6533b86ffe1ef96bd12cd1da

RESEARCH PRODUCT

Local Directional Multi Radius Binary Pattern

subject

description

Face recognition becomes an important task performed routinely in our daily lives. This application is encouraged by the wide availability of powerful and low-cost desktop and embedded computing systems, while the need comes from the integration in too much real world systems including biometric authentication, surveillance, human-computer interaction, and multimedia management. This article proposes a new variant of LBP descriptor referred as Local Directional Multi Radius Binary Pattern (LDMRBP) as a robust and effective face descriptor. The proposed LDMRBP operator is built using new neighborhood topology and new pattern encoding scheme. The adopted face recognition system consists of three stages: (1) face detection and alignment to normalize the input images to a common form if needed; (2) feature extraction using the proposed descriptor in order to calculate the histogram, which represents the feature vector and (3) face recognition through a supervised image classification task using the simple K-Nearest Neighbors classifier. Simulated experiments on ORL, YALE and FERET under different illumination or facial expression conditions indicate that the proposed method outperforms other texture descriptors and other existing works of the literature.