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

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.