CN114663435B - Automatic monitoring method for tension abnormity of textile fabric - Google Patents

Automatic monitoring method for tension abnormity of textile fabric Download PDF

Info

Publication number
CN114663435B
CN114663435B CN202210571820.0A CN202210571820A CN114663435B CN 114663435 B CN114663435 B CN 114663435B CN 202210571820 A CN202210571820 A CN 202210571820A CN 114663435 B CN114663435 B CN 114663435B
Authority
CN
China
Prior art keywords
gray level
monitoring index
monitoring
run
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.)
Expired - Fee Related
Application number
CN202210571820.0A
Other languages
Chinese (zh)
Other versions
CN114663435A (en
Inventor
邓秋芳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qidong Xinpenglai Textile Technology Co ltd
Original Assignee
Qidong Xinpenglai Textile Technology Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Qidong Xinpenglai Textile Technology Co ltd filed Critical Qidong Xinpenglai Textile Technology Co ltd
Priority to CN202210571820.0A priority Critical patent/CN114663435B/en
Publication of CN114663435A publication Critical patent/CN114663435A/en
Application granted granted Critical
Publication of CN114663435B publication Critical patent/CN114663435B/en
Expired - Fee Related legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • 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
    • G06T2207/20076—Probabilistic 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
    • G06T2207/30—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)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Treatment Of Fiber Materials (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Abstract

The invention relates to the technical field of spinning, in particular to a method for automatically monitoring tension abnormity of textile fabric, which comprises the following steps: acquiring a cloth image, and performing multi-scale down-sampling on the cloth image; acquiring a gray level co-occurrence matrix and a gray level run-length matrix of each sampled image, and acquiring a comprehensive monitoring index of the sampled image according to the gray level co-occurrence matrix and the gray level run-length matrix; and automatically monitoring the abnormal tension of the textile fabric according to the comprehensive monitoring index of each sampling image. The monitoring result of the invention is not interfered by other cloth defects, the false detection rate is low, and the accuracy of the cloth tension abnormity detection is ensured. The method can be applied in general control or regulation systems or in monitoring or testing devices of such systems or units, in particular in production field artificial intelligence systems, in industrial automation system device manufacturing and in intelligent monitoring devices. In addition, the method can be used for developing application software such as computer vision software.

