Professional Documents
Culture Documents
A PROJECT REPORT ON
PROJECT TITLE
1
DR.D.Y.PATIL INSTITUTE OF TECHNOLOGY
Department of Computer Engineering
CERTIFICATE
2
PROJECT APPROVAL SHEET
A Project Title
(Project Title)
Is successfully completed by
3
Dr.D.Y.Patil Institute of Technology, Department of Computer Engineering
2023-24 0
I
Abstract
In an era dominated by digital media, image forgery has become a pervasive issue with
far-reaching consequences. This final year project report presents a comprehensive
investigation into ”Image Forgery Detection Using Deep Learning.” The project’s core aim
is to harness the power of Convolutional Neural Networks (CNNs) and cutting-edge deep
learning techniques to effectively identify manipulated images. By training the neural
networks on diverse datasets containing both authentic and manipulated images, the
project equips them to discern subtle patterns and artifacts introduced during image
forgery. The project also explores various image manipulation techniques to create a
robust benchmark for forgery detection. Additionally, it provides a user-friendly web
interface for users to upload images and assess their authenticity. The system’s
performance is rigorously evaluated, with key metrics such as accuracy, precision, recall,
and F1-score used to determine its efficacy in distinguishing authentic and manipulated
images. This research has significant implications, contributing to the preservation of
digital image authenticity in fields like journalism, forensics, and content moderation. The
project report details the methodology, results, and encountered challenges, offering
valuable insights for further advancements and real-world applications in the domain of
image forensics. It exemplifies the potential of deep learning in combatting the widespread
issue of image forgery in the digital age.
II
Acknowledgments
In the end our special thanks to Other Person Name for providing various
resources such as laboratory with all needed software platforms, continuous
Internet connection, for Our Project.
Student Name1
Student Name2
Student Name3
Student Name4
(B.E. Computer Engg.)
III
Contents
1 Synopsis XII
1.1 Project Title ....................................................................................XII
1.2 Project Option ............................................................................... XII
1.3 Internal Guide ................................................................................. XII
1.4 Sponsorship and External Guide ................................................... XII
1.5 Technical Keywords (As per ACM Keywords) .............................. XII
1.6 Problem Statement ........................................................................ XIII
1.7 Abstract ........................................................................................ XIII
1.8 Goals and Objectives ...................................................................... XIII
1.9 Relevant mathematics associated with the Project ........................ XIII
1.10 Names of Conferences / Journals where papers can be publishedXIV
1.11 Review of Conference/Journal Papers supporting Project idea XIV
1.12 Plan of Project Execution............................................................... XIV
2 Technical Keywords XV
2.1 Area of Project ................................................................................ XV
2.2 Technical Keywords ........................................................................XV
3 Introduction XVI
3.1 Project Idea..................................................................................... XVI
3.2 Motivation of the Project ................................................................ XVI
3.3 Literature Survey ........................................................................... XVI
IV
4.6 Hardware Resources Required ......................................................... XVIII
4.7 Software Resources Required ........................................................... XVIII
V
7.3.1 Internal software data structure ....................................... XXVIII
7.3.2 Global data structure ....................................................... XXX
7.3.3 Temporary data structure ................................................. XXX
7.3.4 Database description ....................................................... XXX
7.4 Compoent Design ......................................................................... XXX
7.4.1 Class Diagram .................................................................. XXX
10 Results XXXIV
10.1 Screen shots .................................................................................. XXXIV
10.2 Outputs ........................................................................................ XXXIV
13 References XXXVII
VI
Annexure F Plagiarism Report XLIII
VII
List of Figures
VIII
List of Tables
IX
[display] 0 1pc
[
]
XI
Chapter 1
Synopsis
1.7 Abstract
In an era dominated by digital media, image forgery has become a pervasive issue with far-
reaching consequences. This final year project report presents a comprehensive investigation into
”Image Forgery Detection Using Deep Learning.” The project’s core aim is to harness the power
of Convolutional Neural Networks (CNNs) and cutting-edge deep learning techniques to
effectively identify manipulated images. By training the neural networks on diverse datasets
containing both authentic and manipulated images, the project equips them to discern subtle
patterns and artifacts introduced during image forgery. The project also explores various image
manipulation techniques to create a robust benchmark for forgery detection. Additionally, it
provides a user-friendly web interface for users to upload images and assess their authenticity. The
system’s performance is rigorously evaluated, with key metrics such as accuracy, precision, recall,
and F1-score used to determine its efficacy in distinguishing authentic and manipulated images.
