An Approach for Classification of Preprocessed Textures Based On Boundary Moments
M. Rama Bai
Dr. M. Rama Bai, Professor in Dept of CSE, Mahatma Gandhi Institute of Technology, Hyderabad, India.
Manuscript received on May 24, 2013. | Revised Manuscript received on June 13, 2013. | Manuscript published on June 30, 2013. | PP: 286-291 | Volume-2, Issue-5, June 2013. | Retrieval Number: E1802062513/2013©BEIESP

Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Texture classification is one of the problems which have been paid much attention on by image processing scientists. Consequently, many different methods have been proposed to solve this problem. In most of these methods the researchers attempted to describe and discriminate textures based on linear and non-linear patterns. The present paper describes a novel and effective method of shape classification by combining innovative preprocessing techniques, morphological boundary method and Hu moments. To offer better classification rate, first innovative preprocessing methods are applied on various texture images. Preprocessing mechanisms describe various methods of converting a grey level image into binary image with minimal consideration of the noise model. Then shape features are evaluated using HM by suitable numerical characterization derived from moment invariant measures on the proposed Morphological Boundary(MB) method for a precise classification. This proposed MB derives a new shape descriptor to address the image classification problem by combining boundary extraction and Hu moment(HM) invariants information. A good comparison is made between these methods by combining preprocessing techniques, boundary extraction and Hu moments. This texture classification study using MB and HM has given a good performance. The experimental results clearly show the efficacy of the present method.
Keywords: Image classification, shape representation, morphological operation, Hu moment invariants, boundary extraction, preprocessing techniques, structuring element.