Omni-Dimensional Convolutional Separable Kernel Attention with Convolutional Neural Network for Image Forgery Classification
Journal of Intelligent Decision Making and Information Science · 17.09.2026 · 3 (12s) · 2866-2877
DOI: 10.17762/jidmis.v3.3711 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Intelligent Decision Making and Information Science, online erschienen am 17.09.2026. Verfasst von Premachand D R. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Image forgery determines whether the image is authentic or tampered by identifying inconsistencies manipulation. Image forgery represents alterations such as, insert, delete, and replicate, where the altered image content is difficult to identify whether the image is forged or not. Differentiating between original and tampered images is difficult because of high visual similarities among original and manipulated regions. To overcome these challenges, this research proposes the Omni-Dimensional Convolutional Separable Kernel Attention with Convolutional Neural Network model (ODCSKA-CNN) to differentiate the authentic and tampered image accurately also to enhance the classification accuracy. The COVERAGE dataset and GRIP dataset are used to evaluate the model. Therefore, during pre-processing stage, the min-max normalization technique applies to normalize the scale values to enhance the model efficiency to improve the image quality. The proposed model ODCSKA-CNN attains the accuracies of 99.01% and 98.75% in COVERAGE dataset and GRIP datasets.
Zitieren
APA
R, P. D. (2026). Omni-Dimensional Convolutional Separable Kernel Attention with Convolutional Neural Network for Image Forgery Classification. Journal of Intelligent Decision Making and Information Science, 3(12s), 2866-2877. https://doi.org/10.17762/jidmis.v3.3711
Vancouver
R PD. Omni-Dimensional Convolutional Separable Kernel Attention with Convolutional Neural Network for Image Forgery Classification. Journal of Intelligent Decision Making and Information Science. 2026;3(12s):2866-2877. doi:10.17762/jidmis.v3.3711
BibTeX
@article{R2026,
author = {R, Premachand D},
title = {Omni-Dimensional Convolutional Separable Kernel Attention with Convolutional Neural Network for Image Forgery Classification},
journal = {Journal of Intelligent Decision Making and Information Science},
year = {2026},
volume = {3},
number = {12s},
pages = {2866--2877},
doi = {10.17762/jidmis.v3.3711}
}
EUVIMED