Model Dual-Branch CNN untuk Deteksi Gambar Palsu Dengan Pendekatan ELA dan SRM

Siti Nur, Rohmatul Ummah (2025) Model Dual-Branch CNN untuk Deteksi Gambar Palsu Dengan Pendekatan ELA dan SRM. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) cover (2).pdf Download (1MB)
	Text (Bab 1) bab 1.pdf Download (225kB)
	Text (Bab 2) bab 2.pdf Restricted to Repository staff only until 20 June 2027. Download (703kB)
	Text (Bab 3) bab 3.pdf Restricted to Repository staff only until 20 June 2027. Download (959kB)
	Text (Bab 4) bab 4.pdf Restricted to Repository staff only until 20 June 2027. Download (818kB)
	Text (Bab 5) bab 5.pdf Download (282kB)
	Text (Daftar Pustaka) daftar pustaka.pdf Download (263kB)

Abstract

The advancement of digital technology has made image manipulation easier, posing significant challenges in maintaining the authenticity of visual information distributed online. This study aims to develop a system capable of detecting manipulated images by combining Error Level Analysis (ELA) and feature extraction using the Spatial Rich Model (SRM), followed by classification through a Convolutional Neural Network (CNN). The research process includes image preprocessing using ELA, SRM-based feature extraction, CNN model training, and web application development using the Flask framework. The dataset utilized consists of images from CASIA and a portion from Columbia to improve the model’s ability to generalize across various types of manipulation. Evaluation results indicate that the proposed system achieves high accuracy in detecting image forgeries. This system is expected to serve as an effective tool for verifying the authenticity of digital images.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Fetty, Tri Anggraeny	19820211 202121 2 005	fettyanggraeny.if@upnjatim.ac.id
Thesis advisor	Achmad, Junaidi	3 7811 04 0199 1	achmadjunaidi.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General) > T58.6-58.62 Management Information Systems

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

siti nur rohmatul ummah

Date Deposited:

20 Jun 2025 06:30

Last Modified:

20 Jun 2025 06:30

URI:

https://repository.upnjatim.ac.id/id/eprint/38809