Implementation of Partial Face Recognition using Directional Binary Code

Apply

Implementation of Partial Face Recognition using Directional Binary Code

Journal Title: International Journal of Linguistics and Computational Applications - Year 2017, Vol 4, Issue 1

Abstract

— In many real-world scenarios especially some unconstrained environments, human faces are occluded by other objects, therefore it is difficult to obtain fully holistic face images for recognition. Most ancient face recognition algorithms have faith in face alignment and face standardization, which is highly infeasible. To address this, a effective partial face recognition approach is required to recognize persons of interest from their partial faces A new partial face recognition approach based on Directional Binary Code is proposed. It is used for automatic conversion of partial faces to gallery faces by aligning partial face patches to gallery faces automatically. DBC is applied on image to encode the directional edge information. It captures the spatial relationship between any pair of neighborhood pixels in a local region along a given direction. The extracted features from the given image are used for face recognition. It reflects the image local feature. It is robust to occlusions as well as illumination changes.

Authors and Affiliations

Pavithra N.

Keywords

EP ID EP642667
DOI -
Views 132
Downloads 0