Medical Image Retrieval using Two Dimensional PCA
Srinivasa Reddy. K1, Jaya. T2

1Srinivasa Reddy. K*, Ph.D. Research Scholar, ECE Dept.,Vels Institute of Science, Technology and Advanced Studies (VISTAS), Chennai, India.
2Jaya.T, Assistant Professor , ECE Dept.,Vels Institute of Science, Technology and Advanced Studies (VISTAS), Chennai, India.
Manuscript received on January 12, 2020. | Revised Manuscript received on January 22, 2020. | Manuscript published on February 10, 2020. | PP: 1852-1856 | Volume-9 Issue-4, February 2020. | Retrieval Number: D1152029420/2020©BEIESP | DOI: 10.35940/ijitee.D1152.029420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Medical image analysis will be used to develop image retrieval system to provide access to image databases using extracted features. Content Based Image Retrieval (CBIR) is used for retrieving similar images from image databases. During the last few years, medical images are grown and used for medical image analysis. Here, we are proposed that medical image retrieval using two dimensional Principal Component Analysis (2DPCA). For extracting medical image features, 2DPCA has advantageous that evaluates accurate covariance matrix easily as much smaller and also requires less time for finding Eigen vectors. Medical image reconstruction is performed with increased values of 2DPCA and observed from results that reconstruction accuracy improves with increase of principal component values. Retrieval is performed for transformed image space by calculating the Euclidean Distance(ED) between 2DPCA values of unknown images with database images. Minimum distance classifier is used for retrieval, which is simple classifier. Simulation results are reported by considering different medical images and showed that simulation results provide increased retrieval accuracy. Further, Segmentation of retrieved medical images is obtained using k-means clustering algorithm. 
Keywords: Covariance Matrix, Feature Extraction, Medical Image Retrieval, 2DPCA.
Scope of the Article: Image Analysis and Processing