Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Robust face detection at video frame rate based on edge orientation features

 
: Fröba, B.; Ernst, A.; Küblbeck, C.

IEEE Computer Society, Technical Committee on Machine Intelligence and Pattern Analysis:
Fifth IEEE International Conference on Automatic Face and Gesture Recognition 2002. Proceedings : 20 - 21 May 2002, Washington, D.C.
Los Alamitos, Calif.: IEEE Computer Society, 2002
ISBN: 0-7695-1602-5
S.342-347
International Conference on Automatic Face and Gesture Recognition (AFGR) <5, 2002, Washington/DC>
Englisch
Konferenzbeitrag
Fraunhofer IIS A ( IIS) ()
robust real-time face detection; video frame rate; edge orientation feature; grey image; video stream; multi-stage detection pipeline; edge orientation matching; face candidate verification; view-based SNoW classifier; object modeling; object matching; speedup; pipelined image matcher; coarse-to-fine grid scan; image location; Athlon PC; grey still image; CMU test set; BioID test set; computational efficiency; recognition performance

Abstract
In this paper, we present a novel approach to real-time face detection in arbitrary grey images and video streams using a multi-stage detection pipeline. It is based on edge orientation matching (EOM) and subsequent candidate verification using a SNoW (Sparse Network of Winnows) classifier in the final stage. We have developed a simple and efficient EOM method for object modeling and matching using edge orientation information only. To make the system more robust, we verify face candidates obtained by the EOM with a view-based SNoW classifier which operates directly on the grey values. For further speedup, the pipelined matcher is combined with a coarse-to-fine grid scan of the image. On average, it thus requires less than 10% of all possible image locations to be processed by the detection pipeline. With this method, it takes 50 ms on an Athlon 1000-MHz PC to analyze an image of spatial size 384x288 pixels. Experimental results on a large database of 18,704 grey still images with 19,030 detectable frontal faces, including the M2VTS (Multi- Modal Verification for Teleservices and Security applications) frontal face database, the CMU (Carnegie Mellon University) test set of H.A. Rowley and S. Baluja (1996) and the newly released BioID (Biometric Identification) test set, show that the presented approach outperforms methods that use neural networks, Bayesian methods and support vector machines (SVMs) by far in terms of computational efficiency while showing comparable detection results. The overall recognition performance is above 96%.

: http://publica.fraunhofer.de/dokumente/N-16903.html