Fabric defect detection under complex illumination based on an improved recurrent attention model

• Published in: Journal of the Textile Institute Vol. 112; no. 8; pp. 1273 - 1279
• Main Authors: Wang, Huang, Duan, Fajie, Zhou, Weiti
• Format: Journal Article
• Language: English
• Published: Manchester Taylor & Francis 03.08.2021; Taylor & Francis Ltd
• Subjects: Algorithms; Artificial neural networks; Cognitive tasks; Complex illumination; Convergence; Decoupling; deep deterministic policy gradient; defect detection; fabrics; Illumination; issues and policy; lighting; Machine learning; neural networks; recurrent attention model; variance
• ISSN: 0040-5000; 1754-2340; 1754-2340
• DOI: 10.1080/00405000.2020.1809918

To solve the problem of fabric defect detection under complex illumination conditions, the Recurrent Attention Model (RAM) which is insensitive to illumination and noise differences has been introduced. However, the policy gradient algorithm in the RAM has some problems, such as the difficulty of convergence and the inefficiency of the algorithm due to the shortcomings of round updating. In this paper, the Deep Deterministic Policy Gradient- Recurrent Attention Model (DDPG-RAM) algorithm is proposed to solve the problems of policy gradient algorithm. Although the decoupling of the reinforcement learning task and classification task will lead to the inconsistency of the data, the gradient variance will be smaller, and the convergence speed and stability will be accelerated. Experiment results show that fabric defects can be detected by the proposed DDPG-RAM algorithm under complex illumination conditions. Compared with RAM and the Convolutional Neural Network (CNN), the accuracy of the decoupled algorithm is 95.24%, and the convergence speed is 50% faster than that of the RAM.