A Novel Approach for Classification of Textures Through Morphological Skeleton Based Shape Representation Schemes on Moment Invariants

The Hu moment invariant features of shapes are useful in image processing for both recognition and classification. Recognition methods that match object images with their skeleton couldn’t resolve well complex object’s recognition and classification problem. The disadvantage of these shape representation schemes is that they yield a poor classification and recognition rate. The classification requires a human intervention, thus the shape representation and classification methods are not automatic. To address these problems the paper presents a novel and effective method of shape representation by morphological skeleton based method. The shape features are evaluated on the proposed morphological skeleton method by suitable numerical characterization derived from moment invariant measures for a precise classification. The proposed Morphological Skeleton based Shape Representation scheme (MSSR) derives a novel scheme of shape representation based on morphological skeleton theory using Enhanced Hu Moments (EHM). This novel scheme of shape representation is applied on original, noisy, rotated and scaled images. The experimental results clearly show the efficacy of the present method.