The nature of statistical learning theory
The nature of statistical learning theory
Probabilistic Visual Learning for Object Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Neural Network-Based Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Example-Based Learning for View-Based Human Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Detecting Faces in Images: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Tutorial on Support Vector Machines for Pattern Recognition
Data Mining and Knowledge Discovery
Face Recognition: Features Versus Templates
IEEE Transactions on Pattern Analysis and Machine Intelligence
Training Support Vector Machines: an Application to Face Detection
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Journal of Cognitive Neuroscience
Hi-index | 0.01 |
Smart Rooms have many interesting advantages in real world applications. They have cameras, microphones, and other sensors installed for performing different functions such as tracking and recognizing people's expressions and gestures, interpreting their behaviors, and finally extracting the required data for specific purposes. In this paper, we propose an accurate face detection/recognition system to recognize people who enter the smart room, then identifying if he/she is an intruder or a registered user of the facility. Accurate face recognition is still a difficult task, especially in the cases that background, pose, expression, lighting and illumination are unconstrained. Through some experiments, in this paper, we deduce that when taking the central part of the upright frontal faces (including eyes, nose, mouth and chin, but no hair) as samples to make face recognition, the recognition rate will be improved dramatically, even with different expressions, not too extreme lighting change and slight head rotation. For the module of face detection, a support vector machine (SVM) approach is used. And classical eigenface algorithm is utilized to solve the face recognition problem. We combined these two techniques together to construct a system for face detection/recognition with accuracy as high as 96.25%.