Skip to main content

Fuzzy ARTMAP classification of invariant features derived using angle of rotation from a neural network

Raveendran, P., Palaniappan, Ramaswamy, Omatu, S. (2000) Fuzzy ARTMAP classification of invariant features derived using angle of rotation from a neural network. Information Sciences, 130 (1-4). pp. 67-84. ISSN 0020-0255. (doi:10.1016/S0020-0255(00)00087-6) (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) (KAR id:70774)

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.
Official URL:
https://doi.org/10.1016/S0020-0255(00)00087-6

Abstract

Conventional regular moment functions have been proposed as pattern sensitive features in image classification and recognition applications. But conventional regular moments are only invariant to translation, rotation and equal scaling. It is shown that the conventional regular moment invariants remain no longer invariant when the image is scaled unequally in the x- and y-axis directions. We address this problem by presenting a technique to make the regular moment functions invariant to unequal scaling. However, the technique produces a set of features that are only invariant to translation, unequal/equal scaling and reflection. They are not invariant to rotation. To make them invariant to rotation, moments are calculated with respect to the principal axis of the image. To perform this, the exact angle of rotation must be known. But the method of using the second-order moments to determine this angle will also be inclusive of an undesired tilt angle. Therefore, in order to correctly determine the amount of rotation, the tilt angle which differs for different scaling factors in the x- and y-axis directions for the particular image must be obtained. In order to solve this problem, a neural network using the back-propagation learning algorithm is trained to estimate the tilt angle of the image and from this the amount of rotation for the image can be determined. Next, the new moments are derived and a Fuzzy ARTMAP network is used to classify these images into their respective classes. Sets of experiments involving images rotated and scaled unequally in the x- and y-axis directions are carried out to demonstrate the validity of the proposed technique.

Item Type: Article
DOI/Identification number: 10.1016/S0020-0255(00)00087-6
Additional information: Unmapped bibliographic data: LA - English [Field not mapped to EPrints] J2 - Inf Sci [Field not mapped to EPrints] AD - Dept. of Elec. and Telecommunication, Eng. Fac., Univ. of Malaya, 50603, Kuala Lumpur, Malaysia [Field not mapped to EPrints] AD - Dept. of Computer and System Science, Coll. Eng., Univ. Osaka P., Osaka, Japan [Field not mapped to EPrints] DB - Scopus [Field not mapped to EPrints] M3 - Article [Field not mapped to EPrints]
Uncontrolled keywords: Backpropagation, Computational methods, Feature extraction, Fuzzy sets, Image analysis, Invariance, Learning algorithms, Neural networks, Backpropagation learning algorithms, Moment functions, Pattern matching
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Depositing User: Palaniappan Ramaswamy
Date Deposited: 15 Dec 2018 16:34 UTC
Last Modified: 16 Nov 2021 10:25 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/70774 (The current URI for this page, for reference purposes)

University of Kent Author Information

Palaniappan, Ramaswamy.

Creator's ORCID: https://orcid.org/0000-0001-5296-8396
CReDIT Contributor Roles:
  • Depositors only (login required):

Total unique views for this document in KAR since July 2020. For more details click on the image.