A Feature Memory Rearrangement Network for Visual Inspection of Textured Surface Defects Toward Edge Intelligent Manufacturing

TL;DR

This paper introduces FMR-Net, an unsupervised neural network that detects textured surface defects efficiently by using synthetic anomalies, contrastive learning, and a novel feature rearrangement approach, suitable for edge manufacturing environments.

Contribution

The paper presents a novel unsupervised defect detection method incorporating synthetic defects, contrastive learning, and feature rearrangement, advancing real-time inspection in industrial textured surface manufacturing.

Findings

Achieves state-of-the-art accuracy in defect detection.

Demonstrates robustness in noisy, real-world scenarios.

Effective deployment in edge-cloud manufacturing systems.

Abstract

Recent advances in the industrial inspection of textured surfaces-in the form of visual inspection-have made such inspections possible for efficient, flexible manufacturing systems. We propose an unsupervised feature memory rearrangement network (FMR-Net) to accurately detect various textural defects simultaneously. Consistent with mainstream methods, we adopt the idea of background reconstruction; however, we innovatively utilize artificial synthetic defects to enable the model to recognize anomalies, while traditional wisdom relies only on defect-free samples. First, we employ an encoding module to obtain multiscale features of the textured surface. Subsequently, a contrastive-learning-based memory feature module (CMFM) is proposed to obtain discriminative representations and construct a normal feature memory bank in the latent space, which can be employed as a substitute for defects and fast anomaly scores at the patch level. Next, a novel global feature rearrangement module (GFRM) is proposed to further suppress the reconstruction of residual defects. Finally, a decoding module utilizes the restored features to reconstruct the normal texture background. In addition, to improve inspection performance, a two-phase training strategy is utilized for accurate defect restoration refinement, and we exploit a multimodal inspection method to achieve noise-robust defect localization. We verify our method through extensive experiments and test its practical deployment in collaborative edge--cloud intelligent manufacturing scenarios by means of a multilevel detection method, demonstrating that FMR-Net exhibits state-of-the-art inspection accuracy and shows great potential for use in edge-computing-enabled smart industries.