Convolutional Neural Networks for Deep LearningBased Image Forgery Detection

Read full text Summarise with VIRAT
Authors: M D Mahesh, Muddu Kuppam Pravallika
Cited by: 0
References: 4

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The quick development of digital image editing tools has made picture manipulation simpler, making it more difficult to confirm the legitimacy of visual content. In fields including journalism, social media, and legal investigations, image forgery can result in false information, a decline in confidence, and improper use of digital media. As a result, identifying forged photos has grown in importance within the discipline of digital image forensics. This study suggests a deep learning-based method for Convolutional Neural Networks (CNN)-based image forgery detection. By identifying unique visual patterns in a labelled dataset of actual and fake photographs, the suggested method is intended to automatically categorise images as either real or altered. The CNN model receives the preprocessed pictures for feature extraction and training. Following training, the model is incorporated into an online application that lets users upload photos and get prediction results and a confidence score. Results from experiments show that the CNN model is capable of accurately and successfully identifying counterfeit images. Digital forensics, cybersecurity, and media verification systems can all benefit from the suggested method's effective and automated approach to picture forgery detection.

Fields of Study & Subjects

Digital Media Forensic Detection Advanced Steganography and Watermarking Techniques Benford’s Law and Fraud Detection

Publication details

Journal / source
JOURNAL OF ADVANCE AND FUTURE RESEARCH
Volume
4
Issue
3
Publication date
1 March 2026
Language
EN