Synthetic Method of Training Samples for Neural Network in Surface Flaw Detection of Parts

Abstract

The invention belongs to the technical field of surface flaw detection, and specifically provides a method for synthesizing training samples of a neural network in part surface flaw detection. The method for synthesizing training samples includes: Step S1: Obtain an image of a sample with defects; Step S2: Obtain a defect image from the image of a sample with defects; Step S3: Extract the image features of the defect image and add disturbances to the image features to generate Training samples. Obtaining training samples through this method only needs to obtain a small number of parts with defects, and by obtaining a small number of images of the surface of defective parts, extract the defects existing in the image to obtain images of various defects, from images of various defects Extract the image features of defects, and then add corresponding perturbations to each image feature to generate a huge number of training samples, which meets the training needs of the neural network and solves the difficulty of obtaining training samples for neural network training, and it is impossible to obtain a large number of training samples The problem.

Description

technical field [0001] The invention belongs to the technical field of surface flaw detection, and specifically provides a method for synthesizing training samples of a neural network in part surface flaw detection. Background technique [0002] The traditional detection method for surface flaws of precision parts is mainly manual detection. The manual detection method is limited by factors such as the working status of the inspectors, the level of detection skills, and the level of proficiency, so it is inevitable that false detections and missed detections will occur. Using manual detection of surface defects of parts has high labor intensity, low detection efficiency and high error rate. [0003] In recent years, with the remarkable effect of deep learning in semantic recognition and image understanding, the object detection method using neural network to automatically train feature expression has been developed more and more rapidly (Krizhevsky A, Sutskever I, Hinton G ...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the difficulty in obtaining training samples for neural network training and the problem that a large number of training samples cannot be obtained, the present invention provides a synthesis of training samples for neural networks in part surface flaw detection. method, the synthesis method includes: step S1: acquiring an image of a part sample with defects; step S2: acquiring a defect image from the image of a part sample with defects; step S3: extracting the image features of the defect image and adding disturbance to the image features to generate training samples

Images