Product appearance defect detection method based on multi-core learning with fuzzy relaxation constraints

Abstract

The invention provides a product appearance defect detection method based on fuzzy relaxation constraint multi-core learning, which belongs to the product quality detection field of machine vision. Firstly, some features of the real-time image are extracted. Then the fuzzy constraint theory is used to quantitatively analyze the mapping relationship between the characteristics and the evaluation indexes. A multi-core learning model is established to classify the appearance defects, and the fuzzy relaxation boundary of each kernel function weight is delineated by combining the mapping quantization relation. The fuzzy relaxation constraint (FRC) method is used to determine the weights of the multi-kernel model and the fuzzy range of the weights. At last, the multi-core learning model with different kinds of defects is obtained by calculating the weights of defects, and the defect detection results are obtained by using the multi-core learning model. The invention adopts the multi-featurefusion multi-core learning classification detection method, which makes the detection range wider, combines the fuzzy relaxation constraint to adapt to different detection requirements, can meet the real-time detection, and has high detection accuracy.

Description

technical field [0001] The invention belongs to the field of product quality inspection based on machine vision, and specifically relates to a method for feature extraction and multi-feature information fusion of real-time collected product images and then for product appearance defect detection. Background technique [0002] With the continuous improvement of people's living standards, consumers also have higher quality pursuits for the quality of home appliances, which requires manufacturers to formulate higher production standards for home appliances that can better meet consumer needs. The appearance defect standards of home appliances are shown in Table 1. Area 1 is the bottom and back, Area 2 is the front, and Area 3 is the top and side. New home appliances that leave the factory often have appearance quality problems, which affect the user's consumption experience and cause certain economic losses to the manufacturer. Traditional manual detection methods cannot solve...

AI Technical Summary

Problems solved by technology

[0018] Existing product appearance detection methods involve a wide range of areas, but for large-scale industrial products, such as household appliances, there is no effective method that can meet the real-time detection standards of industrial production. To solve this problem, the present invention provides a method based on fuzzy The product appearance defect detection method of relaxed constraint multi-core learning adopts the detection scheme of multi-feature fusion combined with multi-core learning classification, which can meet the real-time detection and high detection accuracy

Images