Apparatus and method for iris recognition using multiple iris templates

Abstract

The present invention relates to an apparatus for iris recognition using multiple iris templates which are registered for each individual, and to an apparatus for performing the method. The method comprises the steps of: acquiring single or multiple eye images of a person to be registered; generating a registered iris template group from the acquired single or multiple eye images, and registering the group in a database; photographing an eye with a camera multiple times and acquiring images thereof for authentication; generating multiple iris templates for authentication from the photographed and acquired eye images to configure an iris template group for authentication; comparing the iris template group for authentication with the registered iris template group for each registered person stored in the database; and performing authentication or identification using the result of the comparison.

Description

technical field [0001] The present invention relates to an iris recognition method using a plurality of iris templates registered for each individual and an apparatus for implementing the method. The step of comparing the template sets with each other and the step of performing authentication or identity confirmation according to the comparison result. Background technique [0002] Generally, the iris recognition method performs authentication or identity confirmation by comparing an iris area extracted from an eye image captured by a camera with an iris area extracted from another eye image. If the surrounding environment is not good when shooting the eyes with the camera, it is possible that the acquired eye image is out of focus, noise enters in the iris area, or the iris area is covered by eyelashes, eyelids, reflections of light, etc., or just Takes an image of the eye that has problems such as a part of the iris. [0003] In the case of the iris camera of Sarnoff, st...

AI Technical Summary

Problems solved by technology

If the surrounding environment is not good when shooting the eyes with the camera, it is possible that the acquired eye image is out of focus, noise enters in the iris area, or the iris area is covered by eyelashes, eyelids, reflections of light, etc., or just Image of the eye that captures problems such as a part of the iris

[0003] In the case of the iris camera of Sarnoff, strong lighting is used to capture the eyes of subjects far from the camera, but this lighting reflects on the iris part of the acquired eye image, and as a result, the accuracy of iris recognition decreases. s reason

[0004] Therefore, the problem in the eye image is one of the causes of erroneously extracting the iris area from the eye image, and even if the iris area is successfully extracted, it will cause the iris recognition accuracy to decrease depending on the situation.

[0006] One of the existing methods that is different from the above method is to use an image registration technique to selectively light up multiple lights and obtain multiple face images, and then obtain images without specular reflections produced by spectacle lenses. Face image method, this method can also be applied to iris image, but it is very difficult to use multiple images taken under different conditions as mentioned above to form a complete image like a jigsaw puzzle

[0007] Especially in iris recognition, as mentioned above, in the case of extracting iris features from the above-mentioned images after obtaining multiple iris images from the same object and applying image registration technology to obtain an iris image, since different iris images are combined There is a problem that the correct iris features cannot be easily extracted from the above completed iris image due to the stitching mismatch regions generated during the process

[0008] In addition, in the existing iris recognition, in the case of a person wearing glasses, the part reflected by the glasses lens may appear in the eye image captured by the camera due to the lighting at the time of shooting, and this reflected part appears on the iris In the case of the area, there is a problem that the accuracy of iris recognition decreases

Images