International Journal of Computer Vision
Learning to track the visual motion of contours
Artificial Intelligence - Special volume on computer vision
Detecting Faces in Images: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
Contour Tracking by Stochastic Propagation of Conditional Density
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Colour Model Selection and Adaption in Dynamic Scenes
ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume I - Volume I
Color-Based Probabilistic Tracking
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Skin-Color Modeling and Adaptation
ACCV '98 Proceedings of the Third Asian Conference on Computer Vision-Volume II
Color active shape models for tracking non-rigid objects
Pattern Recognition Letters - Special issue: Colour image processing and analysis
Color-Based Tracking of Heads and Other Mobile Objects at Video Frame Rates
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Elliptical Head Tracking Using Intensity Gradients and Color Histograms
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Segmentation and Tracking of Faces in Color Images
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
Real Time Face and Object Tracking as a Component of a Perceptual User Interface
WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
Mode-based Multi-Hypothesis Head Tracking Using Parametric Contours
FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Detection of Skin Color under Changing Illumination: A Comparative Study
ICIAP '03 Proceedings of the 12th International Conference on Image Analysis and Processing
Probabilistic tracking in joint feature-spatial spaces
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
| Hi-index | 0.00 |
An approach for segmenting and tracking a face in a sequence of color images is presented. It enables reliable segmentation of facial region despite variation of skin-color perceived by a camera. A second order Markov model is utilized to forecast the skin distribution of facial regions in the next frame. The histograms that are constructed from the predicted distribution are backprojected to generate candidates of facial regions. Afterwards, a connected component labeling takes place. Spatial morphological operations, such as size and hole filtering are employed next. The Active Shape Model seeks to match a set of model points to the image. This statistical model of shape supports the segmentation of facial region undergoing tracking. Histograms are accommodated over time using feedback from shape, newly classified skin pixels and predictions of the skin-color evolution. This evolution is described by translation, rotation and scaling. In this context, the novelty of our approach lies in the introduction of Active Shape Model dealing with translation, rotation and scaling of the target to support face verification as well as to guide the evolution of skin distribution. The kernel histograms characterize the face during tracking in subsequent frames. The proposed algorithm achieves reliable detection and tracking results. The resulting system runs in real-time on standard PC computer.