Ternary Patterns and Moment Invariants for Texture Classification

Texture extraction and classification is the key feature that is used in pattern recognition and classification. Binary patterns are very powerful discrimination operators that are able to extract texture features irrespective of its illumination changes. This paper mainly focuses on extraction of fabric texture patterns that are used in discriminating the defects and the non-defects. A ternary pattern is a powerful tool for extracting the microstructures of the images, used for feature extraction that has robustness towards the illumination invariance. On the other hand, a Zernike moment which is simultaneously invariant to similarity transformation and rotation is also explained. Experimental analysis is conducted both on standard texture images and fabric images. The performance of the proposed approach is evaluated using SVM, KNN and Bayes classifiers.