DOI Services Persistent Identifiers for Scholarly Research

Contemporary Journal of Social Science Review • pp. 17-27

DEEP LEARNING-BASED CLASSIFICATION OF AUTHENTIC AND TAMPERED IMAGES WITH TAMPERING LOCALIZATION VIA IMAGE PROCESSING

  • Usman Khalid Faculty of Computer Science and Information Technology, The Superior University, Lahore, Pakistan,Department of Computer Science, The Superior University, Lahore, Pakistan
  • H. M. Shahzad Faculty of Computer Science and Information Technology, The Superior University, Lahore, Pakistan,Department of Software Engineering, The Superior University, Lahore, Pakistan
  • Munazzah Siddique Faculty of Computing, University of Okara, Pakistan, Department of Computer Science, University of Okara, Pakistan
  • Muhammad Asad Saqlain Faculty of Computer Science and Information Technology, The Superior University, Lahore, Pakistan, Department of Computer Science, The Superior University, Lahore, Pakistan

Abstract

Digital photographs underpin evidence in journalism, law, and

medicine, yet skillfully forged images can still evade casual

inspection. This paper introduces an InceptionV3-based network that

simultaneously classifies images as authentic or tampered, while

also identifying the manipulated regions. Experiments were

conducted on the CASIA v2.0 dataset, which contains 7,492

authentic and 5,123 tampered images with 5,123 corresponding

ground truth images. We use an 85% / 7.5% / 7.5% split for training,

validation, and testing. All images are resized to 224 x 224 px and

normalized to [0, 1] be-fore end-to-end training with Adam (initial

learning rate 1 x 10−4

) and categorical cross-entropy. The proposed

model attains 95.31% accuracy on the test set, surpassing recent

InceptionV3 baselines despite its compact architecture. Tamper

localization is achieved by thresholding the network’s dual-branch

saliency map, which is then overlaying binary ground-truth

contours. These overlays accurately highlight boundaries, even

under aggressive JPEG compression and minor edits. By sharing

features between detection and localization, the network learns

forensic artifacts blocking, boundary mismatches, and illumination

discontinuities, without the need for auxiliary loss terms or attention

modules. Code, trained weights, and evaluation scripts are made

publicly available to ensure full reproducibility.

Record

Identifier
https://doi-services.com/1102/3428
DOI
10.66857/3428
Published
2026-10-16
Version
1
License
https://creativecommons.org/licenses/by/4.0
Original
https://studentsconsultancyhome.com/contemporary-journal/index.php/cjssr/article/view/3428