Scribd
Upload
20 views13 pages

D11 Mini Project-1

The document presents a mini project on deepfake video detection using a region-based convolutional neural network (R-CNN). It outlines the aim to develop a robust detection system that addresses the limitations of existing methods, such as low accuracy and inadequate feature analysis. The project emphasizes the importance of ethical AI practices and the need for accurate detection of manipulated content in videos.

Uploaded by

nadimpallivamshi7
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
20 views13 pages

D11 Mini Project-1

The document presents a mini project on deepfake video detection using a region-based convolutional neural network (R-CNN). It outlines the aim to develop a robust detection system that addresses the limitations of existing methods, such as low accuracy and inadequate feature analysis. The project emphasizes the importance of ethical AI practices and the need for accurate detection of manipulated content in videos.

Uploaded by

nadimpallivamshi7
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 13

CMR ENGINEERING COLLEGE

Department of Electronics and Communication Engineering

A Mini Project Presentation on

Deepfake video detection and estimation using region convolutional neural


network

Submitted by:
Under the Guidance of 218R1A04N5 M.RAHUL
Mr. M.Raja, 218R1A04N6 N.VAMSHI
Associate Professor, 218R1A04N7 N.VARSHITHA
ECE, 218R1A04N8 N.SHIVAYADAV
CMREC
CONTENTS
• Aim
• Motivation
• Abstract
• Introduction
• Existing Method
• Drawbacks of Existing System
• Proposed Method
• Block Diagram & Working
• Software Requirements
• References
AIM
• The aim of this project is to develop and implement a
robust deepfake video detection and estimation
system using a region-based convolutional neural
network (R-CNN) for deep fake video detection is to
develop effective and scalable solutions
MOTIVATION

• The motivation behind deep fake video detection using CNNs


lies in upholding truthfulness, protecting individuals and
organizations, preventing deception, promoting ethical AI
practices, advancing media forensics, and challenging
adversarial manipulation in the digital age.
ABSTRACT
• Deep Fake is a generative deep learning algorithm that creates or modifies
face features in a super realistic form, in which it is difficult to distinguish
between real and fake features.
• Basically, Deep Fake is the regenerated media that is obtained by injecting
or replacing some information within the DNN model.
• This project aims to develop an advanced deepfake detection and
estimation system utilizing region-based convolutional neural networks
(R-CNNs)
• focusing on the spatial and temporal inconsistencies characteristic of
deepfake videos, the proposed system analyzes video frames to accurately
identify and quantify manipulated content.
• The R-CNN framework enables precise localization of altered regions
within frames, enhancing the detection accuracy compared to traditional
methods
INTRODUCTION
• The aim of this project is to develop and implement a robust
deepfake video detection and estimation system using a
region-based convolutional neural network (R-CNN).
• Convolutional neural networks (CNNs) are deep learning
architectures that are used in various applications, including
image and video processing, natural language processing
(NLP), and recommendation systems.
• R-CNNs have demonstrated exceptional performance in object
detection tasks by focusing on specific regions of interest
within an image.

Mar 3, 2025 Department of ECE, CMR Engineering Colle 6


ge, Hyderabad
EXISTING METHOD

 Principal Component Analysis


 Local binary pattern and shape features
 KNN and FNN classifier
DRAWBACKS OF EXISTING
METHOD

 Less accuracy

 Feature analysis is less using LBP


PROPOSED METHOD

Input image
Preprocessing
 feature extraction
CNN
BLOCK DIAGRAM
SOFTWARE REQUIREMENT

● Python idle
● Anaconda navigator
● Opencv

Mar 3, 2025 Department of ECE, CMR Engineering Colle 11


ge, Hyderabad
REFERENCES
• [1] Y. Li, M. C. Chang, and S. Lyu, “In Ictu Oculi: Exposing AI created fake videos by detecting eye blinking,”
in 10th IEEE International Workshop on Information Forensics and Security, WIFS 2018, 2019.
• [2] H. Li, B. Li, S. Tan, and J. Huang, “Detection of Deep Network Generated Images Using Disparities in
Color Components,” Aug. 2018.
• [3] Y. Li and S. Lyu, “Exposing DeepFake Videos By Detecting Face Warping Artifacts.”
• [4] D. Guera and E. J. Delp, “Deepfake Video Detection Using Recurrent Neural Networks,” in Proceedings of
AVSS 2018 - 2018 15th IEEE International Conference on Advanced Video and Signal-Based Surveillance,
2019.
• [5] X. Yang, Y. Li, and S. Lyu, “Exposing Deep Fakes Using Inconsistent Head Poses,” in ICASSP, IEEE
International Conference on Acoustics, Speech and Signal Processing - Proceedings, 2019.
• [6] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the
IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016, vol. 2016-Decem, pp.
770–778.
• [7] D. E. King, “Dlib-ml: A machine learning toolkit,” J. Mach. Learn. Res., 2009.
• [8] Adam Geitgey, “Machine Learning is Fun! Part 4: Modern Face Recognition with Deep Learning,” Medium,
2016. [9] G. Bradski, “The OpenCV Library,” Dr Dobbs J. Softw. Tools, 2000. [10] F. Pedregosa et al., “Sc
THANK YOU !

Department of ECE, CMR Engineering


Mar 3, 2025 13
College, Hyderabad

You might also like