STATISTICAL-METHODS TO COMPARE THE TEXTURE FEATURES OF MACHINED SURFACES

Texture studies play a paramount role in many image processing applica tions. In this paper an attempt is made to study the textural features of machined surfaces (grinding, milling and shaping) using the most w idely used statistical methods, viz, co-occurrence matrix approach, th e amplitude varying rate statistical approach (AVRS) and the run lengt h matrix approach. Textural features derived from these matrices are s tudied and analysed. A new matrix for the qualitative evaluation of su rfaces, namely the gray-level difference-pixel distance matrix, is pre sented and its usefulness in texture analysis is analysed. The feature s calculated from these matrices are correlated with surface parameter s, such as roughness, and the different features are studied for class ification of these surfaces. Copyright (C) 1996 Pattern Recognition So ciety. Published by Elsevier Science Ltd.