Effective Local Features Matching Based Rapid Iris Recognition with Interference Elimination Pre-processing for Identity Identification
Abstract— In this paper, the effect ive local features matching based iris matching methods are developed for identity identification. To avoid the eyelid/eyelash interferences, the proposed interference elimination pre-processing scheme is effectively used to remove the image region due to the eyelid/eyelash obstruction, and the retrieved iris region only locates near the pupil around the ring area for the recognition. The iris features are enhanced by the Contrast Limited Adaptive Histogram Equaliza t ion (CLAHE) and Gabor filtering processes. Then the efficient local features matching based technologies, i.e. the Scale-Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF) methods, are applied to the iris features matching. The local features matching technology uses the local features of images, and it keeps the feature invariance for the changes of rotation, scaling, and brightness. Finally, the Fast Library for Approximate Nearest Neighbors (FLANN) and the Random Sample Consensus (RANSAC) algorithms are used to increase the matching efficiency. By the similar iris database and the SIFT-based technologies, the proposed SIFTbased approach yields to better Correct Recognition Rate (CRR) and False Acceptance Rate (FAR) in comparison with the previous SIFT-based designs, where the CRR of the proposed design can be up to 97%.
Index Terms— biometric, iris recognition, interference elimination, SIFT/SURF features, personal identifications.
Kun-Cheng Li, Chih-Peng Fan
Department of Electrical Engineering, National Chung Hsing University, TAIWAN
Cite: Kun-Cheng Li, Chih-Peng Fan, "Effective Local Features Matching Based Rapid Iris Recognition with Interference Elimination Pre-processing for Identity Identification," Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering WCSE_2019_SPRING, pp. 22-30, Yangon, Myanmar, February 27-March 1, 2019.