A New 3-D PCA Regression Method for Manifold Dimension Reduction with Image Analysis

Abstract

In this paper, we propose a new 3-D pca regression method for manifold dimension reduction with applications to image analysis. The proposed method is a novel image analysis method consisting of a regression algorithm of a structure designed based on an improved manifold 3-DPCA and an autoencoder capable of nonlinear expansion of PCA for efficient dimension reduction in large-capacity image data input. With the configuration of an autoencoder, a regression manifold 3-DPCA, which derives the best hyperplane through three-dimensional rotation of image pixel values, and a Bayesian rule structure similar to a deep learning structure, are applied. Conduct experiments for performance verification. Image is improved using fine dust image, and accuracy performance evaluation is performed through classification model. As a result, it can be confirmed that it is effective in performing deep learning.