Texture Classification Based On Integrated Method

The present paper proposes a novel way of extracting local texture features based on the Morphological Primitive Patterns with grain components (MPP-g) on texton based Local Directional Pattern (LDP) for effective stone texture classification. To reduce the dimensionality, the proposed research used Integrated Logical Compact LDP with OR operation on Textons (ILCLDP-T). Mathematical Morphology (MM) provides an efficient framework for analyzing object shape characteristics (such as size and connectivity) due to its geometry-oriented nature which are not easily accessed by linear approaches. A LDP feature is obtained by computing the edge response values in all eight directions at each pixel position of LBP and generating a code from the relative strength magnitude. The local descriptor LDP is more consistent in the presence of noise and illumination changes, since edge response magnitude is more stable than pixel intensity. The proposed Morphological Primitive Patterns with grain components (MPP-g) on ILCLDP-T are rotationally invariant due to Kirsch Edge Response. The present method experimented on the Dataset consists of various brick, granite, and marble and mosaic stone textures with resolution of 256×256 collected from Vistex, Mayang database and also from natural resources from digital camera. The experimental results and comparison with the other methods show the supremacy of the proposed method over the existing methods.