A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape Matching and Object Recognition Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Face Detection Using the Hausdorff Distance
AVBPA '01 Proceedings of the Third International Conference on Audio- and Video-Based Biometric Person Authentication
Automatic feature localisation with constrained local models
Pattern Recognition
Face Recognition Using Parabola Edge Map
ACIVS '08 Proceedings of the 10th International Conference on Advanced Concepts for Intelligent Vision Systems
Face Alignment Via Component-Based Discriminative Search
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast polynomial segmentation of digitized curves
DGCI'06 Proceedings of the 13th international conference on Discrete Geometry for Computer Imagery
ICEC'12 Proceedings of the 11th international conference on Entertainment Computing
Low-complexity scalable distributed multicamera tracking of humans
ACM Transactions on Sensor Networks (TOSN)
Hi-index | 0.00 |
This paper proposes an automatic and real-time system for face analysis, usable in visual communication applications. In this approach, faces are represented with Curve Edge Maps, which are collections of polynomial segments with a convex region. The segments are extracted from edge pixels using an adaptive incremental linear-time fitting algorithm, which is based on constructive polynomial fitting. The face analysis system considers face tracking, face recognition and facial feature detection, using Curve Edge Maps driven by histograms of intensities and histograms of relative positions. When applied to different face databases and video sequences, the average face recognition rate is 95.51%, the average facial feature detection rate is 91.92% and the accuracy in location of the facial features is 2.18% in terms of the size of the face, which is comparable with or better than the results in literature. However, our method has the advantages of simplicity, real-time performance and extensibility to the different aspects of face analysis, such as recognition of facial expressions and talking.