Skin Disease Detection Using Image Processing

ABSTRACT

Dermatological diseases are the most prevalent diseases worldwide. Even

though being common, diagnosis is extremely difficult and requires extensive
experience in the domain. In this project, we provide an approach to detect various
kinds of these diseases. Computer vision and Machine learning are dual stages that
we used to identify diseases accurately. Our objective of the project is to detect the
type of skin disease easily with accuracy and recommend the best. In the first stage
of the image the skin disease is subject to various kinds of pre-processing
techniques followed by feature extraction. Then the second stage involves it uses
Machine learning algorithms to identify diseases based on the analyzing and
observance of the skin. The proposed system is highly beneficial in rural areas
where access to dermatologists is limited. For this proposed system, we use
Pycharm based python script for experimental results.

LITERATURE SURVEY
Gerald Schaefer;Roger Tait;Shao Ying Zhu made a survey on Overlay of thermal and visual
medical images using skin detection and image registration.Thermography captures the
temperature distribution of the human skin and is employed in various medical applications. Often
it is useful to cross-reference the resulting thermograms with visual images of the patient, either to
see which part of the anatomy is affected by a certain disease or to judge the efficacy of the
treatment. An attractive approach to provide this information is to overlay the two image types
and show a composite image to the clinician. Producing such an overlay however is a non-trivial
task due to differences in image capturing conditions of the two modalities. In this paper we
introduce an approach that produces accurate overlays of thermal and visual medical images. First
unnecessary background information of the visual part are removed by an image segmentation
step based on skin detection. The thermal image is then aligned through an intensity based image
registration technique. Experimental results based on an set of visual-thermal image pairs
demonstrate the effectiveness of the proposed approach
Archana Ajith;Vrinda Goel;Priyanka Vazirani;M. Mani Roja made a survey on Digital
dermatology: Skin disease detection model using image processing
This paper proposes a skin disease detection method based on image processing techniques. This
method is mobile based and hence very accessible even in remote areas and it is completely
noninvasive to patient's skin. The patient provides an image of the infected area of the skin as an
input to the prototype. Image processing techniques are performed on this image and the detected
disease is displayed at the output. The proposed system is highly beneficial in rural areas where
access to dermatologists is limited.

Lincy Vincent;J Roopa Jayasingh made a survey on Comparison of

Psoriasis Disease Detection and Classification Through
Various Image Processing Techniques-A Review
Skin disease is the major problem that we facing today. There are many reasons for skin
diseases such as food, water, environmental conditions and so on. Among such diseases,
Psoriasis is one of them. Psoriasis could be a skin contamination that causes reddish,
aggravated flaky patches, most normally on the knees, elbows, trunk and scalp. Psoriasis
could be a typical, long haul contamination (tenacious) with no cure. It tends to go through
cycles, which means it occurs continuously for weeks or months. Skin illnesses such as
psoriasis has lower affect on death rate but have more prominent affect on the quality of life.
There are various types of image processing techniques for the psoriasis disease identification
and classification. In this paper we compare the different techniques used in past for
preprocessing, segmentation, feature extraction and classification. After comparing different
techniques we make a new model approach for the psoriasis disease detection and
classification having high efficiency and accuracy.
K. Veera Swamy;B. Divya made a survey on Skin Disease Classification using Machine
Learning Algorithms
Skin diseases are the large number of spread diseases in the world. Their diagnoses are very
difficult because of its difficulties in skin texture, presence of hair on skin and color. It is
required to develop methods like machine learning in order to increase the accuracy of
diagnosis for various types of skin diseases. Machine learning techniques are widely used in
medical fields for diagnosis. These algorithms use feature values from images as input to
make a decision. The process consists of three stages-The feature extraction stage, the
training stage and the testing stage. The process makes use of machine learning technology to
train itself with the various skin images. The objective of this process is to increase accuracy
of skin disease detection. Three important features in image classification are texture, color,
shape, and combination of these. In this work, color and texture features are used to classify
the skin disease. Normal skin color is different from the skin with disease. Smoothness,
coarseness, and regularity is effectively identified using texture features in the images.
Hence, these two features are explored to identify skin disease effectively

K. Melbin;Y.Jacob Vetha Raj made a survey on An Enhanced Model

for Skin Disease Detection using Dragonfly Optimization based Deep Neural Network. In
this paper, we have proposed an efficient skin disease identification approach using enhanced
deep neural network model. The database images are segmented using enhanced level set
approach-based segmentation. Feature extraction is carried out for all the images to retrieve
the feature vector using GLCM. Finally, dragonfly optimization-based deep neural network is
utilized for the classification of skin diseases. The system is implemented in the working
platform of MATLAB, and the proposed dragonfly based DNN is evaluated using existing
methods such as SVM, ANN for different evaluation metrics such as accuracy, sensitivity,
and specificity to show the system efficiency.

