The impact of a number of samples on unsupervised feature extraction, based on deep learning for detection defects in printed circuit boards

• Main Authors: Volkau, Ihar, Abdul Mujeeb, Dai, Wenting, Erdt, Marius, Sourin, Alexei
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Manufacturing::Quality control; Defect Detection; Image Analysis; Machine Learning; Transfer Learning; Optical Inspection; Unsupervised Learning
• Online Access: https://hdl.handle.net/10356/154941
• Institution: Nanyang Technological University

Deep learning provides new ways for defect detection in automatic optical inspections (AOI). However, the existing deep learning methods require thousands of images of defects to be used for training the algorithms. It limits the usability of these approaches in manufacturing, due to lack of images of defects before the actual manufacturing starts. In contrast, we propose to train a defect detection unsupervised deep learning model, using a much smaller number of images with-out defects. We propose an unsupervised deep learning model, based on transfer learning, that ex-tracts typical semantic patterns from defect‐free samples (one‐class training). The model is built upon a pre‐trained VGG16 model. It is further trained on custom datasets with different sizes of possible defects (printed circuit boards and soldered joints) using only small number of normal samples. We have found that the defect detection can be performed very well on a smooth back-ground; however, in cases where the defect manifests as a change of texture, the detection can be less accurate. The proposed study uses deep learning self‐supervised approach to identify if the sample under analysis contains any deviations (with types not defined in advance) from normal design. The method would improve the robustness of the AOI process to detect defects.