Contact Lens Detection for Security

Gerald Cayabyab
2019 International Journal for Research in Applied Science and Engineering Technology  
This paper feature an efficient extraction and matching approach on eye with or without contact lens to innovate authentication process. The proposed feature extraction and matching approach is develop based on FGM (Feature Group Matching) which extract the key points and descriptor of each images using the two feature extraction algorithm which are SIFT (Scale-Invariant Feature Transform) and SURF(Speeded-Up Robust Features) and to match the key points and descriptors using FLANN based
more » ... FLANN based matcher. The major advantages of the developed approach are the simplicity and accuracy as compared to the prior extraction and matching approaches developed for contact lens detection images. The new used approach was tested in AMD Ryzen 5 2500U with 2GHz processor, 4GB Mobile RAM, dual graphic card and GPU rendering of RX 560 x with 5GB. The experimental results obtained from IIITD-Contact lens Iris Database and publicly available images and respectively achieved better performance in terms of simplicity and accuracy as compared to the previous proposed methods and Filipino Iris Database as an added contribution to the field of contact lens.
doi:10.22214/ijraset.2019.5282 fatcat:ow5gy53tbfemdpq5bwhpbkie3i