On efficient multi-angle face prototype collection

Authors:
Ping-Hsien Lee;Chu-Song Chen
Affiliations:
Institute of Information Science, Academia Sinica, Taipei, Taiwan and Dept. of Computer Science and Information Engineering, National Taiwan University, Taiwan;Institute of Information Science, Academia Sinica, Taipei, Taiwan
Venue:
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
Year:
2004

Citing 6
Cited 0

Introduction to algorithms

Introduction to algorithms
Neural Network-Based Face Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Real-time face pose estimation

Real-Time Imaging - Special issue on real-time visual monitoring and inspection
Discriminant Waveletfaces and Nearest Feature Classifiers for Face Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Support Vector Regression and Classification Based Multi-View Face Detection and Recognition

FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Real-Time Multi-View Face Detection

FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Although extremely tedious, collecting multi-angle face prototypes is essential for face-related applications such as detection, tracking, recognition, and pose estimation. To reduce the load, we propose a user-friendly interface that is designed to collect multi-angle face prototypes in a fast and easily tractable manner. A user-friendly interface called dynamic cursor is designed to guide users' viewing directions for orientation-enforced video acquisition. A new problem called the orientation-enforced face detection problem is proposed and solved for multi-angle face prototype collection. Our method can help build a fast and user-friendly face registration module for face-related applications.