Method, device and system for detecting tire defects

Abstract

The invention relates to a method, device and system for detecting tire defects. The method comprises the following steps of acquiring an X-ray image of a tire; inputting the X-ray image into a trained Mask R-CNN model to carry out defect identification; outputting an identification graph with the defect marks, wherein the Mask R-CNN model training process comprises the following steps of acquiring the X-ray image of the tire, and performing segmentation of a set pixel size on each image by using an image segmentation software; marking the segmented image through a visual image annotator; andtaking the marked image as a training set to carry out adaptive training on the Mask R-CNN model. Compared with the prior art, the defect detection and the classification can be carried out on the detected image at the same time through the trained Mask R-CNN model, so that the defect detection accuracy is obviously improved.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a method, device and system for detecting tire defects. Background technique [0002] With the rapid development of the automobile industry, the use of tires continues to increase, and the quality of the tire itself has become the guarantee of people's property and life safety. Therefore, the quality inspection of each factory tire has become an important part of tire production. The software of the traditional tire inspection system is complex in operation and poor in practicability. The most important part of defect detection is to observe the X-ray image of the tire manually, which greatly reduces the accuracy and efficiency of tire inspection. The use of computers to analyze and identify X-ray images can greatly improve work efficiency, effectively overcome misjudgments and missed judgments caused by human factors in manual evaluation, and make the evaluation proces...

AI Technical Summary

Problems solved by technology

However, most of the existing detection methods have the following problems: 1. It is necessary to set thresholds or parameters suitable for specific defects according to the characteristics of different types of defects, so that these tire internal defect detection and identification algorithms are limited to a certain extent in practical applications. Not universal

2. For tire X-ray images containing internal defects, due to the inherent structural shading of the tire itself, background shading and defect textures are prone to aliasing and are difficult to distinguish, so it is not easy to judge the existence of complex image defects, and the type and shape of defects And the change of the boundary will make the detection algorithm relying on geometric features less robust, and it is prone to missed detection and false detection; or the estimation deviation of the size of the defect area is large, the defect extraction is incomplete, and the geometric shape of the extracted defect is greatly different.

Images