This research has significant implications, contributing to the preservation of digital image
authenticity in fields like journalism, forensics, and content moderation. The project report details
the methodology, results, and encountered challenges, offering valuable insights for further
advancements and real-world applications in the domain of image forensics. It exemplifies the
potential of deep learning in combatting the widespread issue of image forgery in the digital age,
reaffirming its significance in addressing complex real-world challenges.
2.Enhanced Accuracy and Efficiency: Improve the accuracy and efficiency offorgery detection
by leveraging advanced deep learning techniques, reducing false positives and false negatives, and
providing reliable results in real-time or near-realtime.
3.Adaptability and Generalization: Ensure that the system is adaptable to new forgery
techniques and can generalize its detection capabilities across different image types, sizes, and
formats.
XIII
4.User-Friendly Interface: Design an intuitive and user-friendly interface that simplifies the
process of uploading images for forgery detection, understanding the results, and accessing
additional information or guidance.
5.Ethical and Legal Compliance: Ensure the system complies with ethical standards and legal
regulations, addressing privacy concerns, consent, and potential misuse of forgery detection
technology. This objective is crucial for the responsible and ethical use of the system.
XIV
1.10 Names of Conferences / Journals where
papers can be published
• IEEE/ACM Conference/Journal 1
• Conferences/workshops in IITs
• Central Universities or SPPU Conferences
• IEEE/ACM Conference/Journal 2
1. Project Estimates
Project estimation is most important thing in software Engineering. Project estimation is used to
calculate the duration and cost of the project in prior basis, the process of finding an estimate, or
approximation, which is a value that is unable for some purpose even if input data may be
incomplete, uncertain, or uncertain, or unstable. corresponding population parameter. The sample
provides information that can be pro- Jetted,through various formal or informal processes, to
determine a range most likely to describe the missing information. An estimate that turns out to be
incorrect will be a overestimate if the estimate exceeded the actual result and an underestimate if
the estimate fell short of the actual result. Project Estimation report is size oriented matrix. Here,
constructive cost model Le COCOMO-2(1990) is used to estimate effort And time duration by
using size of software. Suze in terms of the KLOC(kilo Line Of Code). It include only executable
lines not variable, function declaration
2. Project Resources
To undertake your image forgery detection project with deep learning, you'll need a combination
of crucial resources. Start with diverse datasets like CASIA, COVERAGE, and Image Manipulation
Dataset (IMD) for training and testing. If you're focusing on face spoofing or video forgery,
consider NUAA Image Dataset and YouTube Face Dataset, along with dedicated deepfake
XV
detection datasets. For the technical side, make Python your primary language and leverage deep
learning frameworks like TensorFlow and PyTorch. Tools such as OpenCV for image processing
and Scikit-Learn for evaluation are invaluable. Explore Keras for its simplicity and pre-trained CNN
models like ResNet, VGG, and Inception. Stay informed by delving into research papers on image
forgery detection, and regularly check platforms like arXiv for the latest developments.
Complement your knowledge with online courses and tutorials, and for efficient model training,
consider GPU/TPU resources available on cloud platforms like AWS, Google Cloud, and Azure.
Join forums and communities for problem-solving, refer to official documentation for guidance,
and follow blogs and YouTube channels specializing in deep learning and computer vision for
insightful tips and tutorials. These resources will form the foundation of your successful project.
Chapter 2
Technical Keywords
Computer Vision: Your project will heavily rely on computer vision techniques, as it involves the
analysis and manipulation of digital images. Computer vision is concerned with the automatic
extraction of information from images and is a fundamental component of your image forgery
detection system.
