Ramdas, V and Sridhar, V and Krishna, G (1994) An effective clustering technique for feature extraction. In: Pattern Recognition Letters, 15 (9). pp. 885-891.
Restricted to Registered users only
Download (513Kb) | Request a copy
The performance of a classifier depends on the accuracy of measurement of the feature values. In this paper, we describe an approach for estimating feature values using a clustering technique. To begin with, we discuss the role of multiple versions of a pattern in pattern analysis. Specifically, we describe how clustering can be employed in pattern analysis. We follow this with a discussion on the usefulness of clustering in class-characterization. Specifically, we describe an approach to account for feature value measurement errors. The proposed approach has been applied in the context of speech recognition. Specifically, we inves- tigate the estimation of formant frequencies (feature values) that form an essential ingredient in the design of a speaker-inde- pendent digit recognition system (classifier).
|Item Type:||Journal Article|
|Additional Information:||The copyright of this article belongs to Elsevier.|
|Department/Centre:||Division of Information Sciences > Supercomputer Education & Research Centre
Division of Electrical Sciences > Computer Science & Automation (Formerly, School of Automation)
|Date Deposited:||04 Jul 2006|
|Last Modified:||19 Sep 2010 04:29|
Actions (login required)