Hierarchical Defect Detection Based On Reinforcement Learning

Fen Fang, Qianli Xu, Joo-Hwee Lim

Abstract: In this paper, we propose a novel reinforcement learning (RL) based method for defects detection in high-resolution (HR) images. e.g. cracks and scratches on the surfaces of buildings, constructions, and products. Our innovation leverages RL to explore challenging images in progressive manner, using pre-trained deep learning (DL) detection as feedback mechanism. First, The DL model is pre-trained on low resolution (LR) images with relatively high defect background ratio (DBR). The RL agent is trained by optimizing a policy network according to feedback of DL model on selected regions of HR images with fairly low DBR to coarsely predict defective region by executing two actions: defective region selection and region refinement. Then, the selected defective regions are evaluated using the DL model to generate final defect region which will be mapped back to the HR images. Experimental results on HR crack and scratch images indicate that our method is able to achieve state-of-the-art performance with 0.976 and 0.965 F1-score respectively.