DocumentCode :
1596181
Title :
Estimating face direction from wideview surveillance camera
Author :
Abe, Shinji ; Morimoto, Masakazu ; Fujii, Kensaku
Author_Institution :
Grad. Sch. of Eng., Univ. of Hyogo, Himeji, Japan
fYear :
2010
Firstpage :
1
Lastpage :
6
Abstract :
In this paper, we propose a facial direction estimating system from low resolution facial images captured by surveillance camera. The proposed system first detects moving objects by background subtraction, then detects pedestrians by using histograms of oriented gradients (HOG) and support vector machine (SVM). After that, it trims head area by template matching and finally estimates facial direction by using another SVM. Experimental results show that, when the SVM learns fluctuated facial images, it achieve more than 96% estimation accuracy for facial database images. Experimental results of actual surveillance camera images show that, by learning fluctuated images, estimation accuracy of facial directions improves from 34% to 38%. When we tolerate estimation error within 30 degrees, it can achieve 72% estimation rate.
Keywords :
cameras; face recognition; support vector machines; video surveillance; visual databases; SVM; background subtraction; face direction estimation; histograms of oriented gradient; low resolution facial image; support vector machine; wideview surveillance camera; Image resolution; Support vector machines; Facial Direction Estimation; Histograms of Oriented Gradients; Human Behavior Recognition; Support Vector Machine;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
World Automation Congress (WAC), 2010
Conference_Location :
Kobe
ISSN :
2154-4824
Print_ISBN :
978-1-4244-9673-0
Electronic_ISBN :
2154-4824
Type :
conf
Filename :
5665674
Link To Document :
بازگشت