Description

Automatic monitoring method for tension abnormity of textile fabric
Technical Field
The invention relates to the field of textiles, in particular to an automatic monitoring method for tension abnormity of textile fabrics.
Background
In the textile industry, the tension of cloth directly affects the quality of finished cloth products, if the tension of the cloth is abnormal, the tension of the cloth not only can cause the surface quality defect of the cloth, but also can cause the failure of a cloth rolling machine in the subsequent finishing procedure of the cloth, the damage of the winding of the cloth and the uneven winding diameter of the finished cloth can be easily caused, and the production efficiency of enterprises and the quality of products can be seriously affected. Therefore, in the production process of the cloth, the tension of the cloth needs to be monitored to prevent the above situation.
The existing method for monitoring the cloth tension mostly utilizes a cloth tension detector, although the method can accurately detect the tension of the cloth, the method essentially belongs to the direct measurement of the tension, and the method is sampling measurement and cannot comprehensively detect all cloth finished products on the whole production line; although the method ensures the accuracy of detection, the method ignores the comprehensiveness of the detection. When tension of the cloth is abnormal, the tension is often abnormal along with the position abnormality of warps and wefts of the cloth, namely the phenomenon of uneven density of warps and wefts on the surface of the cloth occurs, whether the tension of the cloth is abnormal can be indirectly determined by utilizing the position abnormality of the warps and wefts on the surface of the cloth, however, other defects of the cloth can also cause the position abnormality of the warps and wefts, and the existing image processing technology such as a gray level co-occurrence matrix method can only monitor the position abnormality of the warps and wefts, so that the tension abnormality monitoring result is interfered by other cloth defects, and false detection is generated.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide an automatic monitoring method for tension abnormity of textile fabric, which adopts the following technical scheme:
in a first aspect, an embodiment of the present invention provides a method for automatically monitoring tension abnormality of a textile fabric, including the following specific steps:
acquiring a cloth image, and performing multi-scale down-sampling on the cloth image;
acquiring a gray level co-occurrence matrix and a gray level run-length matrix of each sampled image, acquiring a first monitoring index according to an entropy characteristic value of the gray level co-occurrence matrix, calculating a second monitoring index based on the gray level run-length matrix, representing the distribution complexity of pixels continuously appearing in each gray level, and acquiring a comprehensive monitoring index of the sampled image by combining the first monitoring index and the second monitoring index;
and automatically monitoring the abnormal tension of the textile fabric according to the comprehensive monitoring index of each sampling image.
Further, the obtaining of the first monitoring index specifically includes:
setting a space parameter and a direction angle parameter of a pixel point pair for each sampling image, and acquiring a plurality of gray level co-occurrence matrixes; dividing the gray level of the pixel to obtain a plurality of gray level binary groups of the pixel point pair, and calculating an entropy characteristic value according to the occurrence probability of the pixel point pair corresponding to each gray level binary group based on the pixel gray level; and the mean value of the entropy characteristic values corresponding to the angle parameters in each direction is a first monitoring index.
Further, the obtaining of the second monitoring index specifically includes:
setting a walking direction for each sampled image, and acquiring a plurality of gray level run matrixes; for each gray level run matrix, the gray level and the walk length form a run binary group, the ratio of the number of pixels corresponding to each run binary group is probability, and the calculation result is a second sub-monitoring index according to the entropy calculation mode; and the mean value of the second sub-monitoring index is the second monitoring index.
Further, the obtaining of the number of pixels corresponding to each run binary group specifically includes:
the product of the walk length in the run binary and the value of the run binary corresponding to the gray scale run matrix is the number of pixels corresponding to the run binary.
