Network model training method, metal surface defect detection method and electronic equipment

Abstract

The invention discloses a network model training method, a metal surface defect detection method and electronic equipment, and belongs to the related technical field of defect detection. The training method comprises the following steps: obtaining and marking metal surface defect data to obtain training samples; performing data enhancement on the training samples by adopting an oversampling method to obtain a training set; replacing a trunk feature extraction network of a target detection model with a lightweight network to obtain a lightweight target detection network; using an NEU-DET data set as a pre-training data set, and sending the pre-training data set into the lightweight target detection network to obtain an improved lightweight target detection network; and inputting the training set into the improved lightweight target detection network for training to obtain a lightweight target detection network model. The invention can effectively realize automatic detection of large-scale metal surface small defects, has high accuracy, has the characteristics of lightweight, high-precision real-time picture monitoring and the like, and can be applied to industrial scenes.

Description

technical field [0001] This application belongs to the technical field of defect detection, and in particular relates to a network model training method, a metal surface defect detection method and electronic equipment. Background technique [0002] In the actual production process of metal, due to the influence of various factors, defects such as scratches and grooves will appear on the metal surface, and these defects will seriously affect the quality of the metal. In order to ensure product quality, manual visual inspection is required. However, the metal surface itself will contain lines, drilling holes and oil stains, etc., and the degree of distinction from defects is not high. The traditional manual visual inspection is very laborious, and the surface defects cannot be judged in time and accurately, and the efficiency of quality inspection is difficult to control. [0003] In recent years, algorithms based on deep convolutional networks have had a huge impact. In th...

AI Technical Summary

Problems solved by technology

[0005] The current target detection algorithm builds a deeper and more complex network while improving performance, but these networks do not meet the needs of embedded devices and mobile devices in terms of scale and speed, and their application in the industrial field is narrow

[0006] Current target detection algorithms require a large amount of data for training, and it is difficult to collect sufficient defect target data in actual industrial scenarios

[0007] In industrial scenarios, the metal surface itself contains lines, drill holes, and oil stains, etc., and the degree of discrimination from defects is not high, and the groove defects on the metal surface are small, and the scratches are thin and shallow, resulting in the low accuracy of most detection methods and easy detection. Occurrence of missed detection, etc.

Images