Abstract
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 without defects. We propose an unsupervised deep learning model, based on transfer learning, that extracts 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 background; 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.
Highlights
Accepted: 21 December 2021The automatic optical inspection (AOI) of printed circuit boards (PCBs) has always been an important area in any manufacturing process of electronic items, and a variety of methods have been developed by research communities
We develop a method of AOI using machine learning (ML)/DL methods
The performance measures of defect detection for different architectures are provided in Tables 1 and 2 for solders and in Tables 3 and 4 for PCBs
Summary
The automatic optical inspection (AOI) of printed circuit boards (PCBs) has always been an important area in any manufacturing process of electronic items, and a variety of methods have been developed by research communities. Manual inspection is the oldest approach to optical inspection [4]. It is, being replaced by computer vision-based methods, with a goal to be more flexible and exclude human subjectivity. New emerging approaches in AOI include machine learning (ML)-based methods [2,5,6], which have been proved to be far more successful than algorithmic approaches in many other areas of image processing, such as face recognition
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have