And further, automatically monitoring the tension abnormity of the textile fabric according to the sum of the comprehensive monitoring indexes of each sampling image.
Furthermore, setting weight for comprehensive monitoring indexes of the sampled image, wherein the smaller the size of the sampled image is, the smaller the weight is; and automatically monitoring the abnormal tension of the textile fabric according to the weighted sum of the comprehensive monitoring indexes of the sampling images.
The embodiment of the invention at least has the following beneficial effects: the method comprises the steps of obtaining a first monitoring index based on a gray level co-occurrence matrix, obtaining a second monitoring index based on a gray level run matrix, obtaining a comprehensive detection index of a sampling image by combining the first monitoring index and the second monitoring index, and automatically monitoring the tension abnormity of the textile fabric based on the comprehensive detection index; the method has the advantages that the monitoring result is not interfered by other cloth defects, the false detection rate is low, the accuracy of the tension abnormity detection of the cloth is ensured, and the comprehensiveness of the detection is improved. Based on the above advantages, the method can be applied in general control or regulation systems or in monitoring or testing devices of such systems or units, in particular in production field artificial intelligence systems, in industrial automation system device manufacturing and in intelligent monitoring devices. In addition, the method can be used for developing application software such as computer vision software.
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 flowchart illustrating steps according to an embodiment of the present invention.
Detailed Description
In order to further illustrate the technical means and effects of the present invention adopted to achieve the predetermined invention purpose, the following detailed description will be given to the specific implementation manner, structure, features and effects of the automatic monitoring method for tension abnormality of textile fabric according to the present invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily 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 following application scenarios are taken as examples to illustrate the present invention:
in textile material tension monitoring, the existing automatic monitoring generally utilizes a cloth tension detection machine to carry out selective examination, and the cloth tension detection machine is difficult to set on a production line, so that the whole batch of cloth can not be comprehensively monitored. The existing image processing technology is easy to misjudge some defect types on the surface of the cloth as tension abnormity when judging the tension abnormity according to the position abnormity of the warp and weft yarns on the surface of the cloth. Therefore, a method for automatically monitoring tension abnormality of cloth is needed to improve the efficiency and comprehensiveness of tension abnormality monitoring and ensure the monitoring accuracy.
Based on the reasons, the invention provides an automatic monitoring method for tension abnormity of textile fabrics.
The following describes a specific scheme of the automatic monitoring method for tension abnormality of textile fabric provided by the invention in detail with reference to the accompanying drawings.
Referring to fig. 1, a flow chart of steps of an automatic monitoring method for tension abnormality of a textile fabric according to an embodiment of the present invention is shown, the method includes the following steps:
acquiring a cloth image, and performing multi-scale down-sampling on the cloth image;
acquiring a gray level co-occurrence matrix and a gray level run-length matrix of each sampled image, acquiring a first monitoring index according to an entropy characteristic value of the gray level co-occurrence matrix, calculating a second monitoring index based on the gray level run-length matrix, representing the distribution complexity of pixels continuously appearing in each gray level, and acquiring a comprehensive monitoring index of the sampled image by combining the first monitoring index and the second monitoring index;
and automatically monitoring the abnormal tension of the textile fabric according to the comprehensive monitoring index of each sampling image.
The above steps are described in detail below:
(1) and acquiring a cloth image, and performing multi-scale down-sampling on the cloth image.
