Abstract

Traditionally, image intensities have been processed to segment an image into regions or to find edge-fragments. Image intensities carry a great deal more information about three-dimensional shape, however. To exploit this information, it is necessary to understand how images are formed and what determines the observed intensity in the image. The gradient space, popularized by Huffman and Mackworth in a slightly different context, is a helpful tool in the development of new methods. 0.

Citations

345	Illumination for computer generated pictures - Phong - 1975
128	Impossible objects as nonsense sentences - Huffman - 1971
70	Obtaining Shape from Shading Information - Horn - 1975
47	Interpreting pictures of polyhedral scenes - Mackworth - 1973
16	A.: Curvature and creases: A primer on paper - HUFFMAN - 1976
15	Photometric Method for Lunar Topography - Rindfleisch - 1966
8	On Boundary Detection - Herskovits, O - 1970
5	A Photometric Investigation of the Slopes and Heights of the Ranges of Hills in the Maria of the Moon - Diggelen - 1951
1	Image intensity understanding, MIT Artificial Intelligence Memo 335 - Horn - 1975