TY  - JOUR
AU  - Ali, Aamir
AU  - Raza, Aamir
AU  - Syed, Khaleelullah
AU  - Mohan, Swetank
AU  - Fatima, Nikhat
AU  - Umar, Muhammad
AU  - Ali, Misbah
PY  - 2026
DA  - 2026/04/28
TI  - Passive Image Forgery Detection Using Multiscale Weber Local Descriptor and SVM Classification
JO  - ICCK Journal of Image Analysis and Processing
T2  - ICCK Journal of Image Analysis and Processing
JF  - ICCK Journal of Image Analysis and Processing
VL  - 2
IS  - 2
SP  - 69
EP  - 91
DO  - 10.62762/JIAP.2026.490874
UR  - https://www.icck.org/article/abs/JIAP.2026.490874
KW  - digital image forgery detection
KW  - passive image authentication
KW  - copy-move forgery
KW  - image splicing
KW  - weber local descriptor
KW  - multiscale texture analysis
KW  - chroma analysis
KW  - support vector machine
AB  - Digital image manipulation has become increasingly prevalent with the widespread availability of editing tools, raising concerns regarding image authenticity in critical applications. This study presents a passive image forgery detection framework based on multiscale Weber Local Descriptor features extracted from chrominance components and classified using a Support Vector Machine. The proposed method operates without embedded authentication information and focuses on detecting both copy-move and splicing forgeries through texture-based analysis. Experiments were conducted on two benchmark datasets, CASIA v2.0 and MICC F2000, using ten-fold cross-validation. On the CASIA v2.0 dataset, the framework achieved an overall classification accuracy of 97.0%, with a true positive rate of 98.4% for spliced images and an area under the ROC curve of 0.98. On the MICC F2000 dataset, the framework achieved an overall accuracy of 97.4%, with a true positive rate of 99.7% for copy-move forgery detection and an AUC value of 0.98. The results indicate consistent classification performance across different manipulation types and dataset characteristics. The use of chrominance channels enables the preservation of subtle manipulation artifacts, while multiscale texture representation enhances feature discrimination. The proposed framework demonstrates competitive performance compared to existing methods while maintaining moderate computational complexity, making it suitable for practical image authentication tasks.
SN  - 3068-6679
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Ali2026Passive,
  author = {Aamir Ali and Aamir Raza and Khaleelullah Syed and Swetank Mohan and Nikhat Fatima and Muhammad Umar and Misbah Ali},
  title = {Passive Image Forgery Detection Using Multiscale Weber Local Descriptor and SVM Classification},
  journal = {ICCK Journal of Image Analysis and Processing},
  year = {2026},
  volume = {2},
  number = {2},
  pages = {69-91},
  doi = {10.62762/JIAP.2026.490874},
  url = {https://www.icck.org/article/abs/JIAP.2026.490874},
  abstract = {Digital image manipulation has become increasingly prevalent with the widespread availability of editing tools, raising concerns regarding image authenticity in critical applications. This study presents a passive image forgery detection framework based on multiscale Weber Local Descriptor features extracted from chrominance components and classified using a Support Vector Machine. The proposed method operates without embedded authentication information and focuses on detecting both copy-move and splicing forgeries through texture-based analysis. Experiments were conducted on two benchmark datasets, CASIA v2.0 and MICC F2000, using ten-fold cross-validation. On the CASIA v2.0 dataset, the framework achieved an overall classification accuracy of 97.0\%, with a true positive rate of 98.4\% for spliced images and an area under the ROC curve of 0.98. On the MICC F2000 dataset, the framework achieved an overall accuracy of 97.4\%, with a true positive rate of 99.7\% for copy-move forgery detection and an AUC value of 0.98. The results indicate consistent classification performance across different manipulation types and dataset characteristics. The use of chrominance channels enables the preservation of subtle manipulation artifacts, while multiscale texture representation enhances feature discrimination. The proposed framework demonstrates competitive performance compared to existing methods while maintaining moderate computational complexity, making it suitable for practical image authentication tasks.},
  keywords = {digital image forgery detection, passive image authentication, copy-move forgery, image splicing, weber local descriptor, multiscale texture analysis, chroma analysis, support vector machine},
  issn = {3068-6679},
  publisher = {Institute of Central Computation and Knowledge}
}