In this paper, we discuss a method to detect defects in industrial products by using Denoising AutoEncoder Generative Adversarial Networks. In previous methods, a defective area is detected by restoring a defective product image which added an artificial defect to a non-defective product image by Denoising AutoEncoder (DAE). Therefore, a defective area is detected by subtracted image of them. We discuss whether further accuracy improvement is possible by introducing a framework of adversarial learning to DAE in order to restore a defective image to a non-defective image clearer.
Inspection of the solder joints on a printed circuit board (PCB) is challenging because such defects cannot be observed directly due to the solder joints being sandwiched between the PCB and an integrated circuit (IC) chip. To solve this problem, automated x-ray inspection, which can perform nondestructive inspection, is generally employed.1,2 In our method, we employed an automated x-ray inspection that collects sliced images of the solder joints by x-ray computed tomography (CT) scans on the x-ray inspection machine and detects defects in the solder joints.
In this paper, we aimed at discrimination of defects under conditions where there is a large number of good products and a small number of defective products. Although automation of a visual inspection is essential to improve the quality of products, either or both of the features extracted by the experts and balanced dataset are needed. We tackled such a problem. By combining AAE, which can extract features following any distribution and Hotelling's T-Square, which is an effective anomaly detection method when data follows a normal distribution, it is possible to discriminate defects with a small number of defective samples.