Title :
Open-ball-operators for 3-D object recognition
Author :
Kim, Sung-Soo ; Kasparis, TiKis ; Schiavone, Guy A.
Author_Institution :
Dept. of Electr. & Comput. Eng., Univ. of Central Florida, Orlando, FL, USA
Abstract :
Recognition of three-dimensional objects is a crucial and challenging problem. This paper presents a method of three-dimensional object recognition using the Hopfield associative memory in neural networks. The input vectors to the Hopfield associative memory are obtained via the three-dimensional feature extraction open-ball operator (OBO). This approach is invariant to shift, translation, and rotation (R 3) of three-dimensional objects
Keywords :
Hopfield neural nets; content-addressable storage; feature extraction; object recognition; 3D object recognition; Hopfield associative memory; input vectors; neural networks; open ball operators; rotation invariant operation; shift invariant operation; three-dimensional feature extraction; three-dimensional objects; translation invariant operation; Associative memory; Computational modeling; Computer simulation; Drives; Feature extraction; Hopfield neural networks; Neural networks; Object recognition; Sampling methods; Spatial resolution;
Conference_Titel :
Southcon/96. Conference Record
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-3268-7
DOI :
10.1109/SOUTHC.1996.535084
