Unlock instant, AI-driven research and patent intelligence for your innovation.

A fabric defect detection method based on image projection and singular value decomposition

A singular value decomposition and image projection technology, applied in image analysis, image data processing, character and pattern recognition, etc., can solve the problems of SVD low-rank reconstruction properties, no original image projection operation, etc., to reduce computational complexity, Strong adaptability and good robustness

Active Publication Date: 2016-04-20
DONGHUA UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] It is worth noting that the above researchers all directly performed SVD on the original fabric image, and then extracted the corresponding features for flaw detection, did not perform projection operations on the original image and did not make full use of the low-rank reconstruction properties of SVD

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A fabric defect detection method based on image projection and singular value decomposition
  • A fabric defect detection method based on image projection and singular value decomposition
  • A fabric defect detection method based on image projection and singular value decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0056] Training phase:

[0057] (1) The flawless fabric image is divided into sub-windows with a size of 32×32 (pixels) in an overlapping manner, and the horizontal and vertical translation steps are both 1 pixel. The schematic diagram of the sub-window division is as follows figure 1 , figure 2 and image 3 shown;

[0058] (2) Project the sub-windows along the vertical and horizontal directions respectively, that is, calculate the average value of the gray value of all pixels in each column and each row in the sub-window, and obtain two projection sequences; then, connect the obtained two projection sequences After that, the joint projection sequence is obtained;

[0059] (3) Arrange the joint projection sequences corresponding to all sub-windows as the columns of the matrix into a matrix, and perform singular value decomposition on the obtained matrix; extract the first 4 columns of the left singular matrix as the base vector D.

[0060] Determination of the threshold: ...

Embodiment 2

[0066] Training phase:

[0067] (1) The flawless fabric image is divided into sub-windows with a size of 32×32 (pixels) in an overlapping manner, and the horizontal and vertical translation steps are both 1 pixel. The schematic diagram of the sub-window division is as follows figure 1 , figure 2 and image 3 shown;

[0068] (2) Project the sub-windows along the vertical and horizontal directions respectively, that is, calculate the average value of the gray value of all pixels in each column and each row in the sub-window, and obtain two projection sequences; then, connect the obtained two projection sequences After that, the joint projection sequence is obtained;

[0069] (3) Arrange the joint projection sequences corresponding to all sub-windows as the columns of the matrix into a matrix, and perform singular value decomposition on the obtained matrix; extract the first 16 columns of the left singular matrix as the base vector D.

[0070] Determination of the threshold:...

Embodiment 3

[0076] Training phase:

[0077] (1) The flawless fabric image is divided into sub-windows with a size of 32×32 (pixels) in an overlapping manner, and the horizontal and vertical translation steps are both 31 pixels. The schematic diagram of the sub-window division is as follows figure 1 , figure 2 and image 3 shown;

[0078] (2) Project the sub-windows along the vertical and horizontal directions respectively, that is, calculate the average value of the gray value of all pixels in each column and each row in the sub-window, and obtain two projection sequences; then, connect the obtained two projection sequences After that, the joint projection sequence is obtained;

[0079] (3) Arrange the joint projection sequences corresponding to all sub-windows as the columns of the matrix into a matrix, and perform singular value decomposition on the obtained matrix; extract the first 4 columns of the left singular matrix as the base vector D.

[0080] Determination of the threshold...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a fabric flaw detection method based on image projection and singular value decomposition. In the training stage, the method includes the following steps: first, dividing flawless fabric image samples into square child windows in an overlapping mode, then, projecting the obtained child windows in the longitudinal direction and the transverse direction respectively to obtain union projection sequences, and at last, carrying out singular value decomposition on a matrix formed by the union projection sequences to extract base vectors. In the detection stage, the method includes the following steps: first, dividing fabric image samples to be detected into square child windows in a non-overlapping mode, second, projecting the child windows in the longitudinal direction and the transverse direction to obtain union projection sequences, and third, reconstructing the obtained union projection sequences by using the base vectors and judging whether the child windows comprise flaws through reconstruction errors. According to the fabric flaw detection method based on image projection and singular value decomposition, longitude and latitude orientation characteristics of fabric textures and the flaws are fully used; by analyzing the sequences obtained through projection in the longitudinal direction and the transverse direction, complexity of the method is greatly reduced, besides, the method has strong adaptability to texture and flaw types of different fabrics, especially linear flaws.

Description

technical field [0001] The invention belongs to the field of image analysis and processing, and relates to a fabric flaw detection method based on image projection and singular value decomposition, which is applied to the field of automatic detection and control of textile surface quality. Background technique [0002] Assuming that matrix A is an m×n matrix, singular value decomposition (SVD) can decompose matrix A into three matrices U, Σ and V. Among them, matrix U is an orthogonal matrix of m×n, matrix V is an orthogonal matrix of n×n, matrix Σ is a matrix of m×n, and the elements outside its diagonal are all zero, that is, matrix Σ=diag(σ 1 , σ 2 ,...,σ r ) is a diagonal matrix, r is the rank of matrix A, σ 1 , σ 2 ,...,σ r is the singular value of A matrix. The matrices U and V are called left singular matrix and right singular matrix respectively, and the elements on the diagonal of matrix Σ are in descending order, namely: σ 1 ≥σ 2 ≥…≥σ r ≥0. [0003] Set t...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06K9/66
Inventor 周建汪军王钢李立轻陈霞万贤福李冠志
Owner DONGHUA UNIV