Automatic Classifier for Skin Disease Using k-NN and SVM

被引：8

作者：

Nosseir, Ann ^{[1
,2
]}

Shawky, Mokhtar Ahmed ^{[3
]}

机构：

[1] INP, Cairo, Egypt

[2] British Univ Egypt, BUE ICS Dept, Cairo, Egypt

[3] BUE ICS Dept, Cairo, Egypt

来源：

PROCEEDINGS OF 2019 8TH INTERNATIONAL CONFERENCE ON SOFTWARE AND INFORMATION ENGINEERING (ICSIE 2019) | 2019年

关键词：

Image recognition; k-NN classifier; Multi SVM;

D O I：

10.1145/3328833.3328862

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

Accurate diagnose of skin diseases from images is good for early treatment. This work develops a novel algorithm to differentiate between Warts, Hemangiomas and Vitiligo skin diseases. The algorithm is based on both skin color and texture features (features derives from the GLCM) to give a better and more efficient recognition accuracy of skin diseases. The work compares between accuracy of two supervised classifiers namely, k-nearest neighbor algorithm (k-NN) and Multi Support vector machine (SVM). The results of the K-NN is better 98.2%.

引用

页码：259 / 262

页数：4