Texture analysis and Characterization of Fused Medical Images using NLAF-PCA and SVM
Suneetha Rikhari1, Sandeep Jaiswal2
1Suneetha Rikhari, Department of ECE, SET, MUST, Lakshmangarh, Sikar (Rajasthan), India.
2Sandeep Jaiswal, Department of BME, SET, MUST, Lakshmangarh, Sikar (Rajasthan), India.
Manuscript received on 25 March 2019 | Revised Manuscript received on 02 April 2019 | Manuscript Published on 12 April 2019 | PP: 16-23 | Volume-7 Issue-6C April 2019 | Retrieval Number: F90220476C19/2019©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: Texture is one of the important characteristic of an image. Texture analysis provides the details about the arrangement of pixel intensity values in the spatial domain. The input image is a fused image obtained from Non-Linear Anisotropic filtering in PCA domain (NLAF-PCA) method. Fusion process gives highly informative image as it combines the information from two or more images into a single image. Effective fusion algorithms are required to obtain accuracy of successful diagnosis of diseases. Magnetic resonance (MR) and computed tomography (CT) images are most widely utilized images for analyzing the human body. Any fusion technique is said to be efficient if it is able transfer maximum information from the input image into the fused image without information loss. The features from the fused image are extracted using Discrete Wavelet Transform (DWT). The features Homogeneity, Correlation, Entropy, variance etc. are calculated which describe the texture analysis. The extracted features are segmented using Support Vector Machine (SVM) classifier. The combination of NLAF-PCA and SVM produces robust results compared to traditional SVM classifier.
Keywords: MR and CT Images, Image Fusion, Non-linear Anisotropic Filtering, Principal Component Analysis and SVM.
Scope of the Article: Image Security