Defect detection algorithm based on product quantization learning strategy

Abstract

The invention discloses a defect detection algorithm based on a product quantization learning strategy, which is an improved algorithm based on a common Cartesian K-means algorithm, namely a semi-supervised Cartesian K-means algorithm. The method mainly adopts a mode comprising the following three stages: stage 1, determining positions and types of defects, and adopting an optimal reverse prediction algorithm as a detection means; stage 2, carrying out positioning detection on defect positions in structural images detected in the stage 1 also by adopting a mode based on target detection; and stage 3, on the basis of the stage 2 cutting detection images, and sending the cut detection images to a classification model for classification so as to determine final classification and identification results. According to the method, quantization errors of each subspace can be effectively reduced, and the recognition performance is improved.

Description

technical field [0001] The present invention relates to the technical field of data processing and pattern recognition, in particular to a defect detection algorithm based on a product quantitative learning strategy, which is mainly used for image detection and recognition, especially a method based on the different characteristics reflected in the image information, A method for distinguishing and locating different types of defects in an image. It uses computer to carry out quantitative analysis on images, and classifies each pixel or area in the image or image into one of several categories to replace human visual interpretation. The high accuracy rate recognition of the image is realized. Background technique [0002] Defect detection is widely used in cloth defect detection, workpiece surface quality detection, aerospace fields, etc. Traditional algorithms can work well for situations with rule defects and relatively simple scenes, but they are no longer suitable for ...

AI Technical Summary

Problems solved by technology

[0008] The above algorithms have been significantly improved over the research on product quantification algorithms, but all these algorithms still belong to the unsupervised learning framework, which may clearly limit the performance of these algorithms

Images