Plastic meal box defect detection method, device and system based on image processing

Abstract

The invention provides a plastic meal box defect detection method, device and system based on image processing. The method comprises the following steps: acquiring a to-be-detected image of a to-be-detected plastic meal box; sequentially carrying out denoising processing and gray processing on the to-be-detected image to obtain a gray image; determining a first probability that any pixel point in the gray image belongs to the background area and a second probability that any pixel point belongs to the target area; calculating a background region entropy according to the first probability, and calculating a target region entropy according to the second probability; determining a to-be-detected threshold value according to the background region entropy and the target region entropy; comparing the gray value of each pixel point in the gray image with a to-be-detected threshold value, and segmenting the gray image according to a comparison result to obtain a target region image; determining the similarity between the target region image and the standard image of the plastic meal box, and comparing the similarity with a preset threshold; and determining whether the to-be-detected plastic meal box has defects or not according to the comparison result. According to the technical scheme, the defect detection accuracy of the plastic meal box is improved.

Description

technical field [0001] The present invention relates to the technical field of measurement and detection, in particular to a defect detection method, device and system for plastic lunch boxes based on image processing. Background technique [0002] At present, the rapid development of the catering takeaway industry has driven a substantial increase in the demand for disposable plastic lunch boxes. In the production process of plastic lunch boxes, defects are prone to occur due to the production process and technical level. Therefore, in order to ensure the quality of plastic lunch boxes, it is necessary to perform defect detection on plastic lunch boxes during the production process. If the product defect rate is too high, timely intervention and adjustments to the production process, such as maintenance of production equipment, etc., to eliminate faults and reduce losses as soon as possible. [0003] At present, the detection of surface defects of plastic lunch boxes is ma...

AI Technical Summary

Problems solved by technology

However, this method has the following problems: fixed interference, there are usually interference features such as trademarks and printings on plastic lunch boxes, which will adversely affect the defect detection process and easily cause misjudgment; texture effects, edge detection methods usually pass gray However, the surface of most lunch boxes has complex textures, and it is difficult to distinguish whether the gray-scale mutation is caused by the texture or the defect during the detection process, which will affect the accuracy of defect detection.

[0005] Therefore, the existing image processing-based surface defect detection method for plastic lunch boxes has the problem of low accuracy.

Images