Scalable Image Search System
Ansila Henderson1, Kavitha K V2
1Ansila Henderson, Computer Science and Engineering, SCTCE Pappanamcode, Thiruvananthapuram (Kerala), India.
2Kavitha K.V, Computer Science and Engineering, SCTCE Pappanamcode, Thiruvananthapuram (Kerala), India.
Manuscript received on 15 August 2015 | Revised Manuscript received on 25 August 2015 | Manuscript Published on 30 August 2015 | PP: 197-200 | Volume-4 Issue-6, August 2015 | Retrieval Number: F4212084615/15©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: Several applications such as fingerprint identification, biodiversity information systems, digital libraries, crime prevention, medicine, historical research, among others uses the image search system for searching similar images. The goal of the scalable image search system is to support image retrieval based on content properties such edge and texture, encoded into feature vectors. Hashing technique is used to embed high dimensional image features into hamming space. The image search can be performed in real-time based on Hamming distance of compact hash codes. An extensive experiment on flickr image dataset demonstrates the performance of the proposed methods.
Keywords: Gray-Level Co-Occurrence Matrix (GLCM), Homogeneous Texture Descriptor (HTD, The Edge Histogram Descriptor (EHD).
Scope of the Article: Image analysis and Processing