Example Based Learning for View-Based Human Face Detection.
Kah-Kay Sung, Tomaso Poggio · 1994
Finding human faces automatically in an image is a di cult yet important rst step to a fully automatic face recognition system.It is also an interesting academic problem because a successful face detection system can provide valuable insight o n h o w one might a p p r o a c h other similar object and pattern detection problems.This paper presents an example-based learning approach for locating vertical frontal views of human faces in complex scenes.The technique models the distribution of human face patterns by means of a few view-based \face" and \non-face" prototype clusters.At e a c h image location, a di erence feature vector is computed between the local image pattern and the distribution-based model.A trained classi er determines, based on the di erence feature vector, whether or not a human face exists at the current image location.We s h o w empirically that the prototypes we c hoose for our distribution-based model, and the distance metric we adopt for computing di erence feature vectors, are both critical for the success of our system.
Cited by 268 works. doi:10.21236/ada295738
Authors
References
- Eigenfaces for Recognition
- Introduction to Statistical Pattern Recognition
- Low-dimensional procedure for the characterization of human faces
- View-based and modular eigenspaces for face recognition
- Face recognition: features versus templates
- Feature extraction from faces using deformable templates
- Example Based Learning for View-Based Human Face Detection.
- Example Based Image Analysis and Synthesis
- Principal-Component Imagery For Statistical Pattern Recognition Correlators
- Recognition and Structure from One 2D Model View: Observations on Prototypes, Object Classes and Symmetries