Synthesis method and device for iris features

Abstract

The invention discloses a method and device for synthesizing iris features. The method includes: acquiring iris features of N iris images satisfying preset conditions, the iris features including noise templates and iris feature codes, and the coded values ​​of each bit of the noise templates represent The effectiveness of this bit; calculate the composite noise template according to the noise template of N iris features, the effective bits of the composite noise template are formed by the fusion of the regions formed by the effective bits of the N noise templates; according to the composite noise template to N iris The iris feature codes of the features are counted to obtain the synthetic iris feature codes; the iris feature codes corresponding to all the noise templates that are valid on the same bit appear the most frequently on the corresponding bits of the bit, which is the synthetic iris feature codes. The encoded value of the bit; the synthetic iris feature is obtained by combining the synthetic noise template and the synthetic iris feature encoding. The invention increases the effective area of ​​the iris and improves the quality of iris features.

Description

technical field [0001] The invention relates to the field of iris image processing, in particular to a synthesis method and device for iris features. Background technique [0002] A complete iris identification system mainly consists of five aspects: iris image acquisition, iris image preprocessing, iris image feature extraction and iris feature comparison. The application mode of the iris identification system can generally be divided into two types: registration and authentication. In the iris identification system, the feature extraction of iris image is a key link, and the quality of the extracted iris features directly affects the accuracy and speed of registration and authentication. [0003] Taking the iris registration process as an example, in practical applications, it is generally only registered once, but it will be authenticated multiple times during use. If the iris feature template is not very good during registration, it will affect the subsequent authentica...

AI Technical Summary

Problems solved by technology

[0004] For the method of judging the quality of iris images during registration, because each iris image will be judged for quality during registration, the complexity of the program is increased, the registration time is long, and the quality of the iris images of the collected user is not good or the user's location If it is not suitable, it will cause difficulties in registration, registration failure, and the need for users to register multiple times. Therefore, this registration method has the problems of long registration time, difficult registration, and poor user experience.

[0005] For the method of registering multiple iris image samples at the same time, on the one hand, it takes up system memory, and on the other hand, it may affect the subsequent authentication process. For example, a large-scale database search is required during authentication, because there are many feature templates registered at the same time and the quality cannot be guaranteed. , will increase the risk of misidentification, and the authentication time will be longer. Therefore, this registration method may have a higher misidentification rate and increase the comparison time (for example, 5 feature samples, each authentication needs to be compared five times)

Images