RoIA: Region of Interest Attention Network for Surface Defect Detection

Surface defect detection plays an important role in manufacturing and has aroused widespread interests. However, it is challenging as defects are highly similar to non-defects. To address this issue, this paper proposes a Region of Interest Attention (RoIA) network based on deep learning for automatically identifying surface defects. It consists of three parts: multi-level feature preservation (MFP) module, region proposal attention (RPA) module, and skip dense connection detection (SDCD) ones, where MFP is designed to differentiate defect features and texture information by feature reserved block, RPA is developed to locate the position of the defects by capturing global and local context information, and SDCD is proposed to better predict defect categories by propagating the fine-grained details from low-level feature map to high-level one. Experimental results conducted on three public datasets (e.g., NEU-DET, DAGM and Magnetic-Tile) demonstrate that the proposed method can significantly improve the detection performance than state-of-the-art ones and achieve an average defect detection accuracy of 99.49%.

I. Introduction

Nowadays, automatic surface defect detection is becoming more and more vital in industry [1]. However, the traditional detectors of defects (e.g., gray-level co-occurrence matrices, scale invariant feature transform, and local binary patterns) usually focus on texture analysis to simulate the difference between defective and non-defective regions by using manual features [2], where common methods include statistical ones [3], structural-based ones [4], filter-based ones [5] and model-based ones [6]. Unfortunately, these approaches are typically proposed for specific categories of defects or surfaces, such as steel and/or wood surfaces, as well as inclusions and/or cracks, so that it is difficult to generalize them into the detection of different categories of defects and surfaces.