Tire X-ray defect detection method based on twin distance comparison

Abstract

The invention belongs to the technical field of image recognition and detection, and particularly provides a tire X-ray defect detection method based on twin distance comparison, which comprises the following steps: acquiring a set of pictures of a standard picture, a normal picture and a defect picture of a specific tire pattern; labeling the sample set of the X-ray detection picture according todifferent types of pictures, and dividing samples with labeling information into a training set, a verification set and a test set; preprocessing the X-ray detection picture; establishing a Siamese Network model; training the Siamese Network model based on the training set, iterating the training process for multiple periods, and finally selecting parameters enabling the Siamese Network model tobe highest in accuracy; and after the obtained Siamese Network model is loaded, judging whether a defective part exists in the X-ray detection picture or not. Compared with a traditional method, the detection method has the advantages that the detection effect on unobvious defects can be greatly improved, the detection method is suitable for X-ray films shot by different models, tire patterns andX-ray machines, the burden of tire quality inspection personnel can be reduced, and tire quality control is facilitated.

Description

Technical field [0001] The invention belongs to the technical field of tire defect detection and mainly implements a tire X-ray defect detection method based on twin distance comparison during the tire defect detection process. Background technique [0002] The tire production process is very precise, and errors in any link may result in inferior tires. The quality of tires is closely linked to traffic safety, so strict quality supervision is necessary. One of the important tire quality inspection links is to take X-ray images of the tires, and then use the X-ray images to determine whether the current tires have any defects. [0003] The traditional method of tire X-ray defect detection is to use an X-ray machine to take pictures of the tires and then arrange for quality supervisors to determine whether the tires have certain defects. There are many disadvantages to manually identifying tire X-ray defects: First, the efficiency is relatively low. The X-ray image of a tire ...

AI Technical Summary

Problems solved by technology

There are many unfavorable factors in using manual identification of tire X-ray defects: first, the efficiency is relatively low, the X-ray image of a tire is generally relatively large, and it takes tens of seconds for skilled quality inspectors to completely determine whether a tire is defective Secondly, the discrimination accuracy is not high, and there are many misjudgments and missed judgments. People who look at the display screen for a long time are prone to fatigue. Or the judgment of the defect category is wrong, resulting in missed judgment; finally, long-term manual identification will cause great damage to the health of quality inspectors

[0004] At present, there are some tire X-ray automatic detection algorithms, but they are all based on traditional image processing methods. These methods can only detect relatively obvious defects. For relatively obscure defects (such as air bubbles), the detection rate of the modified method is not ideal.

Images