Injection molding product surface image defect identification method based on transfer learning

Abstract

The invention discloses an injection molding product surface image defect identification method based on transfer learning. The surface defect image of the non-injection molding product is used as a source domain data set; the surface defect image of the injection molding product is used as a target domain data set; carrying out defect category marking on the source domain data set, carrying out domain information marking on all images, establishing a CNN model, inputting the two data sets into the CNN model for training, obtaining a first feature map of a sample through extraction of a plurality of convolutional layers by the CNN model, and outputting a predicted defect classification result through a full connection layer; establishing a migration learning model, constructing a migrationloss function, migrating the source domain data set as knowledge to the CNN model according to the migration loss function, and performing optimization iteration to obtain a target CNN model; and collecting an injection molding product image with surface defects, and inputting the injection molding product image into the target CNN model for testing to obtain a predicted defect classification result. The method is high in identification accuracy, and solves the problem that samples for identifying the surface defects of the injection molding product are lack.

Description

technical field

[0001] The invention relates to the technical fields of computer vision and industrial automation, in particular to a method for identifying surface image defects of injection molded products based on migration learning. Background technique

[0002] The surface of injection molded products is affected by many factors such as molds and raw material characteristics, and is closely related to the processing environment, product cooling time, and post-processing technology. It is prone to various defects and seriously affects product quality; its characteristics can reflect the quality of injection molded products. The formation mechanism of surface defects of injection molded products is complex and manifests in various forms, making it difficult to quantify. The identification of surface defects has always been a difficult problem. Since the surface defect detection technology based on machine vision is an intuitive and non-contact quality detection method, it...

Images