Carrying out image acquisition on the surface of the cloth, setting the obtained image to be equal in length and width in the embodiment, carrying out graying to obtain a cloth image, carrying out multi-scale pyramid sampling on the cloth image, and carrying out the steps
Figure DEST_PATH_IMAGE002
Sub-sampling by a sub-pyramid, and recording the sampled image obtained after each time of down-sampling as
Figure DEST_PATH_IMAGE004
，
Figure DEST_PATH_IMAGE006
The value range of (a) is [0,
Figure 60925DEST_PATH_IMAGE002
]，
Figure 571540DEST_PATH_IMAGE006
when the value is 0, it means that downsampling is not performed, that is, the sampled image is the original image.
(2) The method comprises the steps of obtaining a gray level co-occurrence matrix and a gray level run-length matrix of each sampled image, obtaining a first monitoring index according to an entropy characteristic value of the gray level co-occurrence matrix, calculating a second monitoring index based on the gray level run-length matrix, representing the distribution complexity of pixels continuously appearing in each gray level, and obtaining a comprehensive monitoring index of the sampled image by combining the first monitoring index and the second monitoring index.
The first monitoring index is specifically obtained as follows: setting a space parameter and a direction angle parameter of a pixel point pair for each sampling image, and acquiring a plurality of gray level co-occurrence matrixes; dividing the gray level of the pixel to obtain a plurality of gray level binary groups of the pixel point pair, and calculating an entropy characteristic value according to the occurrence probability of the pixel point pair corresponding to each gray level binary group based on the pixel gray level; and the mean value of the entropy characteristic values corresponding to the angle parameters in each direction is a first monitoring index.
The second monitoring index is specifically obtained as follows: setting a walking direction for each sampled image, and acquiring a plurality of gray level run matrixes; for each gray level run matrix, the gray level and the walk length form a run binary group, the ratio of the number of pixels corresponding to each run binary group is probability, and the calculation result is a second sub-monitoring index according to the entropy calculation mode; and the mean value of the second sub-monitoring index is the second monitoring index.
Following to sample the image
Figure 882436DEST_PATH_IMAGE004
For example, the process of acquiring the first monitoring index, the second monitoring index and the comprehensive monitoring index of the sampled image is described.
(a) Acquiring a sampled image
Figure 808804DEST_PATH_IMAGE004
The first monitoring index of (1):
multiple gray level co-occurrence matrixes of the sampled images can be obtained due to different statistical modes, and direction angle parameters are set in the embodiment
Figure DEST_PATH_IMAGE008
Is composed of
Figure DEST_PATH_IMAGE010
And
Figure DEST_PATH_IMAGE012
i.e., vertical and horizontal; distance parameter for pixel point pairs
Figure DEST_PATH_IMAGE014
，
Figure 839820DEST_PATH_IMAGE014
The value range of (a) is [1,
Figure DEST_PATH_IMAGE016
]，
Figure 724600DEST_PATH_IMAGE016
the maximum distance between pixel point pairs, in the embodiment
Figure 24256DEST_PATH_IMAGE016
Is 10. Pitch parameter based on pixel point pairs
Figure 754315DEST_PATH_IMAGE014
And direction angle parameter
Figure 954352DEST_PATH_IMAGE008
Obtaining gray level co-occurrence matrix of sampled image, i.e. direction angle parameter
Figure DEST_PATH_IMAGE018
Or
Figure DEST_PATH_IMAGE020
Distance parameter of pixel point pair
Figure 275612DEST_PATH_IMAGE014
Is a copolymer of (1),
Figure 561100DEST_PATH_IMAGE016
]any one value of the gray level co-occurrence matrixes of the sampled images is obtained, and then the gray level co-occurrence matrixes can be obtained together
Figure DEST_PATH_IMAGE022
A gray level co-occurrence matrix. Acquiring a first monitoring index of a sampling image based on a gray level co-occurrence matrix: dividing the gray scale of the pixel to obtain a plurality of gray of the pixel point pairDegree level binary groups, based on pixel gray levels, calculating entropy characteristic values according to the occurrence probability of pixel point pairs corresponding to each gray level binary group; the mean value of the entropy characteristic values corresponding to the angle parameters in each direction is a first monitoring index; in particular, the pixel gray scale regions 0-255 in the sampled image are divided into
Figure DEST_PATH_IMAGE024
And (2) obtaining corresponding gray levels according to the gray level of each pixel, wherein the gray levels of the pixels in the pixel point pair form gray level binary groups, and the entropy characteristic value is calculated according to the occurrence probability of the pixel point pair corresponding to each gray level binary group, and as an example, the entropy characteristic value is calculated in the following manner:
