Abstract
Gabor wavelet has proved to be an effective tool in extracting important features from the face images. In this research work we are proposing a face recognition system which uses Gabor filter bank to create Gabor feature images. The Gabor feature images with their different orientation and scale has increased the feature dimensionality. To reduce these features and form the final feature descriptor a local approach based on the regional histogram formation is used. In this approach, the featured images are divided into different regions. The histogram of each region is calculated and concatenated to form the final feature descriptor. Chi square similarity measure is used for classification. The effectiveness of the algorithm is justified on the face images which have illumination variations and pose variations in it.
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 callMore From: International Journal of Advanced Research in Computer Science
Disclaimer: 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.