Ma. Christina R. Navarro;Edward Bustillos;Davood Pour Yousefian Barfeh made a

survey on Skin Disease Analysis using Digital Image processing
This research study is focused on the detection and classification of skin diseases with the use of the
Improved Bag of Features Algorithm. The training dataset were gathered from different sources such
as Medical Websites, derma clinic, and captured image through Android mobile device. The needed
data for this study are the sample images of Acne and Boil both as training dataset and test data.
Training and test data will be used in the process of skin disease detection and classification using the
Bag of Features Algorithm. This study used the combined Speed-Up Robust Features (SURF)
algorithm for features extraction. These extracted features from the training dataset will be use to
compare to the features of the test data coming from the actual captured image. K-Means clustering to
cluster the extracted features that will be used to create a visual dictionary and LIBSVM for
classifying kind of skin disease that the person has to avoid self-diagnosing and misunderstanding the
early stage symptoms of the disease, which is common here in Philippines. This study offers a high
speed prediction. The expected output from this study is the predicted type of skin disease does the
person has.

Md. Asaduzzaman Rasel;S. M. Rukunuddin Osmani;Shahed Al Hasan;Md. Hasan;

made a survey on Analyzing Skin Pigment Discoloration on Cheeks
by Using Image Processing
Melanin is the pigment that discerns the color of human skin. The special cells produce
melanin in the skin. If these cells are damaged or unhealthy, skin discoloration is visible. Skin
pigment discoloration on cheeks is a hazardous fact as a symptom of human skin disease with
a possibility of losing natural beauty. The extracted information of the skin discoloration can
work as a guide to diagnosis the disease. In this research, different imaging techniques like
watershed method, edge detection and morphological operations are used to analyze and
extract the information of cheek’s discoloration lesion by measuring the pixel number of
lesion on skin. The image analyzing results are visually examined by the skin specialist and
are observed to be highly accurate. The visual results are presented in the description and the
accuracy of mathematical analysis is 94.88 percent.

Md Nafiul Alam;Tamanna Tabassum Khan Munia;Kouhyar Tavakolian;Fartash

Vasefi;Nick MacKinnon;Reza Fazel-Rezai made a survey Automatic detection and
severity measurement of eczema using image processing
Chronic skin diseases like eczema may lead to severe health and financial consequences for
patients if not detected and controlled early. Early measurement of disease severity,
combined with a recommendation for skin protection and use of appropriate medication can
prevent the disease from worsening. Current diagnosis can be costly and time-consuming. In
this paper, an automatic eczema detection and severity measurement model are presented
using modern image processing and computer algorithm. The system can successfully detect
regions of eczema and classify the identified region as mild or severe based on image color
and texture feature. Then the model automatically measures skin parameters used in the most
common assessment tool called “Eczema Area and Severity Index (EASI),” by computing
eczema affected area score, eczema intensity score, and body region score of eczema
allowing both patients and physicians to accurately assess the affected skin.

John Marnel M. San Pedro;Davood Pour Yousefian Barfeh made a survey

Tuberculin skin test checker using digital image processing
The wheal, produced by tuberculin skin tests, was identified by nurses through marking its
edges. Four marks will be made and these will be measured - the greatest length of each mark
to another mark is considered the size of the wheal. An attempt to imitate the procedure was
done by designing a system that can measure the marked sides of the wheal. The
implemented system uses an algorithm which locates the four marks in an image. These four
marks were measured using the Euclidean distance to determine the distance between each
other. Among the 6 edges of the four marks, the one with the greatest length is considered the
size of the wheal. Using a scale with a defined size, the pixel value of the greatest length was
converted in millimeters. The results showed that the system's measurement is always less
than the measurement of the nurse. With an accuracy of 91.53% for the test data, the
researcher was able to implement a system that can facilitate in reading the results of
tuberculin skin test.

Yasha Hasija;Nikhil Garg;Soumya Sourav made a survey Automated detection of

dermatological disorders through image-processing and machine learning
Dermatological Diseases are one of the biggest medical issues in 21 st century due to it's
highly complex and expensive diagnosis with difficulties and subjectivity of human
interpretation. In cases of fatal diseases like Melanoma diagnosis in early stages play a vital
role in determining the probability of getting cured. We believe that the application of
automated methods will help in early diagnosis especially with the set of images with variety
of diagnosis. Hence, in this article we present a completely automated system of
dermatological disease recognition through lesion images, a machine intervention in contrast
to conventional medical personnel based detection. Our model is designed into three phases
compromising of data collection and augmentation, designing model and finally prediction.
We have used multiple AI algorithms like Convolutional Neural Network and Support Vector
Machine and amalgamated it with image processing tools to form a better structure, leading
to higher accuracy of 95.3%.