Image Retrieval Based on Color and Full Texton Matrix Histogram (C&Ftmh) Features
G. BinduMadhavi1, V. Vijaya Kumar2, K. Sasidhar3

1G. BinduMadhavi, Research Scholar of JNTUH, Department of Computer Science and Engineering, Asst. Professor. Anurag Group of Institutions (Autonomous), Hyderabad, India.
2V. Vijaya Kumar, Professor, Dean – Department of Computer Science and Engineering, Anurag Group of Institutions (Autonomous), Hyderabad, Telangana, India.
3K. Sasidhar, Professor, Head of ECM, Srinidhi Institute of Science and Technology, Hyderabad, India.

Manuscript received on 02 June 2019 | Revised Manuscript received on 10 June 2019 | Manuscript published on 30 June 2019 | PP: 507-521 | Volume-8 Issue-8, June 2019 | Retrieval Number: H6681068819/19©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 (

Abstract: One of the challenging tasks of image processing is image retrieval. Image retrieval is performed by matching the features of the image. In the literature many researchers derived local texture features and produced diverse feature descriptors for efficient image retrieval. Most of the local features are derived based on the relationship between centre pixels versus with boundary or neighboring pixels over a local neighborhood. In this paper we propose a new local descriptor based on full texton index pattern using HSV color space. The HSV color space is used to derive color, intensity and brightness features in the form of histograms. This paper transforms the V-plane image into full texton index (FTi ) image. A co-occurrence matrix is derived on FTi image and this results full texton matrix (FTM). This paper derives the co-occurrence structural features in the form of histogram and color histogram features are concatenated to derive feature vector. This feature vector is named as “color and full texton matrix histogram” (C&FTMH). The proposed C&FTMH framework is tested on the five popular databases and results are compared with state-of-art methods with color features.
Keyword: HSV, Texton, Histograms, Structural, Color features.
Scope of the Article: RetrievalStructural Engineering.