Feature Extraction and Reconstruction of Medical Images using Two-Dimensional Principal Component Analysis

Feature Extraction and Reconstruction of Medical Images using Two-Dimensional Principal Component Analysis Srinivasa K Reddy T Jaya Abstract
Two-Dimensional Principal Component Analysis (2DPCA) is a classical technique used to reduce the cost of computation than standard PCA. In 2DPCA, images are treated as vectors and appear image as a matrix which is further computed and results as Eigenvalues consisting of lower dimensionality as compared to PCA. 2DPCA depends on the image matrix which is a computationally most efficient method than PCA used to enhance feature extraction speed and high accuracy. 2DPCA is represented as an image matrix, its Co-Variance matrix is computed with the image matrix directly without converting into a 1D vector, and Eigenvectors are obtained for feature extraction. 2DPCA computes an accurate Co-Variance matrix and finds Eigenvectors most efficiently. K-Nearest Neighbor (KNN) algorithm is used for classification. 2DPCA is the best method to obtain reconstruction accuracy than PCA. The main advantage of 2DPCA is less time required for feature extraction and to provide the highest reconstruction accuracy. For testing and evaluating 2DPCA performance, we are conducted several experiments using different databases such as IRMA, WANG, etc., for different medical images and observed that reconstruction accuracy depends on increasing the number of principal components. 03 01 2021 012012 http://dx.doi.org/10.1088/crossmark-policy iopscience.iop.org Feature Extraction and Reconstruction of Medical Images using Two-Dimensional Principal Component Analysis Journal of Physics: Conference Series paper Published under licence by IOP Publishing Ltd http://creativecommons.org/licenses/by/3.0/ https://iopscience.iop.org/info/page/text-and-data-mining 10.1088/1742-6596/1817/1/012012 https://iopscience.iop.org/article/10.1088/1742-6596/1817/1/012012 https://iopscience.iop.org/article/10.1088/1742-6596/1817/1/012012/pdf https://iopscience.iop.org/article/10.1088/1742-6596/1817/1/012012/pdf https://iopscience.iop.org/article/10.1088/1742-6596/1817/1/012012 https://iopscience.iop.org/article/10.1088/1742-6596/1817/1/012012/pdf IEEE Tran. Neu. Nwks. Movellan 13 1450 2002 10.1109/TNN.2002.804287 Face Recog. by Indent. Compt. Analy Pattn. Recog. Yang 35 2002 From Ima. Vect. to Matx: A straight forward img. Proj. Tech. IMPCA Vs PCA IEEE Trans. on pattn. Analy. and Mach. Intel. Yang 26 131 2004 10.1109/TPAMI.2004.1261097 2DPCA: A New app. to Appear.-Based Face Repren. and Recog Science Direct Elsevier Neu. Nwks Kang 18 585 2005 Gen. 2DPCA for face img. Repren. and Recog Pattn. Rocog. Letts. Wang 26 57 2005 10.1016/j.patrec.2004.08.016 The equiv. of 2DPCA to line-based PCA ACTA Automtica Sinica Li-Wei 31 2005 Is 2DPCA A New Technq Neu. Compng Zhou 69 224 2005 2- Directional 2-Dimensional PCA for effint. face repren. and recog Hongchuan 2006 1-D PCA, 2D-PCA to n-D PCA Anbang 2006 Compl. 2DPCA for Face Recog IEEE Tans. System. Man cybern. Part cybern Wang 36 194 2006 10.1109/TSMCB.2005.852471 On Img. Matx. based feature extran. algorms Int. J. of Elect. and Comp. Engg. Venkatramaphanikumar 6 1610 2016 Face Recognition with Modular Two-Dimensional PCA under controlled illumination variations Mao 1625 2016 Sci. Jour. of Inform. Sutarti 6 64 2019 Compn. of PCA and 2DPCA Accu. with KNN Classification in Face Img. Recog Int. Jour. of Innova. Tech.and explor. Engg. Srinivasa 9 1852 2020 10.35940/ijitee.D1152.029420 Medi. Img. Retriev. using Two Dimen. PCA