Fast Automatic Exposure Adjustment Method for Iris Recognition System
Vitaly Gnatyuk, Sergey S. Zavalishin, Xenya Yu Petrova, Gleb Odinokikh, Alexey M. Fartukov, Alexey Danilevich, Vladimir Eremeev, Juwoan Yoo, Kwanghyun Lee, Hee-Jun Lee, Daekyu Shin, Ivan A. Solomatin · 2019
In this paper, we propose a novel algorithm for automatic camera parameter adjustment, which is exploited for getting the correct image exposure required for iris recognition. We use two-step processing, where the first step adjusts the camera parameters on the basis of a single shot, and the second step applies precise iterative adjustment. In order to get the correct iris exposure, we use a weighted mask, which is constructed offline using a set of face images. In contrast to the existing algorithms, our method does not need to be calibrated for a particular camera sensor. We show that the proposed method significantly decreases false rejection rate caused by incorrect image exposure and reduces recognition time.