View-based and modular eigenspaces for face recognition
Alex Pentland, Moghaddam, Starner · 1994
We describe experiments with eigenfaces for recognition and interactive search in a large-scale face database. Accurate visual recognition is demonstrated using a database of O(10/sup 3/) faces. The problem of recognition under general viewing orientation is also examined. A view-based multiple-observer eigenspace technique is proposed for use in face recognition under variable pose. In addition, a modular eigenspace description technique is used which incorporates salient features such as the eyes, nose and mouth, in an eigenfeature layer. This modular representation yields higher recognition rates as well as a more robust framework for face recognition. An automatic feature extraction technique using feature eigentemplates is also demonstrated.>
Cited by 1,800 works. doi:10.1109/cvpr.1994.323814
Authors
References
- Eigenfaces for Recognition
- Application of the Karhunen-Loeve procedure for the characterization of human faces
- Face recognition: features versus templates
- Photobook: tools for content-based manipulation of image databases
- Eye Movements and Vision
- Space-time gestures
- Principal-Component Imagery For Statistical Pattern Recognition Correlators
- Picture processing by computer complex and recogniton of human faces
- Picture processing by computer complex and recognition of human faces
- Learning and recognition of 3D objects from appearance