Singular value feature extraction of color image and its application for recognition

摘要

A new tool of feature extraction and recognition of color image is introduced. It is based on the quaternion representation of color image and quaternion matrix algebra, which are discussed firstly in the paper. Then the singular value (SV) feature vector of a color image is introduced and its many important properties are proved. The properties are very useful for the description and recognition of color image. Then a method for color image recognition is presented. As an application of SV feature vector, the experiment of color image recognition is made and the experiment results are satisfactory.