A Compact Convolutional Neural Network for Textured Surface Anomaly Detection

Convolutional neural methods have proven to outperform other approaches in various computer vision tasks. In this paper we apply the deep learning technique to the domain of automated visual surface inspection. We design a unified CNN-based framework for segmentation and detection of surface anomalies. We investigate whether a compact CNN architecture, which exhibit fewer parameters that need to be learned, can be used, while retaining high classification accuracy. We propose and evaluate a compact CNN architecture on a dataset consisting of diverse textured surfaces with variously-shaped weakly-labeled anomalies. The proposed approach achieves state-of-the-art results in terms of anomaly segmentation as well as classification.