Title :
An approach to three-dimensional object recognition using a hybrid Hopfield network
Author :
Brooks, Timothy D. ; Kim, Jung H.
Author_Institution :
Dept. of Electr. Eng., North Carolina A&T State Univ., Greensboro, NC, USA
Abstract :
A hybrid Hopfield network previously used to solve two-dimensional occluded object recognition problems is adapted to the three-dimensional problem. It is assumed that feature extraction has yielded a set of vertices for the model and a set of vertices for the input object. From these vertices local and relational features are obtained for use in a hybrid Hopfield network graph-matching algorithm used to realize three-dimensional single-input object recognition
Keywords :
Hopfield neural nets; convergence; feature extraction; fuzzy neural nets; multidimensional systems; object recognition; relational algebra; feature extraction; graph-matching algorithm; hybrid Hopfield network; local features; occluded object recognition; relational features; three-dimensional object recognition; Data mining; Equations; Feature extraction; Fuzzy neural networks; Impedance matching; Maintenance; Neural networks; Object recognition;
Conference_Titel :
System Theory, 1993. Proceedings SSST '93., Twenty-Fifth Southeastern Symposium on
Conference_Location :
Tuscaloosa, AL
Print_ISBN :
0-8186-3560-6
DOI :
10.1109/SSST.1993.522839