Image Processing: Image processing is a core component of your project. This includes tasks
such as image enhancement, feature extraction, and filtering to preprocess and analyze images
effectively. Image processing techniques will help your deep learning model identify image
forgeries.
Deep Learning: Deep learning is the primary technology behind your project. You'll be using
convolutional neural networks (CNNs) and potentially other deep learning architectures to develop
a model that can automatically detect image forgeries. Deep learning is a subset of machine
learning that excels at image classification and feature learning.
Machine Learning: Beyond deep learning, your project may also involve traditional machine
learning techniques for data preprocessing, feature engineering, and model evaluation. These are
essential for building a robust forgery detection system.
XVI
Image Forensics: Image forensics is a specialized field within computer vision that deals with the
analysis of digital images to detect manipulation or forgeries. Your project is essentially a practical
application of image forensics techniques.
Data Science: You will need strong data science skills to curate and preprocess datasets, evaluate
model performance, and make data-driven decisions throughout your project.
Ethics and Privacy: Consider the ethical implications of image forgery detection, especially in
terms of privacy and consent. Addressing these concerns is important in any project dealing with
image analysis.
Cybersecurity: In cases where image forgery is used for malicious purposes, your project aligns
with aspects of cybersecurity by providing a tool to detect and prevent digital deception.
Media and Journalism: In the context of journalism and media, your project can contribute to the
verification of image authenticity and help combat the spread of fake news and misinformation.
Content Moderation: In the realm of online content, your project can be applied to content
moderation platforms to ensure that manipulated or inappropriate images are not shared.
XVII
Chapter 3
Introduction
XVIII
Chapter 4
4.4 Outcome
The envisioned outcome of our image forgery detection project is the creation of a reliable and
precise deep learning-based system designed to automatically detect various forms of image
manipulation, such as copy-move and splicing. This system will serve as a valuable tool for
verifying the authenticity of digital images, making significant contributions to the domains of
digital forensics, journalism, and online content moderation. We expect to achieve outstanding
performance, characterized by high precision, recall, and overall model accuracy. This will be
accomplished through meticulous dataset selection, the use of innovative deep learning
architectures, and rigorous model evaluation. Furthermore, our project aims to increase public
awareness of the prevalence of image forgeries and their potential societal impact, while
encouraging the responsible use of digital media.
4.5 Applications
XX
Digital Forensics: Our project is essential for digital forensics investigations. It enables the
analysis of digital images to uncover various types of forgery, such as splicing, copy-move, and
retouching. This is invaluable for verifying image authenticity and maintaining the integrity of
evidence.
Journalism and Media: In the realm of journalism and media, our system plays a critical role in
verifying the authenticity of images. It ensures the publication of reliable content, helping to
combat the dissemination of fake news and misinformation by detecting manipulated images.
Online Content Moderation: Content moderation platforms can benefit from our project's ability to
automatically detect and filter out inappropriate or manipulated images. This guarantees a safe and
trustworthy online environment.
Law Enforcement: Law enforcement agencies can employ our image forgery detection system to
aid criminal investigations, especially in cases involving digital evidence.
Cybersecurity: Our project is a valuable tool for cybersecurity, assisting in the detection and
prevention of digital deception. It is particularly relevant in situations where cybercriminals might
use manipulated images for fraudulent activities.
Privacy Protection: Our system is also applicable in contexts where individuals seek to safeguard
their own privacy and ensure that their images have not been altered without consent.
Academic and Research Purposes: Researchers and academics specializing in image analysis,
computer vision, and deep learning can leverage our project as a valuable resource for further
research and development in the field of image forensics.
2. IDE:Google Colab
3. Programming Language: Python 2.7 and above
Chapter 5
Project Plan
XXIV
1. Have top software and customer managers formally committed to sup-
port the project?
6. Does the software engineering team have the right mix of skills?
Impact
ID Risk Description Probability
Schedule Quality Overall
1 Description 1 Low Low High High
2 Description 2 Low Low High High
XXV
Probability Value Description
High Probability of occurrence is > 75%
Medium Probability of occurrence is 26 − 75%
Low Probability of occurrence is < 25%
Risk ID 1
Risk Description Description 1
Category Development Environment.
