A fast and accurate iris segmentation method using an LoG filter and its zero-crossings
This work addresses iris segmentation for biometric identification, presenting an incremental improvement in speed and robustness against noise.
The paper tackles iris segmentation by proposing a hybrid method using a Laplacian of Gaussian filter, region growing, and zero-crossings to detect inner and outer circular boundaries, achieving superior accuracy and speed compared to existing methods on three public databases.
This paper presents a hybrid approach to achieve iris localization based on a Laplacian of Gaussian (LoG) filter, region growing, and zero-crossings of the LoG filter. In the proposed method, an LoG filter with region growing is used to detect the pupil region. Subsequently, zero-crossings of the LoG filter are used to accurately mark the inner and outer circular boundaries. The use of LoG based blob detection along with zero-crossings makes the inner and outer circle detection fast and robust. The proposed method has been tested on three public databases: MMU version 1.0, CASIA-IrisV1 and CASIA-IrisV3- Lamp. The experimental results demonstrate the segmentation accuracy of the proposed method. The robustness of the proposed method is also validated in the presence of noise, such as eyelashes, a reflection of the pupil, Poisson, Gaussian, speckle and salt-and-pepper noise. The comparison with well-known methods demonstrates the superior performance of the proposed method's accuracy and speed.