Figure DEST_PATH_IMAGE026
Figure DEST_PATH_IMAGE028
the distance parameter for a pixel point pair is
Figure 718018DEST_PATH_IMAGE014
The direction angle parameter is
Figure 772562DEST_PATH_IMAGE008
The entropy eigenvalue of the time-acquired gray level eigenvalue matrix is in the value range of [0, 1%]；
Figure DEST_PATH_IMAGE030
Representing binary groups of grey levels
Figure DEST_PATH_IMAGE032
The probability of occurrence of the corresponding pixel point pair, i.e. the gray level binary group in the gray level co-occurrence matrix is
Figure 530302DEST_PATH_IMAGE032
The probability of occurrence of a pixel point pair of (a);
Figure 70130DEST_PATH_IMAGE032
the gray levels of two pixels in the pixel point pair are respectively the first
Figure DEST_PATH_IMAGE034
A gray scale and
Figure DEST_PATH_IMAGE036
the number of the gray-scale levels is,
Figure 673150DEST_PATH_IMAGE034
and
Figure 113359DEST_PATH_IMAGE036
the value ranges of (A) are all [1,
Figure 979684DEST_PATH_IMAGE024
]preferably in the examples
Figure 974184DEST_PATH_IMAGE024
The value was taken to be 5.
The mean value of the entropy characteristic values and the entropy characteristic values corresponding to the angle parameters in all directions is a first monitoring index, and specifically:
Figure DEST_PATH_IMAGE038
Figure DEST_PATH_IMAGE040
is used as a first monitoring index and is used as a second monitoring index,
Figure 676168DEST_PATH_IMAGE040
the larger the value is, the more possible tension abnormality of the textile fabric in the sampling image exists, based on the arrangement mode of the warps and the wefts on the textile fabric, if the tension of the textile fabric is abnormal, the warps and the wefts can be subjected to position deviation, namely twisting, so that the interval of the pixels with the same gray level can be uneven, and if the tension abnormality of the textile fabric is not generated, the pixels with the same gray level are at 0 degree or 9 degreesNo matter what pixel point is used for counting the distance parameter in the 0-degree direction, the corresponding first monitoring index tends to be 0 value. Thus, for the differences
Figure 705304DEST_PATH_IMAGE014
Different entropy characteristic values exist, namely the entropy characteristic values of the cloth materials are different under different point-to-point distance statistical modes, and the entropy characteristic values are different
Figure 8109DEST_PATH_IMAGE014
Corresponding entropy eigenvalues are based on the pixel point-to-point spacing parameter
Figure 224327DEST_PATH_IMAGE014
The first monitoring index is obtained by weight distribution of the size of the first monitoring index;
Figure DEST_PATH_IMAGE042
and
Figure DEST_PATH_IMAGE044
respectively, direction angle parameter
Figure 700307DEST_PATH_IMAGE018
And
Figure 85415DEST_PATH_IMAGE020
the corresponding sum of entropy eigenvalues.
(b) Acquiring a sampled image
Figure 559121DEST_PATH_IMAGE004
The second monitoring index of (1):
setting the direction of wandering
Figure DEST_PATH_IMAGE046
Acquiring a plurality of gray level run matrixes; direction of embodiment
Figure 59373DEST_PATH_IMAGE046
Including 0 deg. and 90 deg., directions of wandering
Figure 745569DEST_PATH_IMAGE046
Respectively at 0 degree and 90 degrees, and acquiring two gray level run-length matrixes; sampling images
Figure 749297DEST_PATH_IMAGE004
Length of side is noted as
Figure DEST_PATH_IMAGE048
Then sampling the image
Figure 925063DEST_PATH_IMAGE004
Has a maximum run length of
Figure 381453DEST_PATH_IMAGE048
。
For each gray level run matrix, the gray level and the migration length form a run binary group, the pixel number ratio corresponding to each run binary group is probability, and the calculation result is a second sub-monitoring index according to the calculation mode of entropy; and the mean value of the second sub-monitoring index is the second monitoring index. The obtaining of the number of pixels corresponding to each run binary group specifically includes: the product of the walk length in the run binary and the value of the run binary corresponding to the gray scale run matrix is the number of pixels corresponding to the run binary.
As an example, the second monitoring index is calculated by:
Figure DEST_PATH_IMAGE050
Figure DEST_PATH_IMAGE052
Figure DEST_PATH_IMAGE054
based on sampled images
Figure 25667DEST_PATH_IMAGE004
Corresponding to a direction of travel of
Figure 618323DEST_PATH_IMAGE046
Calculating a second sub-monitoring index obtained by the gray level run matrix;
Figure DEST_PATH_IMAGE056
in order to run the binary group,
