Title :
Genetic selection of biologically inspired receptive fields for computational vision
Author :
Perez, Claudio A. ; Salinas, Cristian
Author_Institution :
Dept. of Electr. Eng., Chile Univ., Santiago, Chile
Abstract :
The paper presents the genetic selection of biologically inspired receptive fields classifiers to improve pattern recognition in neural networks. A genetic algorithm is employed to select the x and y dimensions of the receptive fields in a two plane per layer configuration with two hidden layers. Networks were ranked based on the fitness criterion: best generalization performance on handwritten digits. Results show a strong correlation between the neural network performance and the receptive field x and y dimensions. The best receptive field configuration results outperformed those of the perceptron based models. Best receptive field configurations consist of a small aspect ratio in x and y direction in each plane of the two hidden layers
Keywords :
computer vision; genetic algorithms; handwritten character recognition; image classification; multilayer perceptrons; best generalization performance; biologically inspired receptive fields classifiers; computational vision; fitness criterion; genetic algorithm; genetic selection; handwritten digits; hidden layers; neural networks; pattern recognition; perceptron based models; Application software; Biological information theory; Biological system modeling; Biology computing; Computer vision; Databases; Genetic algorithms; Network topology; Neural networks; Testing;
Conference_Titel :
[Engineering in Medicine and Biology, 1999. 21st Annual Conference and the 1999 Annual Fall Meetring of the Biomedical Engineering Society] BMES/EMBS Conference, 1999. Proceedings of the First Joint
Conference_Location :
Atlanta, GA
Print_ISBN :
0-7803-5674-8
DOI :
10.1109/IEMBS.1999.804078
