EFFICIENT COMBINED TECHNIQUES FOR PERSON RECOGNITION WITH COVERED FACE AND EYES
No Thumbnail Available
Date
2020-12-30
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Face is the most common parameter which defines any person uniquely. Face recognition is a
process of identifying or verifying the identity of an individual using their face. Principal
component analysis is algorithm for face recognition. In facial recognition there are some
complexities that degraded the efficiency of face recognition using Principal Component
Analysis for covered face and covered eyes. Iris recognition is a process of detecting a person
uniquely by reading the eyes. Iris recognition can remove the covered face complexities but when
someone wears sunglasses which covered eyes then iris recognition will not work properly. Face
recognition is not efficient for covered face like faces with mask, long beard and naqab. Iris
recognition is not efficient for covered eyes like eyes with sunglasses. To overcome all these
complexities which include covered face or eyes, our proposed efficient models are Combined
PCA-Segmentation, Combined PCA-Daugman and Combined PCA-SVM Face Recognition. In
this work, Principal Component Analysis process will take place combined with Segmentation,
Daugman and Support Vector Machine. Segmentation will help for creating upper and lower face
evaluation separately, Support Vector Machine will help to detect the covered faces to improve
the recognition accuracy. To calculated the accuracy of the systems there are four image datasets
used called ORL, Yale, Real and CASIA which is iris image dataset. This work has used also
real image dataset. For all dataset each model has provided better accuracy than solo PCA. The
motto of this work is to remove the complexities of beard, mustache, hijab and sunglasses at
facial recognition to increase the overall accuracy for improving the face recognition.