Automobile coating surface defect detection method and system based on deep learning

Abstract

The embodiment of the invention provides an automobile coating surface defect detection method and a system based on deep learning. The method comprises the steps of acquiring a detection image of a to-be-detected area of an automobile coating surface; uniformly segmenting the detection image into a plurality of small images with set sizes so as to form a small image test set; inputting the smallimage test set into a deep learning network model, and obtaining a detection result list corresponding to the small images of the set size; wherein the set sizes are N types, and N is greater than orequal to 2; and performing de-duplication integration processing on the N detection result lists to obtain a defect detection result. According to the method of the invention, the workload of detection personnel can be effectively reduced, the detection efficiency and the detection precision are improved, and the small defects in the complex area of the automobile coating surface can be efficiently and accurately detected under the non-uniform and uncertain complex illumination condition.

Description

technical field [0001] The invention relates to the technical field of machine vision and image processing, in particular to a method and system for detecting surface defects of automobile coating based on deep learning. Background technique [0002] At present, in the automobile painting workshop, the quality of the automobile painting surface is usually roughly sampled and evaluated by manual visual inspection, that is, the specific area of ​​the outer surface of the automobile body after painting and drying is inspected, and the inspectors visually search for defects. And marked, and then manual statistical records. Since the surface of the car body after painting is smooth and the defects are small and weak, the visibility of the defects is poor. It is necessary to frequently change the visual direction and observation distance to find the defects more effectively. Therefore, the use of manual sampling and visual inspection has a high rate of missed detection, low effic...

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention provides a method and system for detecting defects on the surface of automobile painting based on deep learning, which is used to solve the problem of low recognition rate, large error of inspection algorithm, high hardware cost, and occupation of automobile painting surface defects in the prior art. The defect of large space

Images