110-2 SEMINAR 林秀豪(清大物理)-1110518

Time:1110518 (Wed.) 14:20~16:20
Speaker:Prof.林秀豪(Hsiu-Hau Lin) 國立清華大學物理學系/Department of physics, National Tsing Hua University Title:Deep Exposure – hidden behind natural images
Abstract:Human vision is a powerful sensory system for detecting environmental information. However, its efficiency comes along with built-in fallacies often neglected. Utilizing a machine-learning approach, we reveal universal hidden structures embedded in most natural images and show that 2D natural images can be compressed and thus encoded faithfully by vorticities along 1D boundaries. In addition, a hierarchy of visual information can be constructed according to the human-eye sensitivity. By projecting out the principal components for human vision, the invisible textures of the natural images emerge, providing a promising tool for medical image analysis in the future.
Place:ON-LINE
  • Post author: