Defect Detection and Visualization of Understanding Using Fully Convolutional Data Description Models

Abstract

Recently, image data-based deep learning models such as Convolutional Neural Network (CNN), Support Vector Machine (SVM), Convolutional Auto Encoder (CAE), Variable Auto Encoder (VAE), Fully Convolution Network (FCN) and so on have been applied to defect detection for various kinds of industrial products and materials. For example, after some defect is detected in an inspection process using a CNN model, Gradient-weighted Class Activation Mapping (Grad-CAM) or Occlusion Sensitivity is applied to visualization process of the defect areas. This means that a defect detection process and visualization one have to be separately employed in the production line. In this paper, Fully Convolutional Data Description (FCDD) approach is applied to the defect detection and its concurrent visualization of industrial products and materials. Our developed MATLAB application for building defect detection models has already allowed users to efficiently design, train and test various kinds of models such as an originally designed CNN, transfer learning-based CNN, SVM, CAE, VAE, FCN, and YOLO, however, FCDD has not been supported yet. This paper includes the software development to build FCDD models. The usefulness of FCDD models in terms of defect detection is compared with conventional transfer learning-based CNN models.