e-ISSN: 2582-5208

International Research Journal of Modernization in Engineering Technology and Science

( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:05/Issue:05/May-2023 Impact Factor- 7.868 www.irjmets.com
SKIN DISEASE DETECTION USING MACHINE LEARNING AND
CONVOLUTIONAL NEURAL NETWORK
Ashwini Hipparage*1, Gitanjali Suryawanshi*2, Prachi Patil*3, Pranali Agale*4,
Prof. Shital Borse*5
*1,2,3,4Student, Information Technology, D.Y. Patil College of Engineering Ambi, Talegaon, Pune, India.
*5Guide, Information Technology, D.Y. Patil College of Engineering Ambi, Talegaon, Pune, India.
DOI : https://www.doi.org/10.56726/IRJMETS40689
ABSTRACT
Skin diseases are most common all over the globe, skin disease may be caused due to fungal infection, bacteria,
allergy, viruses, inheritance or exposure to chemicals. Environmental factors can also play a profound role in
common skin problems for example, UV radiations, climate conditions, pollution. It is very important to identify
and diagnosis the skin disease at the early stage. Earlier, the skin diseases are identified using biopsy process
which is analyzed and medicinal prescribed manually by the physicians. The advancement of lasers and
Photonics based medical technology has made it possible to diagnose the skin diseases much more quickly and
accurately. But the cost of such diagnosis is still limited and very expensive. So, image processing techniques help
to build automated screening system for dermatology at an initial stage.
To overcome this manual inspection and provide favorable results in short period of time, we propose a hybrid
approach combining Deep learning and machine learning techniques.
The patient provides an image of the infected area of the skin as an input to the prototype. Our objective of the
project is to detect the type of skin disease easily with accuracy and recommend the best solution. Different
machine learning (ML) and deep learning (DL) algorithms are used for diagnostic purposes. These methods
drastically improve the diagnosis process and also speed up the process.
Keywords: Skin Diseases; Image Processing; CNN; Machine Learning
I. INTRODUCTION
Skin is the most important and largest body part of the human. The 20 square feet of total body area of a human
is covered by skin. It protects different vital organs of the human body from outside harm and also protects from
microbes and the elements, regulates the body temperature, and allows the sensations of touch, heat, and cold.
But due to the variety of external and genetic factors, the skin may be influenced. Basically, three types of skin
diseases appear on human skin 1) Viral type, 2) Fungal type and 3) Allergic type.
The fungal and allergic-type diseases can be cure if it is diagnosis properly and recognize at its early stages. But
for viral types, it is very necessary to identify the disease in its early stages. Over the past few years, artificial
intelligence, machine learning, and deep learning techniques are rapidly developed in the medical field. With the
physical symptoms, image analysis is also very important to detect different skin diseases three different
machine learning processes and three different deep neural networks were used to predict different skin
diseases.
In many developing countries also people consult dermatologist for skin disease and prevention measures. The
people are uncertain of the medicinal prescriptions provided by the dermatologist and there is no justification in
the current system. Importance of skin disease without ignoring at the early stage is very important as skin plays
a major role in protecting the human body against fungal and harmful bacterial infections. Many people get skin
disease through their inheritance, job, lack of nutrition, regular habitats, exposed to chemicals etc. Environmental
factors also influence the existence of skin disease like climate, summer season, winter season.

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[7923]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:05/Issue:05/May-2023 Impact Factor- 7.868 www.irjmets.com
II. METHODOLOGY

Fig 1: Block Diagram of Proposed System

Fig 1 explains the overall Block Diagram of Proposed System for skin disease detection using image processing.
Preprocessing:
Achieving high performance of skin disease detection system requires overcoming some major difficulties. Such
as creating a database and unifying image dimensions. In the following section, the technique used in image
resizing is explained. Data preprocessing is a step in the data mining and data analysis process that takes raw
data to make it suitable for building and training machine learning model. Data Preprocessing include cleaning,
instance selection normalization, one hot encoding, transformation, feature extraction and selection, etc.
Image Resizing:
To resolve the problem of different image sizes in the database an input image is either increase or decrease in
size. Unifying the image size will get the same number of features from all images. Moreover, resizing the image
reduces processing time and thus increases system performance. Fig 3 shows the original image of size is
260×325 pixels. Fig 4 shows the resized image with the new size of 227×227 pixels.
Feature Extraction:
At the beginning, Convolutional Neural Network (CNN) is a set of stacked layers involving both nonlinear and
linear processes. These layers are learned in a joint manner. The main building blocks of any CNN model are:
convolutional layer, pooling layer, nonlinear Rectified Linear Units (ReLU) layer connected to a regular
multilayer neural network called fully connected layer, and a loss layer at the backend. CNN has known for its
significant performance in applications as the visual tasks and natural language processing.
Classification:
Classification is a computer vision method. After extracting features, the role of classification is to classify the
images via Support Vector Machine (SVM). A SVM can train classifier using extracted features from the training
set.

