TY - BOOK ID - 11200981 TI - Visual reconstruction AU - Blake, Andrew AU - Zisserman, Andrew. PY - 1987 SN - 0262022710 9780262255769 9780262524063 0262255766 9780262022712 0262524066 PB - Cambridge, Mass. : MIT Press, DB - UniCat KW - Pattern perception KW - #TELE:MI2 KW - Design perception KW - Pattern recognition KW - Form perception KW - Perception KW - Figure-ground perception KW - Pattern perception. KW - Engineering & Applied Sciences KW - Computer Science KW - NEUROSCIENCE/Visual Neuroscience KW - COMPUTER SCIENCE/Artificial Intelligence UR - https://www.unicat.be/uniCat?func=search&query=sysid:11200981 AB - "Visual Reconstruction presents a unified and highly original approach to the treatment of continuity in vision. It introduces, analyzes, and illustrates two new concepts. The first -- the weak continuity constraint -- is a concise, computational formalization of piecewise continuity. It is a mechanism for expressing the expectation that visual quantities such as intensity, surface color, and surface depth vary continuously almost everywhere, but with occasional abrupt changes. The second concept -- the graduated nonconvexity algorithm -- arises naturally from the first. It is an efficient, deterministic (nonrandom) algorithm for fitting piecewise continuous functions to visual data. The book first illustrates the breadth of application of reconstruction processes in vision with results that the authors' theory and program yield for a variety of problems. The mathematics of weak continuity and the graduated nonconvexity (GNC) algorithm are then developed carefully and progressively." ER -