Multiple Guidance Network for Industrial Product Surface Inspection With One Labeled Target Sample.

Abstract

Most automatic product surface inspection methods in industry are data-hungry and task-specific. It is difficult to collect adequate labeled samples in practice due to factors including expensive data annotation cost, inadequate samples for some categories, and limitations on the initial production stage. In this article, a multiple guidance network (MGNet) is proposed to address these issues. In the network, the feature extraction machine (FEM) produces four feature maps of different functions to enhance the inspection ability of the algorithm. Also, the probability map generation (PMG) module is designed for coarse positioning of objects. Moreover, the structures of the mutual guidance and historical guidance (HG) guarantee that the network can fully utilize the information of the auxiliary dataset. Only one support sample containing the labeled objects is required for reference, and the network can determine whether the same labeled objects exist in the query images and locate them. For a comprehensive evaluation of MGNet, three experiments are carried out using three real-world datasets. Experiment results verify that the proposed method is promising for industrial product surface inspection with one labeled target sample.