Iris image classification method based on depth learning characteristics and Fisher Vector coding model

Abstract

The invention provides an iris image classification method. The method comprises steps that a sample iris image is processed at a construction stage of an iris texture primitive, and the iris texture primitive is acquired; an iris classifier is constructed based on the iris texture primitive and a support vector machine at a construction stage of the iris classifier; target iris images are classified through utilizing the iris classifier at a discrimination stage. The method is advantaged in that iris image classification can be effectively accomplished, high effectiveness and security of iris identification are improved; characteristics acquired through depth learning are utilized to replace characteristics acquired through traditional manual design to extract the iris texture primitive, high precision, high robustness and high reliability are realized, and the method is suitable for iris image classification of multiple application demands such as in vivo detection, race recognition and sex identification; a system safety problem and a large-scale data retrieval problem existing in an iris system productization process are effectively solved.

Description

technical field [0001] The invention relates to the technical fields of computer vision, pattern recognition and machine learning, in particular to a method for classifying iris images based on deep learning features and Fisher Vector coding models. Background technique [0002] With the rapid development of the Internet, the relationship between people is closer and the interaction is more frequent. Identification based on biometrics has attracted people's attention and has penetrated into every aspect of people's daily life. Among many biological characteristics, iris has the advantages of high uniqueness, strong stability, and non-invasiveness. These advantages make the iris particularly suitable for identification and identification of people. It has received more and more attention in the past ten years, and related research and technology have also developed rapidly. Iris recognition can not only be applied to e-commerce, financial securities, information security, tr...

AI Technical Summary

Problems solved by technology

[0006] With the continuous development of hardware and software, the iris recognition system is developing in the direction of user-friendliness and ease of use, and the requirements for user cooperation are reduced, which will lead to problems such as the degradation of iris image quality, which makes it difficult in the actual application system. Find the optimal most discriminative features

With the increase of classification categories, there is still room for improvement in existing iris classification methods, and how to quickly and efficiently classify in iris recognition systems is still a difficult problem

Images