Fig 2. Image Classification using CNN

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[7924]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:05/Issue:05/May-2023 Impact Factor- 7.868 www.irjmets.com
Hardware used
• RAM: 4 GB
• Hard Disk: 2 GB of Disk space for development
• Processor: Minimum intel i3
• Smart Phone: Mobile with minimum of 2GB RAM
• Input Device: Phone Camera
Software Used
• Operating System: Windows 10
• Programming language: Python
• Anaconda
• Jupyter Notebook
The methodology utilized is carefully quality controlled. The technique includes the utilization of pre-prepared
picture recognizers with alterations to distinguish skin images. The measure confirms that the application is
without bug and it meets the necessities expressed in the prerequisites report of the system.
The overall experimental approach for skin disease detection using image processing and computer vision
techniques. In this the skin images are given into the system for processing. The input image is subjected to image
processing process like pre-processing, feature extraction and machine learning based classifier to predict skin
disease or not and recommend medicinal guidance based on the skin disease stage. The machine learning phase
invokes 3 steps: processing, training and detection steps.
CNN:
A convolutional neural network (CNN or ConvNet), is a network architecture for deep learning which learns
directly from data, eliminating the need for manual feature extraction. CNNs are particularly useful for finding
patterns in images to recognize objects, faces, and scenes.
Pooling Layer:
Pooling layers are used to reduce the dimensions of the feature maps. Thus, it reduces the number of parameters
to learn and the amount of computation performed in the network. The pooling layer summarises the features
present in a region of the feature map generated by a convolution layer.
III. FLOWCHART/ALGORITHM

Fig 5. Flowchart of Skin Disease detection

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science
[7925]
 e-ISSN: 2582-5208
International Research Journal of Modernization in Engineering Technology and Science
( Peer-Reviewed, Open Access, Fully Refereed International Journal )
Volume:05/Issue:05/May-2023 Impact Factor- 7.868 www.irjmets.com
Algorithm:
Efficient Net:
Efficient Net is a convolutional neural network architecture and scaling method that uniformly scales all
dimensions of depth/width/resolution using a compound coefficient. Unlike conventional practice that arbitrary
scales these factors, the Efficient Net scaling method uniformly scales network width, depth, and resolution with
a set of fixed scaling coefficients. EfficientNet uses a compound coefficient to uniformly scales network width,
depth, and resolution in a principled way.
MobileNetV3
MobileNetV3 is a convolutional neural network that is tuned to mobile phone CPUs through a combination of
hardware-aware network architecture search (NAS) complemented by the NetAdapt algorithm, and then
subsequently improved through novel architecture advances. Advances include
(1) Complementary search techniques,
(2) New efficient versions of nonlinearities practical for the mobile setting,
(3) New efficient network design.
IV. RESULT
[1] In the proposed system accepts user input images by developing an UI through which the user can provide
the respective skin images for analysis. The UI is developed using HTML.
[2] After we click on Camera there comes option on screen: Choose File
[3] The user has provided the skin image input and pre-processing steps are performed on the input images and
after pre-processing steps like image enhancement, edging the processed image.
[4] Briefs the input image is subjected to feature extraction and machine learning based classifier trained at the
backend and based on the input image provided by the user, feature extraction and classifier steps are performed.
Finally the prediction along with medicinal recommendation is suggested.
V. CONCLUSION
The proposed system is able to detect the skin disease with promising results combining computer vision and
machine learning techniques. It can be used to help people from all over the world and can be used in doing some
productive work. The tools used are free to use and are available for the user, hence, the system can be deployed
free of cost. The application developed is light-weight and can be used in machines with low system
specifications. It has also a simple user interface for the convenience of the user. The image processing and
machine learning algorithms were successfully implemented.
ACKNOWLEDGMENT
It was very simulating for us to work on the project entitled “Skin Disease Detection”. During this work we have
gained theoretical knowledge of great significance. We are greatly thankful to all faculty members of college to
guide us through this work. We are greatly obliged to our respected guide and Head of the Department.
An excessive thankful to “Prof. Shital Borse” for his suggestions, guidance and his help in our project. It has been
a highly encouraging and knowledge gaining experience. She has been a source of inspiration throughout the
project and has helped us in all problems. We also thankful to our parents and friends for their extended support
and valuable guidance.
VI. REFERENCES
[1] Ray, S. SVM | Support Vector Machine Algorithm in Machine Learning. Analytics Vidhya (2021).
[2] Patel, K. Image Feature Extraction: Traditional and Deep Learning Techniques. Medium (2020).
[3] Deep Learning Based Image Segmentation with AlexNet Feature Extraction for Classification of
Mammogram Images. International Journal of Pharmaceutical Research 13(01) (2021).
[4] Kaushik, A. Understanding ResNet50 architecture. OpenGenus IQ: Computing Expertise & Legacy (2020).
[5] Manasa, K., & Student, M. T Skin Cancer Detection Using VGG-16. European Journal of Molecular & Clinical
Medicine 08(01) (2021).

www.irjmets.com @International Research Journal of Modernization in Engineering, Technology and Science

[7926]