Title :
An FDO neural network model and its application to image recognition
Author :
Sheng, Dingang ; Qi, Feihu
Author_Institution :
Inst. of Image Process. & Pattern Recognition, Shanghai Jiao Tong Univ., China
Abstract :
A full domain optimum neural network is proposed. A method of devising stable points firstly and basins of attraction latterly increases speed and correctness of image recognition. This paper proves the quality and speed of convergence and invariance of mapping. Several computer simulation examples involving trained and recognized targets illustrate the usefulness of the method
Keywords :
convergence; image recognition; learning (artificial intelligence); neural nets; basins of attraction; computer simulation; convergence; full domain optimum neural network; image recognition; invariance of mapping; stable points; Bismuth; Convergence; Cost function; Equations; Image converters; Image recognition; Neural networks; Neurofeedback; Output feedback; Target recognition;
Conference_Titel :
Singapore ICCS/ISITA '92. 'Communications on the Move'
Print_ISBN :
0-7803-0803-4
DOI :
10.1109/ICCS.1992.255028
