Recognition Of An Object in A Stack Of Industrial Parts

our purpose. This paper describes a method f o r anal y z i n g an input scene of a stack of indust r i a l parts i n order to recognize an obj e c t which is not obscured by others. Detecting a simple f a m i l i a r pattern such as an e l l i p s e in a set of strong feature points, an analyzer selects models of the machine parts from the a t t r i b u t e s of other feature points around the pattern under the constraints of the proposed models. F i n a l l y one of the models i s v e r i f i e d through processes of matching the d e t a i l e d structures of the models to the less obvious feature points.