Title :
Using contextual information to set control parameters of a vision process
Author :
Houzelle, S. ; Strat, T.M. ; Fua, P. ; Fischler, M.A.
Author_Institution :
Projet Pastis, Inst. Nat. de Recherche en Inf. et Autom., Sophia Antipolis, France
Abstract :
This paper presents a novel approach to supervised learning of image-understanding tactics based on the use of contextual information. We use a database to store past experiences. From this database and the context elements computed from the task specifications and the input data, we determine whether or not an algorithm is applicable, and which parameters are suitable for it. The database is continuously updated with information of success or failure of the system
Keywords :
computer vision; computer vision; contextual information; database; image-understanding; machine learning; parameter vector selection; supervised learning; task specifications; vision control parameters; Cameras; Computer vision; Focusing; Geometry; Image analysis; Layout; Machine learning; Machine learning algorithms; Process control; Supervised learning;
Conference_Titel :
Pattern Recognition, 1994. Vol. 1 - Conference A: Computer Vision & Image Processing., Proceedings of the 12th IAPR International Conference on
Conference_Location :
Jerusalem
Print_ISBN :
0-8186-6265-4
DOI :
10.1109/ICPR.1994.576460
