Color face recognition method based on quaternion non-convex penalty sparse principal component analysis

Abstract

The invention discloses a color face recognition method based on quaternion non-convex penalty sparse principal component analysis, and belongs to the field of mode recognition and artificial intelligence. The method comprises the following steps: firstly, encoding red, green and blue channels of a color image by utilizing quaternion, constructing a complex representation form of a quaternion matrix, then calculating a quaternion covariance matrix, and carrying out characteristic decomposition on the quaternion covariance matrix to obtain a principal component vector; and introducing a non-convex penalty L1 / 2 norm as a sparse constraint term to obtain a new quaternion non-convex penalty sparse principal component analysis (QHSPCA) optimization model, and solving a sparse solution of the model by adopting a coordinate descent method and an immobile point iteration method, and finally realizing face recognition by using a nearest neighbor classifier. Experiments on a Geoga Tech face database show that the QHSPCA method provided by the invention has relatively good recognition performance, and the calculation efficiency is also improved.

Description

technical field [0001] The invention relates to a color face recognition method based on quaternion non-convex penalty sparse principal component analysis, which belongs to the field of pattern recognition and artificial intelligence. Background technique [0002] As one of the important biometric identification technologies, face recognition technology has been more and more widely used in criminal investigation security, video surveillance, identity verification, smart payment and other fields. Although face recognition technology has broad application prospects, the recognition performance of many existing methods is still affected by factors such as expression, posture, and illumination. Compared with fingerprints, retina, etc., there is a big gap in both recognition rate and anti-counterfeiting. [0003] The traditional principal component analysis (PCA) algorithm will first grayscale the color face image, but the grayscale processing will cause the color information o...

AI Technical Summary

Problems solved by technology

Cadima et al. used the hard threshold method to truncate elements whose absolute value is less than a given threshold in the principal component loads to 0, which improved the interpretability of the principal components, but the principal components given by this method are easy to identify wrong original variables.

Hausman fixed the value of the load in a discrete set, such as {-1,0,1}, but the sparsity of the load obtained by this method is not ideal, and the variance of the sparse principal component is greatly reduced

Inspired by LASSO, I.T.Jolliffe directly put L 1 Norm constraints are introduced into the principal component model, and the first sparse PCA algorithm based on convex optimization is proposed, but L 1 Norm is just L 0 An approximation of the norm, the resulting principal component loadings are not sparse enough

Images