DocumentCode :
2088855
Title :
Detection of human faces using decision trees
Author :
Huang, Jeffrey ; Gutta, Srinivas ; Wechsler, Harry
Author_Institution :
Dept. of Comput. Sci., George Mason Univ., Fairfax, VA, USA
fYear :
1996
fDate :
14-16 Oct 1996
Firstpage :
248
Lastpage :
252
Abstract :
The paper proposes a novel algorithm for face detection using decision trees (DT) and shows its generality and feasibility using a database consisting of 2340 face images from the FERET database (corresponding to 817 subjects and including 190 sets of duplicates) over a semi-uniform background. The approach used for face detection involves three main stages, those of location, cropping, and post-processing. The first stage finds a rough approximation for the possible location of the face box, the second stage will refine it, and the last stage decider whether a face is present in the image and if the answer is positive would normalize the face image. The algorithm does not require multiple (scale) templates and the accuracy achieved is 96%. Accuracy is based on the visual observation that the face box includes both eyes, nose, and mouth, and that the top side of the box is below the hairline. Experiments were also performed to assess the accuracy of the algorithm in rejecting images where no face is present. Using a small database of 25 images of various but complex backgrounds the algorithm failed on two images for an overall accuracy rate of 92%
Keywords :
decision theory; edge detection; eye; face recognition; feature extraction; trees (mathematics); FERET database; algorithm; cropping; decision trees; eyes; face box; face image normalization; face images; human face detection; image rejection; location; mouth; nose; post-processing; semi-uniform background; visual observation; Computer science; Decision trees; Eyes; Face detection; Face recognition; Forensics; Humans; Image databases; Mouth; Nose;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Automatic Face and Gesture Recognition, 1996., Proceedings of the Second International Conference on
Conference_Location :
Killington, VT
Print_ISBN :
0-8186-7713-9
Type :
conf
DOI :
10.1109/AFGR.1996.557272
Filename :
557272
Link To Document :
بازگشت