Source Software requirement Specification document.
Probability Low
Impact High
Response Mitigate
Strategy Strategy
Risk Status Occurred
XXVI
Risk ID 2
Risk Description Description 2
Category Requirements
Source Software Design Specification documentation review.
Probability Low
Impact High
Response Mitigate
Strategy Better testing will resolve this issue.
Risk Status Identified
Risk ID 3
Risk Description Description 3
Category Technology
Source This was identified during early development and test-
ing.
Probability Low
Impact Very High
Response Accept
Strategy Example Running Service Registry behind proxy bal-
ancer
Risk Status Identified
XXVII
5.3 Project Schedule
5.3.1 Project task set
Major Tasks in the Project stages are:
XXVIII
5.4 Team Organization
The manner in which staff is organized and the mechanisms for reporting are
noted.
XXX
Chapter 6
Software requirement
specification
6.1 Introduction
6.2.2 Use-cases
All use-cases for the software are presented. Description of all main Use cases
using use case template is to be provided.
XXXI
Sr No. Use Case Description Actors Assumptions
1 Use Case 1 Description Actors Assumption
XXXII
6.3 Data Model and Description
6.3.1 Data Description
Data objects that will be managed/manipulated by the software are described
in this section. The database entities or files or data structures required to
be described. For data objects details can be given as below
• Performance Requirements
XXXIII
6.4.4 State Diagram:
State Transition Diagram
Fig.6.2 example shows the state transition diagram of Cloud SDK. The states
are represented in ovals and state of system gets changed when certain events
occur. The transitions from one state to the other are represented by arrows.
The Figure shows important states and events that occur while creating new
project.
Heterogeneous Data Sources: If your project involves data from various sources and formats,
integrating and processing these diverse data types can be a significant constraint.
XXXIV
Real-Time Processing: For applications that require instant forgery detection, processing speed
becomes a critical constraint, and you may need to optimize the model for low latency.
Cross-Domain Generalization: If the model needs to perform well on images from different
domains (e.g., medical imaging and artistic creations), achieving cross-domain generalization can
be a challenging constraint.
Data Privacy and Compliance: Strict data privacy and compliance requirements can constrain data
collection, storage, and model deployment, especially in industries like healthcare and finance.
XXXV
Chapter 7
7.1 Introduction
This document specifies the design that is used to solve the problem of Prod-
uct.
XXXVI
Figure 7.1: Architecture diagram
XXXVIII
Chapter 8
Project Implementation
8.1 Introduction
8.2 Tools and Technologies Used
8.3 Methodologies/Algorithm Details
8.3.1 Algorithm 1/Pseudo Code
8.3.2 Algorithm 2/Pseudo Code
XXXIX
Chapter 9
Software Testing
XL
Chapter 10
Results
10.2 Outputs
Outputs / Snap shots of the results
XLI
Chapter 11
XLII
Chapter 12
XLIII
Chapter 13
References
XLIV
Annexure A
References
XLV
Annexure B
Laboratory assignments on
Project Analysis of Algorithmic
Design
I D E A
Increase Drive Educate Accelerate
Improve Deliver Evaluate Associate
Ignore Decrease Eliminate Avoid
XLVI
Annexure C
Laboratory assignments on
Project Quality and Reliability
Testing of Project Design
XLVII
Annexure D
Project Planner
XLVIII
Annexure E
(At-least one technical paper must be submitted in Term-I on the project de-
sign in the conferences/workshops in IITs, Central Universities or UoP Con-
ferences or equivalent International Conferences Sponsored by IEEE/ACM)
1. Paper Title:
3. Paper accepted/rejected :
XLIX
Annexure F
Plagiarism Report
Plagiarism report
L
Annexure G
4. Test tool selection and testing of various test cases for the project per-
formed and generate various testing result charts, graphs etc. including
reliability testing.
Additional assignments for the Entrepreneurship Project:
LI
Annexure H
LII
photo.jpg
1. Name :
2. Date of Birth :
3. Gender :
4. Permanent Address :
5. E-Mail :
6. Mobile/Contact No. :
7. Placement Details :
8. Paper Published :
LIII