Pose-invariant face detection using edge-like blob map and fuzzy logic
IEA/AIE'2005 Proceedings of the 18th international conference on Innovations in Applied Artificial Intelligence
Using natural class hierarchies in multi-class visual classification
Pattern Recognition
Perspective change: a system for switching between on-screen views by closing one eye
AVI '08 Proceedings of the working conference on Advanced visual interfaces
Automatic real time localization of frowning and smiling faces under controlled head rotations
WSEAS Transactions on Signal Processing
Automatic real-time localization of frowning and smiling faces under head rotation variations
ISCGAV'08 Proceedings of the 8th conference on Signal processing, computational geometry and artificial vision
Face detection and tracking in video sequences using the modifiedcensus transformation
Image and Vision Computing
Adapted active appearance models
Journal on Image and Video Processing
Face detection with the modified census transform
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
ICNC'06 Proceedings of the Second international conference on Advances in Natural Computation - Volume Part I
Robust facial landmark detection for intelligent vehicle system
AMFG'05 Proceedings of the Second international conference on Analysis and Modelling of Faces and Gestures
Adapting hausdorff metrics to face detection systems: a scale-normalized Hausdorff distance approach
EPIA'05 Proceedings of the 12th Portuguese conference on Progress in Artificial Intelligence
Coarse-to-fine classification for image-based face detection
CIVR'06 Proceedings of the 5th international conference on Image and Video Retrieval
An effective method for detecting facial features and face in human-robot interaction
Information Sciences: an International Journal
Real-time eye-gaze estimation using a low-resolution webcam
Multimedia Tools and Applications
| Hi-index | 0.00 |
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 an edge orientation matching and a subsequent candidate verification using a SNoW classifier at the final stage.We have developed a simple and efficient method for object modeling and matching using edge orientation information only which we call EOM (Edge Orientation Matching). 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 msec on an Athlon 1000MHz PC to analyze an image of spatial size 384x288. Experimental results on a large database of 18704 grey still images with 19030 detectable frontal faces, including the M2VTS frontal face database, the CMU test set of Rowley and Baluja and the newly released BioID testset, show that the presented approach outperformes methodes that use Neural Networkes, Bayesian methods and SVMs by far in terms of computational efficiency while showing comparable detetction results. The overall recognition performance is above 96%.