Image Representations for Visual Learning

Science  28 Jun 1996:
Vol. 272, Issue 5270, pp. 1905-1909
DOI: 10.1126/science.272.5270.1905


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 induces 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).