screen printing textile production abnormity identification and positioning method and system | |
| CN108022219B (en) | Two-dimensional image gray level correction method | |
| CN115115632B (en) | Analysis method for accompanying phenomenon of textile seam slippage detection | |
| CN115311279A (en) | Machine vision identification method for warp and weft defects of fabric | |
| CN115471504B (en) | Automatic thread end identification method based on textile fabric | |
| CN115496762B (en) | Textile technology-based dyeing defect identification method | |
| CN111402225B (en) | Cloth folding false-detection defect discriminating method | |
| US20070115462A1 (en) | Method for inspecting the quality criteria of flat textile structures embodied in a multi-layer form according to a contour | |
| JP2004185246A (en) | Evaluation method of uniformity of color | |
| CN109165650A (en) | PRINTED FABRIC image minimum repetitive unit automatic testing method | |
| Owczarek | The impact and importance of fabric image preprocessing for the new method of individual inter-thread pores detection | |
| KR20230115024A (en) | Deep Learning based Vision System for Inspecting Atypical Defect and Method for Controlling the same | |
| JP4355479B2 (en) | DEFECT LEVEL INFORMATION SETTING METHOD IN DEFECTED CRACK DETECTOR | |
| Liu et al. | Automatic analysis the braiding angle of the braided fabrics using image processing | |
| Ma et al. | A Method for Detecting and Correcting Specular Highlights in Capsule Endoscope Images Based on Independent Cluster Distribution |
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 |