ILivSpot: Secure Biometric System based on Iris Liveliness Detection
Sunil Kumar1, Vijay Kumar Lamba2, SurenderJangra3

1Sunil Kumar*, Computer Science and Engineering, I.K.G. Punjab Technical University, Jalandhar, Punjab, India.
2Vijay Kumar Lamba, Electronics and Communication Engineering, Global College of Engineering and Technology, Ropar, Punjab, India.
3SurenderJangra, Computer Science and Applications, Guru Teg Bahadur College, Sangrur, Punjab, India.
Manuscript received on November 23, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 1720-1726 | Volume-9 Issue-2, December, 2019. | Retrieval Number:  B2376129219/2019©BEIESP | DOI: 10.35940/ijeat.B2376.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Liveliness detection aims to determine whether the iris presented to the sensor belongs to a live subject or it is a fake one. Liveliness detection is to classify input sample into one of the category between fake and real. This work proposes an improved biometric system which recognizes the liveliness of the iris samples in order to increase the security. In this work, the dataset of UBIRIS.v2 is used where input samples are segmented into pupil, sclera and iris and these individual segments are filtered to enhance the quality of the samples. Further, the segmentation using Fuzzy C-Mean and K-Mean clustering methods is done. Different features are extracted and fused thereafter. Fused features are then used as a training data. For testing purpose, a combined dataset of original and fake samples is used and accuracy of the system is calculated with a novel hybrid classifier AHyBrK which is a combination of ANN and KNN. Results achieve 97% accuracy in differentiating between fake and live which is 8.2% better than KNN and 5.1% better than ANN.
Keywords: Iris, Liveliness, Segmentation, Filters, Fuzzy C-Mean, K-Mean, Features, Fusion, ANN, KNN, AHyBrK Classifier, Hybrid Classification.