The role of the quaternion Fourier descriptors for preprocessing in neuralcomputing

Author

Bayro-Corrochano, Eduardo ; Noel, T.T. ; Naranjo, Michel

Author_Institution

Comput. Sci. Dept., CINVESTAV, Guadalajara, Mexico

Volume

4

fYear

2003

fDate

20-24 July 2003

Firstpage

2881

Abstract

This paper presents a preprocessing for neural computing using the quaternion Fourier transform. The 1D signals of French vocables are represented as 2D signals in the frequency and time domain. The images are convolved in the quaternion Fourier domain with a quaternion Gabor filter for the extraction of features. Two methods of feature extraction are tested. The features vectors are then used for the training of two neural network architectures. The results are very encouraging which justify plenty the preprocessing in the quaternion frequency domain.

Keywords

Fourier transforms; feature extraction; learning (artificial intelligence); neural nets; speech recognition; 1D signals; 2D signals; French vocables; feature extraction; neural computing; neural network architectures; neuralcomputing preprocessing; quaternion Fourier descriptors; quaternion Gabor filter; speech recognition; Algebra; Computer architecture; Computer science; Feature extraction; Fourier transforms; Frequency domain analysis; Gabor filters; Neural networks; Quaternions; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2003. Proceedings of the International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-7898-9

Type

conf

DOI

10.1109/IJCNN.2003.1224028

Filename

1224028