29 October 1993 Probabilistic spectral feature extraction technique for neural networks
Author Affiliations +
Abstract
Artificial neural net models have been studied for many years in the hope of achieving human- like performance in the fields of speech, image recognition and pattern recognition. For high performance and for controlling the size of the network, the input information must be preprocessed before being fed into the neural network. In this paper, a probabilistic spectral feature extraction technique (PSFET) with multiview spectral representations and its applications are described. During training and testing, the PSFET allows efficient extraction of useful information in addition to generating an input vector size for best classification performance by the following neural network. Experimental results indicate that the performance of the neural network increases in classification accuracy when PSFET is used at the input. The network also generalizes better.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Young Ro Yoon, Okan K. Ersoy, "Probabilistic spectral feature extraction technique for neural networks", Proc. SPIE 2032, Neural and Stochastic Methods in Image and Signal Processing II, (29 October 1993); doi: 10.1117/12.162026; https://doi.org/10.1117/12.162026
PROCEEDINGS
12 PAGES


SHARE
KEYWORDS
Neural networks

Quantization

Binary data

Feature extraction

Distance measurement

Data storage

Pattern recognition

RELATED CONTENT


Back to Top