Publication: Forgery detection algorithm based on texture features
No Thumbnail Available
Date
2021
Authors
Ahmed I.T.
Hammad B.T.
Jamil N.
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Advanced Engineering and Science
Abstract
Any researcher's goal is to improve detection accuracy with a limited feature vector dimension. Therefore, in this paper, we attempt to find and discover the best types of texture features and classifiers that are appropriate for the coarse mesh finite differenc (CMFD). Segmentation-based fractal texture analysis (SFTA), local binary pattern (LBP), and Haralick are the texture features that have been chosen. K-nearest neighbors (KNN), na�ve Bayes, and Logistics are also among the classifiers chosen. SFTA, LBP, and Haralick feature vector are fed to the KNN, na�ve Bayes, and logistics classifier. The outcomes of the experiment indicate that the SFTA texture feature surpassed all other texture features in all classifiers, making it the best texture feature to use in forgery detection. Haralick feature has the second-best texture feature performance in all of the classifiers. The performance using the LBP feature is lower than that of the other texture features. It also shows that the KNN classifier outperformed the other two in terms of accuracy. However, among the classifiers, the logistic classifier had the lowest accuracy. The proposed SFTA based KNN method is compared to other state-of-the-art techniques in terms of feature dimension and detection accuracy. The proposed method outperforms other current techniques. � 2021 Institute of Advanced Engineering and Science. All rights reserved.