Two-dimensional asynchronous code comparison method

Abstract

The invention discloses a two-dimensional asynchronous coding comparison method, which not only considers the rotation difference of pixels, but also takes into account the error tolerance of iris inner and outer circle segmentation errors, and realizes the two-dimensional asynchronous comparison of iris pixels in the angular direction and radial direction . Compared with the traditional one-dimensional pixel comparison method (that is, only considering the movement correction in the iris angle direction), the invention considers the segmentation error in the iris pixel process. Compared with the synchronous two-dimensional pixel comparison (that is, the overall movement correction in the radial direction and the angular direction), the comparison method of this method is more flexible. This method not only covers the method of synchronous two-dimensional comparison, but also allows two-dimensional pixels to be dislocated and overlapped within a reasonable range, so the present invention can better adapt to the center shift and radius that occur in the iris segmentation process The error has the advantages of small calculation amount and fast detection speed.

Description

technical field [0001] The invention relates to the technical field of iris recognition, in particular to a two-dimensional asynchronous code comparison method. Background technique [0002] The texture feature of random distribution of iris is a natural and high-confidence identification of human beings. Therefore, iris recognition has become one of the important means of identity verification, which is the trend of technology and market development. [0003] The iris recognition process generally includes iris segmentation, conversion of iris space coordinates to polar coordinates, iris texture enhancement, iris pixel and pixel comparison. The present invention mainly relates to the pixel comparison link in the iris recognition process. [0004] The iris is an organ used to adjust the size of the pupil. It is ring-shaped when viewed from the front. The inner and outer circles of the iris refer to the outer edge of the pupil and the outer edge of the iris respectively; the...

AI Technical Summary

Problems solved by technology

Since the pixels strictly depend on the segmentation results of the inner and outer circles, the seemingly reasonable segmentation error may lead to misjudgment in some cases

Still using the example of the elliptical pupil mentioned above, the result of segmentation may be biased towards the circle with the largest number of fitting points or an average circle. It is reasonable to consider both cases from the perspective of fitting, but in space coordinates In the process of converting to polar coordinates, the expanded image may be very different, and this difference will also lead to differences in pixels

In this case, it is obviously unreasonable to only consider the difference in rotation and ignore the segmentation error

Images