Biometric systems have become a vital part of our present day automated systems. Every individual has its unique biometric features in terms of face, iris and periocular regions. Identification/recognition of a person by using these biometric features is significantly studied over the last decade to build robust systems. The periocular region has become the powerful alternative for unconstrained biometrics with better robustness and high discrimination ability. In the proposed paper, various local descriptors are used for the feature extraction of discriminative features from the regions of full face, periocular and city block distance is used as a classifier. Local descriptors used in the present work are Local Binary Patterns (LBP), Local Phase Quantization (LPQ) and Histogram of Oriented Gradients (HOG) and Weber Local Descriptor (WLD). FRGC database is used for the experimentation to compare the performance of both periocular and face biometric modalities and it showed that the periocular region has a similar level of performance of the face region using only 25% data of the complete face.
Mendeley helps you to discover research relevant for your work.
CITATION STYLE
Kishore Kumar, K., & Trinatha Rao, P. (2018). Periocular region based biometric identification using the local descriptors. In Advances in Intelligent Systems and Computing (Vol. 673, pp. 341–351). Springer Verlag. https://doi.org/10.1007/978-981-10-7245-1_34