Abstract—This paper presents an efficient algorithm for iris recognition using the spatial fuzzy clustering with level set method, and genetic and evolutionary feature extraction techniques. The novelty of this research effort is that we deploy a fuzzy c-means clustering with level set (FCMLS) method in an effort to localize the nonideal iris images accurately. The FCMLS method incorporates the spatial information into the level set-based curve evolution approach and regularizes the level set propagation locally. The proposed iris localization scheme based on FCMLS avoids the over-segmentation and performs well against blurred iris/sclera boundary. Furthermore, we apply a genetic and evolutionary feature extraction (GEFE) technique, which uses genetic and evolutionary computation to evolve modified local binary pattern (MLBP) feature extractor to elicit the distinctive features from the unwrapped iris images. The MLBP algorithm combines the sign and magnitude features for the improvement of iris texture classification performance. The identification and verification performance of the proposed scheme is validated using the CASIA version 3 interval dataset.
Index Terms—Iris recognition, fuzzy c-means clustering, level set, modified local binary pattern, and genetic and evolutionary feature extraction.
Brian O’Connor, Kaushik Roy, Joseph Shelton, and Gerry Dozier are with the Computer Science Department, North Carolina Agricultural and Technical State University, Greensboro, NC 27411 USA (e-mail: bpoconno@aggies.ncat.edu; kroy@ncat.edu; jashelt1@aggies.ncat.edu; gvdozier@ncat.edu).
Cite: Brian O’Connor, Kaushik Roy, Joseph Shelton, and Gerry Dozier, "Iris Recognition Using Fuzzy Level Set and GEFE," International Journal of Machine Learning and Computing vol.4, no. 3, pp. 225-231, 2014.