Figure DEST_PATH_IMAGE058
the display of the gray scale levels is performed,
Figure 732034DEST_PATH_IMAGE058
the value range of (a) is [1,
Figure 157943DEST_PATH_IMAGE024
]，
Figure DEST_PATH_IMAGE060
the length of the walk is indicated and,
Figure 248259DEST_PATH_IMAGE060
the value range of (a) is [1,
Figure 961000DEST_PATH_IMAGE048
]，
Figure DEST_PATH_IMAGE062
representing a gray level of a gray run matrix of
Figure 947410DEST_PATH_IMAGE058
Run length of
Figure 378392DEST_PATH_IMAGE060
The value of (a) is (b),
Figure DEST_PATH_IMAGE064
representing run doublets
Figure 508284DEST_PATH_IMAGE056
The number of pixels to be used in the corresponding,
Figure DEST_PATH_IMAGE066
representing a sampled image
Figure 872269DEST_PATH_IMAGE004
The total number of pixels in the image data,
Figure DEST_PATH_IMAGE068
representing run doublets
Figure 295160DEST_PATH_IMAGE056
The corresponding pixel number is in proportion;
Figure DEST_PATH_IMAGE070
for sampling images
Figure 744596DEST_PATH_IMAGE004
The corresponding second monitoring index is normalized data, if the textile fabric has no tension abnormity, the number of continuous pixels of each gray level is fixed, the number of pixels corresponding to each run binary group is proportional, namely the distribution of probability is regular, therefore,
Figure 645556DEST_PATH_IMAGE054
is smaller, and then
Figure 565845DEST_PATH_IMAGE070
The value of (A) is also smaller, otherwise, the number of continuous pixels of each gray scale is not fixed, the ratio of the number of pixels corresponding to each run binary group, namely the distribution of probability, is irregular and dispersed, namely, the distribution of the continuously appearing pixels of each gray scale is complex and complex, and further, the distribution of the continuously appearing pixels of each gray scale is complex and complex
Figure 628479DEST_PATH_IMAGE054
The value of (a) is large,
Figure 768474DEST_PATH_IMAGE070
the value of (A) is also large, and therefore, the larger the second monitoring index value is, the more the sampled image is
Figure 473125DEST_PATH_IMAGE004
The more likely there is tension anomaly in the woven cloth of (1).
(c) Acquiring a sampled image
Figure 14964DEST_PATH_IMAGE004
The comprehensive monitoring indexes are as follows:
the comprehensive monitoring index of the sampling image is obtained by combining the first monitoring index and the second monitoring index, the comprehensive monitoring index is in positive correlation with the first monitoring index and the second monitoring index, preferably, as an example, the calculation mode of the comprehensive monitoring index is as follows:
Figure DEST_PATH_IMAGE072
Figure DEST_PATH_IMAGE074
for sampling images
Figure 609019DEST_PATH_IMAGE004
The comprehensive monitoring index of (1) is normalized data;
Figure 236309DEST_PATH_IMAGE040
and
Figure 479072DEST_PATH_IMAGE070
respectively a sampled image
Figure 875418DEST_PATH_IMAGE004
The first monitoring index and the second monitoring index.
According to the method, the comprehensive monitoring index of each sampling image can be obtained.
(3) And automatically monitoring the abnormal tension of the textile fabric according to the comprehensive monitoring index of each sampling image.
In one embodiment, the tension abnormity of the textile fabric is automatically monitored according to the sum of the comprehensive monitoring indexes of each sampling image; set up threshold ∅, when the sum of comprehensive monitoring index was greater than the threshold value, textile fabric had the tension anomaly, reported to the police and suggested.
In another embodiment, a weight is set for the comprehensive monitoring index of the sampled image, and the smaller the size of the sampled image is, the smaller the weight is; and automatically monitoring the abnormal tension of the textile fabric according to the weighted sum of the comprehensive monitoring indexes of the sampling images. As one example, an image is sampled
Figure 545434DEST_PATH_IMAGE004
The weight of the comprehensive monitoring index is
Figure DEST_PATH_IMAGE076
Then, the weighted sum is specifically:
Figure DEST_PATH_IMAGE078
Figure DEST_PATH_IMAGE080
for a weighted sum, a threshold ∅ is set, and tension anomaly monitoring is performed as follows: when Z is equal to 0, ∅]In time, the tension of the textile fabric is not abnormal, and no alarm prompt is given; when Z is equal to [ ∅, 1 ]]And in time, the textile fabric has abnormal tension, and an alarm is given.
It should be noted that: the precedence order of the above embodiments of the present invention is only for description, and does not represent the merits of the embodiments. And specific embodiments thereof have been described above. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (3)

