Title :
One method of structural description rule extraction based on graphical and spatial relations
Author :
Satoh, Shin´ichi ; Satou, Takashi ; Sakauchi, Masao
Author_Institution :
Inst. of Ind. Sci., Tokyo Univ., Japan
fDate :
30 Aug-3 Sep 1992
Abstract :
Recently, multi-purpose and generalized image/pattern recognition methods are required. To achieve this, it is desired to realize an automated recognition rule generation system. In this paper, a learning system of structural description rules which are used as models for the model based vision is presented. This system can generate structural description rules efficiently using partially structured example figure descriptions, and a proper inductive inference algorithm for generating structural description rules
Keywords :
computer vision; image recognition; knowledge based systems; learning systems; spatial reasoning; automated recognition rule generation system; computer vision; image understanding; inductive inference; learning system; model based vision; pattern recognition; spatial relations; structural description rule extraction; Data structures; Engines; Industrial relations; Inference algorithms; Learning systems; Pattern recognition; Spatial databases;
Conference_Titel :
Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on
Conference_Location :
The Hague
Print_ISBN :
0-8186-2915-0
DOI :
10.1109/ICPR.1992.201773
