Reliable CBIR System for Fabric Images Based on NSCT and LDP Features
V. Alan Gowri Phivin1, A.C. Subhajini2
1V. Alan Gowri Phivin, Research Scholar, Noorul Islam Centre for Higher Education, Kumaracoil (Tamil Nadu), India.
2Dr. A.C. Subhajini, Assistant Professor, Department of Computer Applications, Noorul Islam Centre for Higher Education, Kumaracoil (Tamil Nadu), India.
Manuscript received on 13 December 2018 | Revised Manuscript received on 22 December 2018 | Manuscript Published on 30 December 2018 | PP: 328-335 | Volume-8 Issue-2S, December 2018 | Retrieval Number: 100.1/ijeat.B10691282S18/18 ©BEIESP
Open Access | Editorial and Publishing 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: Digital images play an inevitable role in human life and hence, the utilization of images grow day-by-day. Though the advanced storage technology helps in massive data storage, efficient retrieval system is the need of this hour and this issue is well-addressed by Content Based Image Retrieval (CBIR) systems. The CBIR systems are widely present for healthcare and remote sensing domain. However, the presence of CBIR systems is found to be limited for fabric images. Taking this as a challenge, this work presents a CBIR system exclusively meant for fabric images by extracting color and texture features. When the user passes the search query image to the CBIR system, the features of the query image is compared with the features of the images in the dataset, which is performed by ensemble classification. The performance of the proposed CBIR system is found to be satisfactory in terms of retrieval accuracy and time consumption.
Keywords: CBIR, Color and Texture Feature, Image Retrieval.
Scope of the Article: Image Security