1. A textile fabric tension abnormity automatic monitoring method is characterized by comprising the following steps:
acquiring a cloth image, and performing multi-scale down-sampling on the cloth image;
acquiring a gray level co-occurrence matrix and a gray level run-length matrix of each sampled image, acquiring a first monitoring index according to an entropy characteristic value of the gray level co-occurrence matrix, calculating a second monitoring index based on the gray level run-length matrix, representing the distribution complexity of pixels continuously appearing in each gray level, and acquiring a comprehensive monitoring index of the sampled image by combining the first monitoring index and the second monitoring index;
automatically monitoring the abnormal tension of the textile fabric according to the comprehensive monitoring index of each sampling image;
the first monitoring index is obtained specifically as follows:
for each sampled image, setting a distance parameter and a direction angle parameter of a pixel point pair to obtain a plurality of gray level co-occurrence matrixes; dividing the gray level of the pixel to obtain a plurality of gray level binary groups of the pixel point pair, and calculating an entropy characteristic value according to the occurrence probability of the pixel point pair corresponding to each gray level binary group based on the pixel gray level; the mean value of the entropy characteristic values corresponding to the angle parameters in each direction is a first monitoring index;
the second monitoring index is specifically obtained as follows:
setting a walking direction for each sampled image, and acquiring a plurality of gray level run matrixes; for each gray level run matrix, the gray level and the walk length form a run binary group, the ratio of the number of pixels corresponding to each run binary group is probability, and the calculation result is a second sub-monitoring index according to the entropy calculation mode; the mean value of the second sub-monitoring index is a second monitoring index;
the obtaining of the number of pixels corresponding to each run binary group specifically includes:
the product of the walk length in the run binary group and the value of the run binary group corresponding to the gray level run matrix is the number of pixels corresponding to the run binary group;
the acquisition of the comprehensive monitoring index specifically comprises the following steps:
the calculation mode of the comprehensive monitoring index is as follows:
Figure 620887DEST_PATH_IMAGE002
Figure DEST_PATH_IMAGE003
for sampling images
Figure 744832DEST_PATH_IMAGE004
The comprehensive monitoring index of (2);
Figure DEST_PATH_IMAGE005
and
Figure 733517DEST_PATH_IMAGE006
respectively a sampled image
Figure 829780DEST_PATH_IMAGE004
The first monitoring index and the second monitoring index.
2. The method of claim 1, wherein the tension abnormality of the textile fabric is automatically monitored according to the sum of the comprehensive monitoring indexes of the sampled images.
3. The automatic monitoring method for tension abnormality of textile fabric material according to claim 1, characterized in that weight is set for comprehensive monitoring index of sampling image, and the smaller the size of sampling image is, the smaller the weight is; and automatically monitoring the abnormal tension of the textile fabric according to the weighted sum of the comprehensive monitoring indexes of the sampling images.
CN202210571820.0A 2022-05-25 2022-05-25 Automatic monitoring method for tension abnormity of textile fabric Expired - Fee Related CN114663435B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210571820.0A CN114663435B (en) 2022-05-25 2022-05-25 Automatic monitoring method for tension abnormity of textile fabric

