• K.MUTHURANI

Abstract Iris Recognition has become one of the most important biometric mechanisms of all time, because of their unique patterns, which helps in finding the individual. When comparing to other traditional methods in biometric system, Iris Recognition ranks first, because of its high performance in identifying. In real-time Iris Recognition, Iris Localization is very important step for Iris Recognition. So, the Iris Masks plays an important role in iris recognition. So, we use Learning- Based algorithms to estimate accurate Iris Masks from Iris Images, which propose to use Figueiredo and Jain’s Gaussian Mixture Models (FJ-GMMs) to model the underlying probabilistic distributions of both valid and invalid regions on iris images. Then instead of using polar coordinates in normalization, we go for Non-Polar coordinate system, which preserves and enhances the geometric structure of an original iris image and is suitable for multi-scale geometric analysis. Then, we employ the normalized energy components as elements of the feature vector and use Support Vector Machine (SVM) to classify the features. In feature extraction instead of Gabor filter banks we adopt Improved Circular Symmetric Filter Bank (ICSFB) to implement multi-scale decomposition. This Learning-based algorithm is implemented in the UBIRIS dataset to achieve high performance result. Index terms - Figueiredo and Jain’s Gaussian Mixture Model(FJ-GMMs), Non-polar coordinate system, Support Vector Machine(SVM), Improved Circular Symmetric Filter Bank(ICSFB).

"An Effective Feature Set Exploration Of Iris Using High Dimensional Density Estimation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 11, page no.147-152, November-2018, Available :http://www.jetir.org/papers/JETIR1811215.pdf

"An Effective Feature Set Exploration Of Iris Using High Dimensional Density Estimation", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 11, page no. pp147-152, November-2018, Available at : http://www.jetir.org/papers/JETIR1811215.pdf