This paper proposes a novel framework for the use of eye movement patternsfor biometric applications. Eye movements contain abundant information aboutcognitive brain functions, neural pathways, etc. In the proposed method, eyemovement data is classified into fixations and saccades. Features extractedfrom fixations and saccades are used by a Gaussian Radial Basis FunctionNetwork (GRBFN) based method for biometric authentication. A score fusionapproach is adopted to classify the data in the output layer. In the evaluationstage, the algorithm has been tested using two types of stimuli: random dotfollowing on a screen and text reading. The results indicate the strength ofeye movement pattern as a biometric modality. The algorithm has been evaluatedon BioEye 2015 database and found to outperform all the other methods. Eyemovements are generated by a complex oculomotor plant which is very hard tospoof by mechanical replicas. Use of eye movement dynamics along with irisrecognition technology may lead to a robust counterfeit-resistant personidentification system.
展开▼
