Abstract
Most research on face recognition has focused so far on identification from full frontal/profile facial images. We have reported earlier on a study that assesses the usefulness of partial faces for face recognition. We expand on our earlier results as we now assess if face recognition performance changes if the left half or the right half of the face is chosen for analysis. Our approach employs Ensemble of Radial Basis Functions (ERBF) networks. The motivation for ERBF comes from their ability to cope with the inherent variability in the image formation and data acquisition process. The database used to assess the comparative merit of the left vs. right half of the face consists of face images from 150 different subjects. The subjects pose across ±5° rotation for a total of 3,000 images. The experimental results, using average Cross Validation performance, indicate that there is no significant difference if the left half (96%) or the right half (94%) of the face is used.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
