ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

Implementation of Partial Face Recognition using Directional Binary Code

Journal: International Journal of Linguistics and Computational Applications (Vol.4, No. 1)

Publication Date:

Authors : ;

Page : 48-51

Keywords : Face recognition; partial face recognition; feature set matching; feature alignment; image matching; bio metrics.;

Source : Downloadexternal Find it from : Google Scholarexternal


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.

Last modified: 2017-12-23 04:47:45