Measurement of Defocus Level in Iris Images Using Different Convolution Kernel Methods

Abstract

During the video and fixed image acquisition procedure of an automatic iris recognition system, it is essential to acquire focused iris images. If defocus iris images are acquired, the performance of the iris recognition is degraded, because iris images don't have enough feature information. Therefore it's important to adopt the image quality evaluation method before the image processing. In this paper, it is analyzed and compared four representative quality assessment methods on the MBGC iris database. Through methods, it can fast grade the images and pick out the high quality iris images from the video sequence captured by real-time iris recognition camera. The experimental results of the four methods according to the receiver operating characteristic (ROC) curve are shown. Then the optimal method of quality evaluation that allows better performance in an automatic iris recognition system is founded. This paper also presents an analysis in terms of computation speed of the four methods.

Local Quality Method for the Iris Image Pattern

“…However, to carry out the local quality assessment a Kang's kernel is conducted (Figure 4). This election was done after analyzing the results presented by Colores et al [7]. In this work, it was shown that Kang's kernel takes less time that the Daugman's kernel.…”

“…Note that in this work, the pupil region tically located. A square region of interest (SROI) wh res of iris information is determined from PROI cen to analyze the high and low frequencies from all pi quality assessment stage evaluates all images coming fr work realized in [2,4,7]). In this phase, the area of PRO ned.…”

“…Therefore, it is important in all iris recognition systems to ensure the biometric information quality in that region. According to [7], the iris image quality is determinate by two factors: defocus and blur. These factors are considered visually similar.…”

“…Hence, spectral analysis of the frequency suggests that an effective way to estimate the degree of focus is measuring its total energy at higher spatial frequencies. The quality assessment in our system begins with a global analysis of all images in an iris video, in which the whole image is evaluated with a kernel to rapidly select a set of high quality images as it is described by Colores et al in [7]. It is important to note that the global stage provides a rough good quality images.…”

“…Motivated by this idea, we propose as part of a video quality assessment module that our research group is currently developing [2][3][4]7], a new local quality iris image method based on spectral energy analysis. The figure 1 shows how the iris video sequence is first globally analyzed to quickly determine the quality of the whole image and obtain a small quality image set [4].…”