Exploring Faster RCNN for Fabric Defect Detection
Hao Zhou, Byunghyun Jang, Yixin Chen, David Troendle
Abstract
This paper presents a fabric defect detection network (FabricNet) for automatic fabric defect detection. Our proposed FabricNet incorporates several effective techniques, such as Feature Pyramid Network (FPN), Deformable Convolution (DC) network, and Distance IoU Loss function, into vanilla Faster RCNN to improve the accuracy and speed of fabric defect detection. Our experiment shows that, when optimizations are combined, the FabricNet achieves 62.07% mAP and 97.37% AP50 on DAGM 2007 dataset, and an average prediction speed of 17 frames per second.
Topics & Concepts
Convolution (computer science)Computer scienceArtificial intelligencePyramid (geometry)Feature (linguistics)Function (biology)Pattern recognition (psychology)Object detectionFeature extractionBackbone networkDeep learningComputer visionArtificial neural networkPhysicsOpticsBiologyPhilosophyComputer networkEvolutionary biologyLinguisticsIndustrial Vision Systems and Defect DetectionInfrastructure Maintenance and MonitoringAdvanced Neural Network Applications