Neural network-based face detection
Henry A. Rowley, Shumeet Baluja, Takeo Kanade A · IEEE Transactions on Pattern Analysis and Machine Intelligence · 1998
We present a neural network-based upright frontal face detection system. A retinally connected neural network examines small windows of an image and decides whether each window contains a face. The system arbitrates between multiple networks to improve performance over a single network. We present a straightforward procedure for aligning positive face examples for training. To collect negative examples, we use a bootstrap algorithm, which adds false detections into the training set as training progresses. This eliminates the difficult task of manually selecting nonface training examples, which must be chosen to span the entire space of nonface images. Simple heuristics, such as using the fact that faces rarely overlap in images, can further improve the accuracy. Comparisons with several other state-of-the-art face detection systems are presented, showing that our system has comparable performance in terms of detection and false-positive rates.
Cited by 3,518 works. doi:10.1109/34.655647
Authors
References
- Backpropagation Applied to Handwritten Zip Code Recognition
- A Tutorial on Support Vector Machines for Pattern Recognition
- Numerical recipes in Pascal: the art of scientific computing
- Phoneme recognition using time-delay neural networks
- Introduction to the theory of neural computation
- Training support vector machines: an application to face detection
- View-based and modular eigenspaces for face recognition
- The FERET database and evaluation procedure for face-recognition algorithms
- Original approach for the localisation of objects in images
- Probabilistic visual learning for object detection