A Defect Detection Method Based on Gradient Multi-threshold Optimization

Abstract

The present invention is a method for optimizing defect detection based on gradient multi-thresholds. Firstly, the optimized threshold is obtained through a simplified mean value clustering algorithm; secondly, 100 modules in each sample gradient image are counted through a normal distribution model, and the calculated Obtain a dynamic threshold; again, by dividing the sample image into blocks, and based on a statistical method, extract the maximum value of the pixel and the maximum value of the pixel difference in the module; finally, on the basis of modularization, judge through multiple thresholds and obtain the output The modules are combined into a complete image, and the median filter is performed on it to obtain the image of the defect detection result. The present invention improves the accuracy of the algorithm and reduces the time cost of the algorithm in the iterative process through the simplified mean value clustering algorithm; based on the statistics and normal distribution model, the edge is extracted in the gradient image, which significantly increases the accuracy and accuracy of the algorithm. Treatment effect: the invention can quickly and accurately detect the defects of wood, and improve the application range of detection and the quality of produced wood.

Description

technical field [0001] The invention relates to a defect detection method based on gradient multi-threshold optimization. Background technique [0002] In image segmentation processing, an image is divided into components that have a strong correlation with real-world objects or regions, which are mainly divided into the following three categories: global-based segmentation, edge-based segmentation, and local-based segmentation. At present, image segmentation is mainly used for the fine extraction of image edges. For the detection of strong edges, it mainly focuses on global segmentation and local segmentation, that is, thresholding segmentation. However, for some specific occasions, such as wood defect detection, etc., in addition to filtering In addition to removing the noise of the image itself, it is also necessary to remove the annual rings of the wood, etc., and retain the defective parts of the wood. Thresholding segmentation is an ideal method for background and obj...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a defect detection method based on gradient multi-threshold optimization, which is used to solve problems such as inaccurate thresholds, thresholds that cannot change with image fluctuations, too long iterations of optimal thresholding, and complex algorithms, etc., and has defect detection effects Good, fast extraction speed, etc.

Images