TY  - JOUR
T1  - Digital Dermatology
AU - Sugathan, Arsha AU - M. Shamsudeen, Fousia 
JO  - Research Journal of Applied Sciences
VL  - 15
IS  - 8
SP  - 253
EP  - 260
PY  - 2020
DA  - 2001/08/19
SN  - 1815-932x
DO  - rjasci.2020.253.260
UR  - https://makhillpublications.co/view-article.php?doi=rjasci.2020.253.260
KW  - Deep learning
KW  -classification
KW  -image processing
KW  -VGG16
KW  -support vector machine
AB  - Skin diseases are more common than other
diseases. These diseases may be caused by fungal
infection, bacteria, allergy or viruses, etc. Despite being
common its diagnosis is extremely difficult because of its
complexities of skin tone, color, presence of hair.
Treatment options for each type of disease are varying
depending on the prognosis of a disease. Traditional
method of initial clinical screening requires a visual
diagnosing by specialized expertise but the cost of
dermatologist to monitor is very high. 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
also still limited and very expensive. There are often
infections in skin due to viscus damages, therefore it’s
necessary to spot these diseases as soon as possible. Thus,
there is a need to develop an automated system of
classification for the early diagnosis of severity of the
disease and to prevent its spread. The proposed method is
built on well-known convolutional neural network
VGG16. The study focuses on improving the
classification accuracy of skin disease diagnosing. The
CNN Model is used to extract feature from the images
and feature set is given as an input to machine learning
algorithms like random forest, kNN and support vector
machine. The simulation result for the classification of
skin disease show the flexibility and effectiveness of the
proposed system. However, SVM has achieved a higher
classification accuracy of 98%.
ER  -