Abstract
This paper presents an application of the quaternion Fourier transform for the preprocessing for neural-computing. In a new way the 1D acoustic signals of French spoken words are represented as 2D signals in the frequency and time domain. These kind of images are then convolved in the quaternion Fourier domain with a quaternion Gabor filter for the extraction of features. This approach allows to greatly reduce the dimension of the feature vector. Two methods of feature extraction are tested. The features vectors were used for the training of a simple MLP, a TDNN and a system of neural experts. The improvement in the classification rate of the neural network classifiers are very encouraging which amply justify the preprocessing in the quaternion frequency domain. This work also suggests the application of the quaternion Fourier transform for other image processing tasks.
Similar content being viewed by others
References
Bayro-Corrochano, E.: Geometric Computing for Perception Action Systems. Springer, New York (2001)
Bülow, T.: Hypercomplex Spectral Signal Representations for the Processing and Analysis of Images. PhD. thesis, Christian Albrechts University of Kiel (1999)
Gabor, D.: Theory of communication. J. IEE 93, 429–457 (1946)
Felsberg, M.: Signal processing using frequency domain methods in Clifford algebra. Msc. Thesis, Computer Science Institute, Christian Albrechts Universität zu Kiel (1998)
Hamilton, W.R.: Elements of Quaternions. Longmans Green, London (1866). Chelsea, New York (1969)
Mehrotra, K., Mohan, Ch.K., Ranka, S.: Elements of Artificial Neural Networks. MIT Press, Cambridge (1997)
Yaglom, M.: Complex Numbers in Geometry. Academic, Leicester (1968)
Zwicker, E.: Psychoacoustics: Facts and Models, 2nd edn. Springer, Berlin (1998)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bayro-Corrochano, E., Trujillo, N. & Naranjo, M. Quaternion Fourier Descriptors for the Preprocessing and Recognition of Spoken Words Using Images of Spatiotemporal Representations. J Math Imaging Vis 28, 179–190 (2007). https://doi.org/10.1007/s10851-007-0004-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-007-0004-y