Skip to main content

Noise tolerant moments for neural network classification

Palaniappan, Ramaswamy, Raveendran, P., Omatu, Sigeru (1999) Noise tolerant moments for neural network classification. In: IJCNN'99. International Joint Conference on Neural Networks. Proceedings. . pp. 2802-2807. IEEE ISBN 0-7803-5529-6. (doi:10.1109/IJCNN.1999.833525) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)
Official URL
http://dx.doi.org/10.1109/IJCNN.1999.833525

Abstract

Regular moment invariants face two limitations. First, images with symmetry in the x and/or y directions and symmetry at centroid give zero values for odd orders of central moments. Secondly, they are very sensitive to noise, especially the higher order moments. This paper presents a single solution to solve the symmetrical problem and reduce the noise sensitivity of these moments. The solution involves a new set of moment-based features that uses a reference point other than the image centroid. The reference centre is selected such that the new moment features are invariant to translation, scaling and rotation. The derivation of the new moments and their invariance are shown before experimenting them with some symmetrical alphabets. Next, they are shown to be less sensitive under the presence of Gaussian and random noise as compared to the usual regular moment invariants. Noise corrupted English alphabets are classified with a neural network to further verify the advantage of using the new moment features.

Item Type: Conference or workshop item (Proceeding)
DOI/Identification number: 10.1109/IJCNN.1999.833525
Additional information: Unmapped bibliographic data: LA - English [Field not mapped to EPrints] J2 - Proc Int Jt Conf Neural Networks [Field not mapped to EPrints] AD - Univ of Malaya, Kuala Lumpur, Malaysia [Field not mapped to EPrints] DB - Scopus [Field not mapped to EPrints] M3 - Conference Paper [Field not mapped to EPrints] C3 - Proceedings of the International Joint Conference on Neural Networks [Field not mapped to EPrints]
Uncontrolled keywords: Backpropagation, Image processing, Spurious signal noise, Noise tolerant moments, Neural networks
Divisions: Faculties > Sciences > School of Computing
Faculties > Sciences > School of Computing > Data Science
Depositing User: Palaniappan Ramaswamy
Date Deposited: 15 Dec 2018 18:38 UTC
Last Modified: 30 May 2019 08:30 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/70776 (The current URI for this page, for reference purposes)
Palaniappan, Ramaswamy: https://orcid.org/0000-0001-5296-8396
  • Depositors only (login required):