Iris recognizing method

Abstract

The present invention is a method of determining the position of the iris of the eyeball in the digital image obtained from the visible part of the user's eyeball, so as to establish a digital image file that fully expresses the texture information of the iris, and the digital image The file is processed to extract the digital texture features of the iris and perform feature encoding, i.e. the iris code, and compare the iris code with the iris codes of the iris of the same eyeball and / or other eyeballs stored in the database to compare the iris code of the iris The iris recognition method for user authentication is described. The method consists of iris image smoothing, iris boundary detection, iris image transformation, iris texture feature extraction, iris feature encoding and recognition methods. The invention can be used in public security systems, can be used on magnetic cards to replace personal identity codes, and can also be used in information systems to improve access security and the like.

Description

technical field [0001] The invention relates to an iris recognition method, which belongs to the field of computer applications. Background technique [0002] The human iris is the ring-shaped part between the pupil of the human eye and the gray-white sclera (commonly known as the white of the eye). It is a human physiological tissue with rich texture characteristics. As early as the 1960s, medical research has concluded that the texture of iris tissue varies from person to person and remains unchanged throughout life, which can be used as a reliable basis for personal identity authentication (document [1] J.Rohen, "Morphology and Pathology of the Trabecalar Meshwork" in The Structure of Eye, New York: Academic Press, 1961, pp335-341). And because the iris is in the visible part of the eyeball, it is easier to capture images. Therefore, as long as a practical iris recognition method can be given, it is possible to make the recognition of iris tissue in the human eye practic...

AI Technical Summary

Problems solved by technology

[0004] 1. Lack of a practical and non-invasive iris image imaging system;

[0005] 2. The iris positioning scheme adopts a parametric model. The main limitation of this type of method is to have good initial conditions and huge calculation costs;

[0006] 3. The pattern matching scheme used in iris recognition requires huge computational costs

[0012] 1. Image distortion caused by signal noise, this distortion makes it difficult or impossible to detect the inner and outer boundaries of the iris with practical value (i.e. the boundary between the iris and the pupil and the iris and the gray-white sclera) no matter what kind of existing edge detection device is used. the border between);

[0013] 2. Even if the inner and outer boundaries of the iris have been detected more accurately, due to the different image quality of different images of the same iris, or due to the different use environments, it is difficult or impossible to identify certain iris according to the criteria identified by existing systems or methods. Whether the image is from the same iris tissue makes a correct judgment

Images