Image Representations for Visual Learning
David Beymer, Tomaso Poggio · Science · 1996
Computer vision researchers are developing new approaches to object recognition and detection that are based almost directly on images and avoid the use of intermediate three-dimensional models. Many of these techniques depend on a representation of images that induce a linear vector space structure and in principle requires dense feature correspondence. This image representation allows the use of learning techniques for the analysis of images (for computer vision) as well as for the synthesis of images (for computer graphics).
Cited by 271 works. doi:10.1126/science.272.5270.1905
Authors
References
- Eigenfaces for Recognition
- Visual learning and recognition of 3-d objects from appearance
- The Representation and Matching of Pictorial Structures
- Application of the Karhunen-Loeve procedure for the characterization of human faces
- Distortion invariant object recognition in the dynamic link architecture
- Computational vision and regularization theory
- Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks
- Probabilistic visual learning for object detection
- Shape and motion from image streams under orthography: a factorization method
- Recognition by linear combinations of models