Dynamic image fine feature extraction method based on machine vision

Abstract

In the dynamic image feature extraction of machine vision, a single key frame is often used to extract, which affects the accuracy of parameters when obtaining features. Therefore, this paper proposes a method of dynamic image subtle feature extraction based on machine vision. Firstly, the multi key frame extraction method of dynamic image under machine vision is designed. After obtaining the key frame image, the image is enhanced, and then the gray feature is extracted. According to the gray feature, the entropy feature of the image is obtained, and the shape feature is extracted to complete the subtle feature extraction. In order to verify the feasibility of the method, design experiments, using the design method and the methods in literature [1], literature [3], literature [4] to extract the features of dynamic images obtained by machine vision. The experimental results show that the designed feature extraction method is more accurate and has better performance and feasibility.