Detection of counterfeit images using SIFT and PNN
Division for Postgraduate Studies/ Technological Institute of Morelia, Morelia, Mexico.
Review Article
Global Journal of Engineering and Technology Advances, 2024, 20(01), 171–178.
Article DOI: 10.30574/gjeta.2024.20.1.0134
Publication history:
Received on 13 June 2024; revised on 22 July 2024; accepted on 25 July 2024
Abstract:
Manipulation of digital images presents a significant challenge, primarily due to the continuous advancement and sophistication of image enhancement tools. As a consequence, image feature extraction and matching have become pivotal areas of research in the field of image processing. Among the various techniques developed, the Scale-Invariant Feature Transform algorithm has gained widespread recognition for its robustness and superior performance in feature matching tasks when compared to other existing methods. In this context, our proposed method, which integrates the Scale-Invariant Feature Transform algorithm with a probabilistic neural network, offers a novel approach to digital image classification specifically aimed at counterfeit image detection. This integrated system not only enhances the accuracy of feature extraction but also leverages the probabilistic neural network to improve classification efficacy. Empirical results indicate that this hybrid approach achieves a remarkable relative error rate of just 0.666%, underscoring its potential as a reliable tool for combating digital image forgery. Such advancements are crucial for maintaining the integrity of digital media in various applications, from forensic analysis to digital content authentication.
Keywords:
SIFT; PNN; Counterfeit; KNN; Matching
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0