Dermatological disease detection using image processing and artificial neural network

Author

Yasir, Rahat ; Rahman, Md Arifur ; Ahmed, Nova

Author_Institution

Electron. & Comput. Eng. Dept., North South Univ., Dhaka, Bangladesh

fYear

2014

fDate

20-22 Dec. 2014

Firstpage

687

Lastpage

690

Abstract

Skin diseases are among the most common health problems worldwide. In this article we proposed a method that uses computer vision based techniques to detect various kinds of dermatological skin diseases. We have used different types of image processing algorithms for feature extraction and feed forward artificial neural network for training and testing purpose. The system works on two phases- first pre-process the colour skin images to extract significant features and later identifies the diseases. The system successfully detects 9 different types of dermatological skin diseases with an accuracy rate of 90%.

Keywords

computer vision; diseases; feature extraction; feedforward neural nets; medical image processing; skin; colour skin images; computer vision based techniques; dermatological disease detection; feature extraction; feed forward artificial neural network; image processing; skin diseases; Artificial neural networks; Diseases; Feature extraction; Filtering algorithms; Image color analysis; Liquids; Skin; Skin disease; artificial neural network; clustering; computer vision; dermatology;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Computer Engineering (ICECE), 2014 International Conference on

Conference_Location

Dhaka

Print_ISBN

978-1-4799-4167-4

Type

conf

DOI

10.1109/ICECE.2014.7026918

Filename

7026918