Alireza Akhlaghi - M.S. Student, Dept. Computer and Informatics Engineering, Payame Noor University Qeshm, Iran
Mehdi Khalili - Assistant Professor, Dept. Computer and Informatics Engineering, Payame Noor University Tehran, Iran

Malaria is a serious infectious disease, and early and accurate diagnosis is necessary in order to keep it under control. In this paper, we propose an efficient algorithm to diagnose malaria using two-dimensional wavelet transform (DWT2) and a support vector machine (SVM). In the proposed algorithm, after preprocessing, the red blood cells were separated from images using an active contour model. Consequently, 840 features were extracted from the images using wavelet function. Finally, the features were classified into normal and abnormal groups by a multi SVM structure. The results show that compared to previous studies, the proposed algorithm led to improved results and accurately assessed 99.77% of 198 hospital records.

malaria; support vector machines; wavelet function; active contour models; multiple class SVM