VISVESVARAYA TECHNOLOGICAL UNIVERSITY
JNANA SANGAMA, BELAGAVI–590 018
A Project Report on
“SWASTHYA DIAGNOSIS: LEVERAGING CNN
FOR SKIN DISEASE DETECTION”
Submitted in partial fulfillment of the requirements for the VII and VIII
Semester of Bachelor of Engineering in Computer Science & Engineering
Submitted by:
Ms. Gayatri K. 2AV21CS012
Mr. Samadali M H. 2AV21CS041
Ms. Shivani A. 2AV21CS046
Mr. Shriram M P. 2AV21CS050
Under the Guidance of
Ms. Deepti Deshpande B.E, M. Tech
Assistant Professor
Dept. of CSE
AGMRCET, Varur
Department of Computer Science and Engineering
A.G.M Rural College of Engineering &
Technology, Varur-581 207
2024-2025
A. G. M Rural College of Engineering &Technology,
Varur-581 207
Department of Computer Science and Engineering
This is to certify that Ms. Gayatri K., Mr. Samadali M H., Ms.
Shivani A. and Mr. Shriram M P. bearing USN 2AV21CS012, 2AV21CS041,
2AV21CS046, 2AV21CS050 respectively have satisfactorily completed the
Project Work entitled “SWASTHYA DIAGNOSIS: LEVERAGING CNN FOR
SKIN DISEASE DETECTION” in partial fulfillment for the VII semester of
Bachelor of Engineering in Computer Science and Engineering of Visvesvaraya
Technological University Belagavi, during the year 2024-25. The project report
has been approved, as it satisfies the academic requirements in respect of the
project work prescribed for the said degree.
……….………………. ……….………………. ……….……………….
Project Guide HOD Principal/Director
Ms. Deepti Deshpande Mr. Shantabhushana B. M.
External Viva
Name of the Examiners: Signature with Date:
1.
2.
ACKNOWLEDGEMENT
The satisfaction and euphoria that accompany the successful completion of any
task would be incomplete without the mention of the people who made it possible,
whose constant guidance and encouragement crowned our efforts with success.
We would like to take this opportunity thank our Project Guide
[Link] Deshpande, Assistant Professor Department of Computer Science and
Engineering, without his immense guidance and support the work would have been
unthinkable. Also, we would like to thank our Project Coordinator [Link]
Beelagi, Assistant Professor, Department of Computer Science and Engineering, who
helped us in the completion of project work.
We deeply thank our HOD Mr. Shantabhushana B M, Department of
Computer Science and Engineering, for his unstinted support. We extend our gratitude
to the Principal Prof. Sandeep Kyatanavar, AGMRCET, Varur for his generous
support in all regards.
We extend our heartfelt thanks to all the faculty members, Teaching and Non-
Teaching Staff of the Department of Computer Science and Engineering, AGMRCET,
Varur who have helped us directly or indirectly. We are very much indebted to our
parents and friends for their unquestioning best cooperation and support.
Ms. Gayatri K. (2AV21CS012)
Mr. Samadali M H. (2AV21CS041)
Ms. Shivani A. (2AV21CS046)
Mr. Shriram M P. (2AV21CS050)
i
ABSTRACT
Skin diseases are among the most common health issues worldwide and often
require timely diagnosis and treatment. Manual diagnosis by dermatologists can be
time-consuming, subjective, and dependent on expertise. To address this, we propose a
deep learning-based skin disease classification system capable of identifying common
skin conditions such as acne, rashes, vitiligo, and lupus from images. The system
utilizes a convolutional neural network (CNN) architecture enhanced through transfer
learning with MobileNetV2, fine-tuning, and data augmentation to improve accuracy.
A user-friendly web application, built using Flask, allows users to upload images
and receive instant predictions on the type of skin condition. Additionally, the system
supports continuous learning by storing user inputs to enhance future training. This
smart diagnostic tool aims to assist healthcare professionals and individuals in early
skin disease detection, especially in resource-limited settings, offering a scalable and
accessible solution for dermatological care.
ii
CONTENTS
Acknowledgment i
Abstract ii
Contents iii
List of Figures iv
Chapter 1 INTRODUCTION 1
1.1 Motivation 3
1.2 Existing Model 3
1.3 Proposed Model 4
1.4 Problem Statement 4
1.5 Objectives 5
1.6 Challenges 5
1.7 Scope 5
Chapter 2 LITERATURE SURVEY 6
Chapter 3 DOMAIN ANALYSIS 10
3.1 Artificial Intelligence 10
3.2 Deep Learning 10
3.3 Computer Vision 11
3.4 Healthcare Informatics 12
3.5 Web Development 12
Chapter 4 METHODOLOGY 14
Chapter 5 REQUIREMENT SPECIFICATION 24
5.1 Hardware Requirements 24
5.2 Software Requirements 26
5.3 Functional Requirements 28
5.4 Non-Functional Requirements 29
Chapter 6 RESULTS AND DISCUSSION 31
CONCLUSION & FUTURE SCOPE 40
REFERENCES 49
iii
LIST OF FIGURES
Figure No. Figure Name Page No.
Figure 4.1 Project Flow 23
Figure 6.1 Classification Report from Output 33
Figure 6.2 Confusion Matrix from the output 34
iv
i