Pregled bibliografske jedinice broj: 10257
Application of the cascade-correlation network to the classification of circular scanned images
Application of the cascade-correlation network to the classification of circular scanned images // Neural computing & applications, 4 (1996), 3; 161-167 doi:10.1007/BF01414876 (međunarodna recenzija, članak, znanstveni)
CROSBI ID: 10257 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Application of the cascade-correlation network to the classification of circular scanned images
Autori
Mašić, Nikola ; Ristov, Strahil ; Vojnović, Božidar
Izvornik
Neural computing & applications (0941-0643) 4
(1996), 3;
161-167
Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni
Ključne riječi
cascade-correlation network; circular scanning of images; pattern recognition
Sažetak
This paper describes an application of the Cascade-Correlation (CC) network to pattern recognition. The pattern recognition task was to simulate an automatic vision inspection system that had to properly classify five different objects. The feature vectors were extracted from 2D images of circularly scanned images and used as inputs for a neural network that was then trained to classify an unknown presented object. The results show that the CC network is viable tool in pattern recognition tasks. It is able to classify partially occluded objects with high accuracy, and to considerably improve classification of noisy images based on simple histogram trimming preprocessing.
Izvorni jezik
Engleski
Znanstvena područja
Elektrotehnika
Citiraj ovu publikaciju:
Časopis indeksira:
- Current Contents Connect (CCC)
- Scopus
