151. Symmetric Uncertainty Based Search Space Reduction for Fast Face Recognition
- Author
-
Vignesh Sankaran, S. Vasuhi, Vaidehi, Shree Nandhini S, Sharmi P, Ranajit Kumar, C. Sweetlin Hemalatha, and Lavanya B
- Subjects
business.industry ,Computer science ,020206 networking & telecommunications ,02 engineering and technology ,Space (mathematics) ,Facial recognition system ,Reduction (complexity) ,ComputingMethodologies_PATTERNRECOGNITION ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Decision Sciences (miscellaneous) ,Computer vision ,Artificial intelligence ,business ,Information Systems - Abstract
Face recognition from a large video database involves more search time. This article proposes a symmetric uncertainty based search space reduction (SUSSR) methodology that facilitates faster face recognition in video, making it viable for real time surveillance and authentication applications. The proposed methodology employs symmetric uncertainty based feature subset selection to obtain significant features. Further, Fuzzy C-Means clustering is applied to restrict the search to nearest possible cluster, thus speeding up the recognition process. Kullback Leibler's divergence based similarity measure is employed to recognize the query face in video by matching the query frame with that of stored features in the database. The proposed search space reduction methodology is tested upon benchmark video face datasets namely FJU, YouTube celebrities and synthetic datasets namely MIT-Dataset-I and MIT-Dataset-II. Experimental results demonstrate the effectiveness of the proposed methodology with a 10 increase in recognition accuracy and 35 reduction in recognition time.
- Published
- 2018