Textural Features Corresponding to Visual Perception
Hideyuki Tamura, Shunji Mori, T. Yamawaki · IEEE Transactions on Systems Man and Cybernetics · 1978
Textural features corresponding to human visual perception are very useful for optimum feature selection and texture analyzer design. We approximated in computational form six basic textural features, namely, coarseness, contrast, directionality, line-likeness, regularity, and roughness. In comparison with psychological measurements for human subjects, the computational measures gave good correspondences in rank correlation of 16 typical texture patterns. Similarity measurements using these features were attempted. The discrepancies between human vision and computerized techniques that we encountered in this study indicate fundamental problems in digital analysis of textures. Some of them could be overcome by analyzing their causes and using more sophisticated techniques.
Cited by 2,153 works. doi:10.1109/tsmc.1978.4309999
Authors
References
- Textural Features for Image Classification
- Edge and Curve Detection for Visual Scene Analysis
- Digital Picture Processing
- Picture processing and psychopictorics
- A law of comparative judgment.
- Visual texture analysis
- A Comparative Study of Texture Measures for Terrain Classification
- Distance functions on digital pictures
- Visual Pattern Discrimination
- Texture analysis using gray level run lengths