Class Based Semantic Feature Similarity for Efficient Image Mining using BC Patterns
T. Rajendran1, M. Baskar2, T. Gnanasekaran3, N. Mohamed Imtiaz4
1T. Rajendran, Assistant Professor, Department of CSE, GRT Institute of Engineering and Technology, (Tamil Nadu), India.
2Dr. M. Baskar, Professor, Department of CSE, MLR Institute Technology, Dundigal, Hyderabad (Telangana), India.
3Dr. T. Gnanasekaran, Professor, R.M.K. Engineering College, Kavarapetai, (Tamil Nadu), India.
4N. Mohamed Imtiaz, Assistant Professor, Department of CSE, GRT Institute of Engineering and Technology, (Tamil Nadu), India.
Manuscript received on 07 April 2019 | Revised Manuscript received on 20 April 2019 | Manuscript published on 30 April 2019 | PP: 355-358 | Volume-8 Issue-6, April 2019 | Retrieval Number: F3598048619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The Problem of Image Mining Has Been Well studied. Image mining has been approached with several key features like color, texture and shapes. However, the efficiency of image retrieval is still a questioning fact. To improve the performance of image mining, an efficient Class Based Semantic Feature Similarity (CSFS) measure based image mining algorithm is presented in this paper. The method classifies the images under various semantic classes and according to the meanings of semantic class. First, the input image has been applied for noise removal and quality enhancement with Gabor filter and histogram equalization. Second, the input image has been extracted for Binary and Contrast (BC) patterns. Third, the method estimates semantic feature similarity for different classes. Finally a single one has been identified and the images of the class have been returned as result. The proposed algorithm improves the performance of image mining and reduces false classification ratio.
Keyword: Image Mining, Semantics, BC Pattern, CSFS.
Scope of the Article: Data Mining