Title :
Local descriptors based face recognition engine for video surveillance systems
Author_Institution :
Fac. of Electr. Eng. & Commun., Brno Univ. of Technol., Brno, Czech Republic
Abstract :
The paper deals with the local descriptors based face recognition engine for video surveillance systems, where LBP and POEM face descriptors are involved. The FERET database is used for optimal parameters setting with regard to ratio of recognition rate and computational time. The multiple-local-thresholds mechanism is proposed for face template generation and classification task. The engine is verified by using the PubFig database and own database of images from a real surveillance system. The achieved results are suitable to be used in a video surveillance system operating in real-time.
Keywords :
face recognition; image classification; video surveillance; vocabulary; FERET database; LBP face descriptor; POEM face descriptor; PubFig database; face recognition engine; face template classification task; face template generation task; image database; multiple-local-thresholds mechanism; video surveillance system; Databases; Face; Face recognition; Histograms; Lighting; Video surveillance; Face recognition; LBP extraction; POEM extraction; multiple-local-thresholds;
Conference_Titel :
Telecommunications and Signal Processing (TSP), 2013 36th International Conference on
Conference_Location :
Rome
Print_ISBN :
978-1-4799-0402-0
DOI :
10.1109/TSP.2013.6614062
