Recognition of Partially Occluded Face using Block Based Mean Weighted Local Binary Pattern Feature and Adaptive Sparse Classifier

Authors

  • Ch.Rathna Jyothi
  • D.Sree Lakshmi

Abstract

In recent literature related to the problem of face recognition under partial occlusion is a big challenge for the researchers who are working in this domain. The recognition performance of any face recognition system under partial occlusion needs to be improved.To shed some light in this area this paper addresses the face recognition problem partial occlusion due to scarf and sunglasses. Intially the face image is divided in to occluded and non occluded regions, the non occluded portion of the face image is only used for face recognition. For detecting the occluded area the input image is divided in to number of sub blocks and then each block is checked for occlusion using Fuzzy Segmentation. Mean weighted local binary pattern features are extracted from non occluded portion and are given to the adaptive sparse classifier in order to recognize the image. The method is implemented on different datasets and the results were promising.

Downloads

Published

2020-04-07

Issue

Section

Articles