Convolutional neural network and active learning-based ceramic tile surface defect recognition method

Abstract

The invention discloses a convolutional neural network and active learning-based ceramic tile surface defect recognition method. The method comprises the following steps of: (1) obtaining and preprocessing an image; (2) establishing a training set; (3) establishing and training a convolutional neural network; (4) carrying out active learning; (5) carrying out model iteration; and (6) carrying outonline detection. Compared with the prior art, the method has the advantages that (1) features of ceramic tile surface defects are automatically extracted by using the convolutional neural network, sothat good priori knowledges are not required in the aspect of defect feature extraction, and multiple defect types in one to-be-detected image can be recognized; and (2) active learning is imported in convolutional neural network training, so that labeling cost of samples is effectively decreased and the model convergence is accelerated.

Description

technical field [0001] The invention belongs to the technical field of defect detection and recognition, and more specifically relates to a tile surface defect recognition method based on convolutional neural network and active learning. Background technique [0002] In the production process of ceramic wall and floor tiles, due to improper manufacturing processes or collisions during handling, defects such as lack of glaze, cracks, and scratches will appear on the surface of the tiles, which will affect the aesthetics of the tiles as building decoration materials. The detection of surface defects is still largely done manually. This method is not only inefficient, but also easily affected by the intuitive feelings of the inspectors. In recent years, the automatic detection of product surface defects using machine vision has been paid more and more attention. [0003] In the prior art, there are a few tile surface defect detection methods, which mainly use manual selection a...

AI Technical Summary

Problems solved by technology

The flow-based method means that unlabeled samples enter the classifier one by one, and the classifier considers whether to mark it or discard it. This method has a high time complexity.

Images