Iris Image Enhancement And Fusion Recognition Under Natural Light

Iris recognition has been widely regarded as one of the most stable and accurate biometrics technology. Iris recognition systems using iris images captured in visible light have several advantages compared to using near infrared(NIR) images, and draw attention from biometrics researchers. The iris image acquired under natural light may be degraded by non-uniform illumination, which results in the iris texture’s low resolution and low contrast. The recognition accuracy may be affected. However, the color information can be used as an important clue for iris classification. So, fusing the color information and texture is becoming a new method.This paper describes a method for enhancing the iris textures on the V channel of HSV space. The enhancement has two steps. First, the image is divided into small blocks and luminance enhancement is carried out in each block by using nonlinear transfer function and bilinear interpolation. Secondly, contrast enhancement by multiscale Gaussian convolution is applied to improve the quality of the image. Moreover, the result of enhancement is evaluated by recognition. For lots of low quality iris images which obtained in visible light, using the image fusion technology to process it.According to the non-rigid deformation characteristics of iris image zoom pupil,proposed using curve fitting technology in iris image registration.Then the registered iris image using pixel level fusion method of wavelet fusion for fusion,the ultimate aim is to make the missing pieces information of low quality iris images fused into an iris image which contains richer information. For feature extraction and recognition, we transfer the iris image into several color space such as YIQ, YUV, YCbCr, HSI, and CMY and extract the color features, which is measured by using the Euclidean distance(ED), chi square distance(CSD), and hamming distance(HD). Then,we design multilevel classifiers based on color information. Finally, we combine the “color information” and ‘‘textural information’’ extracted by 2D-Gabor filter on the basis of the weighted SUM rule to produce a final matching score for recognition. We test the proposed method on UBIRIS.v2 database. Experimental results show that the proposed method has better performance and can achieve higher recognition accuracy.