Method for detecting flaws of printed fabric based on Gabor filter

Abstract

The invention discloses a method for detecting flaws of printed fabric based on a Gabor filter. The method comprises the steps that the basic Gabor filter is established and Gabor parameters are extracted; the extracted Gabor parameters are selected, intersected and varied, the Gabor parameters are changed, the parameters with the high adaption degree of an objective function are selected, through intersection and variation, the selected parameter with the high adaption degree are transformed, and therefore parameters with the highest adaption degree are generated; according to a Gabor parameter direction theta and the center frequency u0 which are selected through a genetic algorithm, rotation transformation is conducted on the obtained Gabor parameters, and therefore effective flawless printed fabric textural feature information is extracted; Gabor filtering convolution operation is conducted on a printed fabric image to be detected and a flawless printed fabric image, so that texture background information of printed fabric to be detected is extracted; binaryzation is conducted on the printed fabric image to be detected and the flawless printed fabric image, so that a flaw detection result of the printed fabric is obtained. The method for detecting the flaws of the printed fabric based on the Gabor filter can improve detection efficiency and detection accuracy.

Description

technical field [0001] The invention belongs to the technical field of textile defect detection methods, and relates to a printed fabric defect detection method based on a Gabor filter. Background technique [0002] The flaws on the printed fabric have a great impact on its sales price, which will lead to a price reduction of the product ranging from 45% to 65% of the original price. At present, in the actual printed fabric detection, manual detection occupies a dominant position, but there are problems of slow detection speed and low detection success rate. The detection accuracy is only 60% to 70%. Due to the low accuracy rate, most companies choose to use inspection systems instead of manual inspection. The most widely used inspection system is the I-TEX inspection system, and the high hardware maintenance has limited the application of the I-TEX inspection system. [0003] On the basis of a series of printed fabric detection algorithm software, the printed fabric detec...

AI Technical Summary

Problems solved by technology

A statistically based approach is defined as the "energy" of texture features captured in each image response of each pixel in a window of the input image. Conci and Proenca examine the input printed fabric with an estimate of the fractal dimension (FD For image defects, by processing image information and modifying different box counts, the computational complexity is minimized and work efficiency is improved; however, the only weakness is that the detection of defects has a high false positive rate and poor positioning accuracy

The advantage of the model-based method is that similar textures can be constructed to match the observed textures. Cohen of Drexel University in the United States uses Gauss Markov Random Submission (GMRF) to detect textile fabrics, whose parameters are derived from flawless printed fabrics image and obtained ideal detection results, but this method also has disadvantages, such as: it is difficult to reduce the complexity of input image analysis, and it is impossible to achieve rapid detection of fabrics

Spectral-based methods are suitable for materials with random textures. Tsai and Heish use a combined DFT to detect directional texture defects, which can maintain local defects in gray-scale images and remove all homogeneity and directional texture direction information. , however manipulating the frequency content associated with the homogeneous defect-free region can have a dramatic effect on the frequency content of the defect region

Images