Fabric defect detection method based on frequency spectrum curvature analysis

Abstract

The invention discloses a fabric defect detection method based on frequency spectrum curvature analysis. The method comprises the following steps: eliminating a texture background frequency fraction,namely performing masking shielding on frequency spectrum curvature characteristics of fabric images, and eliminating a frequency fraction of a periodic texture background part so as to obtain a residual frequency spectrum only with defect information; performing multi-channel filtering, namely performing frequency domain filtering on the residual frequency spectrum by using a multi-channel filterso as to separate and enhance defect characteristics at different frequency bands; performing threshold partitioning and fusion, namely performing threshold partitioning on the filtering output images, and fusing partitioning results according to position 'or' operation, thereby obtaining finally single detection result diagrams. By adopting the method, prior knowledge related to fabric texturesand defects is not demanded, good self-adaptivity and interference resistance can be achieved, and automatic on-line detection on fabric defects can be effectively achieved.

Description

technical field [0001] The invention relates to the technical field of visual detection of surface defects of industrial products, in particular to a fabric defect detection method based on spectral curvature analysis. Background technique [0002] In the textile production process, the detection of defects on the surface of the fabric is a key factor affecting the quality of such products. For a long time, the detection of defects on the surface of such products has largely relied on experienced technical workers through manual visual inspection. The shortcomings of low efficiency, low precision, low reproducibility, and tedious work have become constraints for manufacturers to improve their products. The key bottleneck of improving quality and enhancing market competitiveness. For example, practice shows that the human visual system can only detect 50-70% of fabric surface defects, with an accuracy of no more than 80%, and the existence of surface defects will reduce the ...

AI Technical Summary

Problems solved by technology

However, in the actual production environment, the state of the system is prone to drift due to illumination changes, foundation vibration, fluctuations in the tension of the guide roller, inherent elastic deformation of the fabric material, and other random disturbances. Due to the cumulative effect, the final image to be tested will be different from the There are large deviations between the "standard" template images, such as the differences in the relative deflection angle, position offset, expansion and contraction deformation, resolution, image grayscale and contrast, etc.

These deviations will cause the detection accuracy of the system to seriously drop or fail, so the production line has to be shut down frequently for lengthy and tedious system adjustment and calibration

Images