Textural Features Corresponding to Visual Perception

TLDR

Textural features aligned with human visual perception are valuable for optimal feature selection and texture analyzer design. The authors aim to address these issues by analyzing their causes and applying more sophisticated techniques. They computationally approximated six basic textural features—coarseness, contrast, directionality, line‑likeness, regularity, and roughness—and attempted similarity measurements using these features. The computational measures correlated well with human perception for 16 texture patterns, yet discrepancies revealed fundamental problems in digital texture analysis.

Abstract

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.