Surface Inspection
Surface inspection aims to automate the detection of defects on various surfaces, improving quality control and efficiency across manufacturing and infrastructure monitoring. Current research emphasizes developing advanced algorithms, such as reinforcement learning for trajectory optimization and transformer networks for feature extraction and defect classification, to enhance accuracy and speed, often incorporating multi-modal sensing (visual and tactile) for improved defect identification. These advancements are significant for industries requiring high-precision surface quality assessment, leading to improved product quality, reduced waste, and enhanced safety in applications ranging from manufacturing to infrastructure inspection.
Papers
Global Context Aggregation Network for Lightweight Saliency Detection of Surface Defects
Feng Yan, Xiaoheng Jiang, Yang Lu, Lisha Cui, Shupan Li, Jiale Cao, Mingliang Xu, Dacheng Tao
CINFormer: Transformer network with multi-stage CNN feature injection for surface defect segmentation
Xiaoheng Jiang, Kaiyi Guo, Yang Lu, Feng Yan, Hao Liu, Jiale Cao, Mingliang Xu, Dacheng Tao
Decision Fusion Network with Perception Fine-tuning for Defect Classification
Xiaoheng Jiang, Shilong Tian, Zhiwen Zhu, Yang Lu, Hao Liu, Li Chen, Shupan Li, Mingliang Xu