An Iris Segmentation Scheme Using Delogne -- Kåsa Circle Fitting Based on Orientation Matching Transform
Pei-Chung Chung, Chia Ming Lyu, Jui Liu, Shyr Shen Yu · 2014
Automatically and reliably segment the iris from the captured eye images is considered to be the most important stage in an iris recognition system, which greatly influences the overall recognition accuracy and processing speed of the whole system. The iris segmentation is to extract the iris from its surrounding noises, like as pupil, sclera, eyelashes and eyebrows. A novel iris segmentation scheme should remove as much noise as possible. Based on edge maps the presented algorithm uses the orientation matching transform to find the rough outer and inner iris boundaries. It then uses Delogne-Kåsa circle fitting (DKCFS) to eliminate the outlier points of the rough outer and inner iris boundaries to extract a more precise iris area from an eye image. In the extracted iris region the proposed algorithm utilizes the differences among the intensity and position characteristics of the iris, eyelid and eyelashes to detect these noises to obtain highly accurate iris segmentation. The algorithm was applied on iris image database, UBIRIS. v1. The experimental results show that the proposed algorithm is effective and efficient in iris segmentation.