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210571820.0A CN114663435B (en) 2022-05-25 2022-05-25 Automatic monitoring method for tension abnormity of textile fabric

Publications (2)

Publication Number Publication Date
CN114663435A CN114663435A (en) 2022-06-24
CN114663435B true CN114663435B (en) 2022-08-09

Family

ID=82038219

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210571820.0A Expired - Fee Related CN114663435B (en) 2022-05-25 2022-05-25 Automatic monitoring method for tension abnormity of textile fabric

Country Status (1)

Country Link
CN (1) CN114663435B (en)

Families Citing this family (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114972331B (en) * 2022-07-15 2022-10-21 启东金耀億华玻纤材料有限公司 Method and device for identifying quality of AGM partition plate by utilizing gray level run-length matrix
CN114913248B (en) * 2022-07-18 2023-08-22 佛山品特塑彩新材料有限公司 Self-adaptive control method of corona machine in film production process
CN114913178B (en) * 2022-07-19 2022-09-23 山东天宸塑业有限公司 Melt-blown fabric defect detection method and system
CN114972894A (en) * 2022-07-26 2022-08-30 南通三信塑胶装备科技股份有限公司 CPP film defect classification method based on computer vision
CN114998345A (en) * 2022-08-04 2022-09-02 南通金丝楠膜材料有限公司 Injection molding silver thread defect detection method and system based on gray level run matrix
CN115082458B (en) * 2022-08-18 2022-11-15 南通睿谷纺织科技有限公司 Textile material defect analysis method based on gray level run matrix
CN115100213B (en) * 2022-08-29 2022-12-09 海门喜满庭纺织品有限公司 Material bleaching identification method in textile technology and data processing system
CN115131719B (en) * 2022-08-31 2022-11-25 江苏永银化纤有限公司 Automatic shuttle piece adjusting method for production of safety belt of gripper shuttle ribbon loom

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8498480B2 (en) * 2009-02-25 2013-07-30 The United States Of America, As Represented By The Secretary Of The Navy Computationally efficient method for image segmentation with intensity and texture discrimination
CN110570418B (en) * 2019-09-12 2022-01-11 广东工业大学 Woven label defect detection method and device
CN111080574A (en) * 2019-11-19 2020-04-28 天津工业大学 Fabric defect detection method based on information entropy and visual attention mechanism
CN114494259B (en) * 2022-04-18 2022-06-17 南通东德纺织科技有限公司 Cloth defect detection method based on artificial intelligence
CN114529550B (en) * 2022-04-25 2022-07-01 启东新朋莱纺织科技有限公司 Textile color fastness detection method and system based on image processing
CN114529549B (en) * 2022-04-25 2022-06-21 南通东德纺织科技有限公司 Cloth defect labeling method and system based on machine vision

Also Published As

Publication number Publication date
CN114663435A (en) 2022-06-24

Similar Documents

Publication Publication Date Title
CN114663435B (en) Automatic monitoring method for tension abnormity of textile fabric
US11091858B2 (en) On-loom fabric inspection system and method
Kuo et al. Gray relational analysis for recognizing fabric defects
CN115311267B (en) Method for detecting abnormity of check fabric
CN115311303A (en) Textile warp and weft defect detection method
CN114693677B (en) Knitted fabric pad dyeing process abnormity detection method
CN115082458B (en) Textile material defect analysis method based on gray level run matrix
CN113724241B (en) Broken filament detection method and device for carbon fiber warp-knitted fabric and storage medium
CN109949287A (en) A kind of fabric defects detection method based on adaptivenon-uniform sampling and template correction
CN115018826B (en) Fabric flaw detection method and system based on image recognition
CN115049671A (en) Cloth surface defect detection method and system based on computer vision
CN115861310B (en) Method for detecting textile defects on surface of bed sheet
CN113638104A (en) Intelligent yarn cleaning control method and system for bobbin winder
CN110097538A (en) A kind of online cloth examination device of loom and defects identification method
Anila et al. Fabric texture analysis and weave pattern recognition by intelligent processing
CN116805312A (en) Knitted fabric quality detection method based on image processing
CN114881960A (en) Feature enhancement-based cloth linear defect detection method and system
CN117089977B (en) Dynamic monitoring method, system and medium for grey cloth production
CN115082460B (en) Weaving production line quality monitoring method and system
CN116341758A (en) Fabric quality prediction method based on KNN improved PSO-BP algorithm
CN115294100A (en) Loom parking control method and system based on data processing
Kumar et al. An intelligent scheme for fault detection in textile web materials
CN115294097A (en) Textile surface defect detection method based on machine vision
CN105717133B (en) Automatic cloth inspecting machine based on linear interpolation method correcting image
CN115035024A (en) Yarn doubling and twisting quality evaluation 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
CF01 Termination of patent right due to non-payment of annual fee

Granted publication date: 20220809