Crack Segmentation for Low-Resolution Images using Joint Learning with Super- Resolution
Yuki Kondo, Norimichi Ukita
Abstract
This paper proposes a method for crack segmentation on low-resolution images. Detailed cracks on their high-resolution images are estimated by super resolution from the low-resolution images. Our proposed method* <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> optimizes super-resolution images for the crack segmentation. For this method, we propose the Boundary Combo loss to express the local details of the crack. Experimental results demonstrate that our method outperforms the combinations of other previous approaches.
Topics & Concepts
Resolution (logic)SegmentationArtificial intelligenceComputer scienceBoundary (topology)Low resolutionComputer visionImage resolutionImage segmentationSuperresolutionPattern recognition (psychology)High resolutionJoint (building)Image (mathematics)MathematicsGeologyRemote sensingStructural engineeringEngineeringMathematical analysisInfrastructure Maintenance and MonitoringIntegrated Circuits and Semiconductor Failure AnalysisIndustrial Vision Systems and Defect Detection