Classification of Textures Based on Ternary Transition Motif Matrix Features
B. Kishore1, V. Vijaya Kumar2 

1B. Kishore Research Scholar, Sri Chandra Sekhar Indra Saraswathi Viswa Maha Vidyalaya University, Kanchipuram & Asst. Professor, Dept. of CSE, Manipal Institute of Technology, MAHE, Manipal.
2V. Vijaya Kumar, Professor & Dean , Dept. of CSE & IT, Aurag Group of Institutions , Hyderabad, Telangana, India.

Manuscript received on 03 March 2019 | Revised Manuscript received on 08 March 2019 | Manuscript published on 30 July 2019 | PP: 1499-1508 | Volume-8 Issue-2, July 2019 | Retrieval Number: B2150078219/19©BEIESP | DOI: 10.35940/ijrte.B2150.078219
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: The various classification methods proposed in the literature are mostly extracted either local features or global features or color features. After an exhaustive study on various local, global and color descriptors this research found that one type of features may not yield good classification results. To address this paper, proposed new variant that integrates the color features derived from HSV color plane and transition based scan features. This paper initially converted RGB color plane image in to HSV color plane. The individual histograms of H, S and V plane are extracted as one of the features and these are named as pure color features. This paper derives a novel extension to the exiting motif frame works of the literature. The proposed ternary transition motif matrix (TTMM) is completely different from the existing motif frameworks and it is derived on the V-plane of the HSV color model. The TTTM scans the given 2×2 grid in a fixed format by visiting each pixel position exactly once. The TTMM derives a ternary transition pattern based on the relationship between grey level intensities of current pixel and its immediate pixel of scan instead of traversing on the incremental difference. The proposed TTMM derives a unique code for each 2×2 grid, ranging from 0 to 80 and replaces the 2×2 grid with this value. The co-occurrence matrix derived on this ternary transition motif (TTM) coded image is named as TTMM and it holds the spatial relationship between the TTM coded grids. The gray level co-occurrence matrix (GLCM) features derived on TTMM are integrated with the pure color features to derive final feature vector. This descriptor is applied on six popular databases using machine learning classifiers. The results are compared with existing motif based and other local based approaches. The results exhibit the high classification rate of the proposed method over the existing ones. .
Index Terms: Ternary Transition, Motif, Spatial Relation, Machine Learning.

Scope of the Article: Machine Learning