Title :
Recognition of 3-D Similar Objects by GRNN
Author :
Polat, Övünç ; Yildirim, Tülay
Author_Institution :
Elektron. ve Haberlesme Muhendisligi Bolumu, Yildiz Teknik Univ., Istanbul
Abstract :
This paper presents an approach for the recognition of similar objects automatically. In the recognition system, colour features were extracted from two dimensional (2-D) pose images of every 3-D object given and the classification of the objects was realized by using these feature vectors in general regression neural networks-GRNN. The system has been simulated with eight different objects having similar shapes and high recognition rate was obtained. The ability of recognizing many undefined objects after training with low number of samples is important property of this system
Keywords :
feature extraction; image classification; image colour analysis; image sampling; neural nets; object recognition; GRNN; colour feature extraction; general regression neural network; image sample; object classification; objects recognition; two-dimensional pose image; Feature extraction; Gaussian processes; Image recognition; Influenza; Neural networks; Shape; Tellurium; Testing; Two dimensional displays;
Conference_Titel :
Signal Processing and Communications Applications, 2006 IEEE 14th
Conference_Location :
Antalya
Print_ISBN :
1-4244-0238-7
DOI :
10.1109/SIU.2006.1659863
