• Tsedeke Temesgen Habe

Abstract-— Malaria is a grave infectious disease, according to the World Health Organization (WHO), it is accountable for nearly half million deaths each year in the year 2016 report. In the world there are three different manual malaria diagnosis techniques such as sign and symptoms, Rapid diagnosis and Microscopic. The aim of this study is work on analysis of suitable feature extraction techniques which is discovering to classify the complete life cycle stages of malaria. The proposed new feature extraction techniques is Gray level co-occurrence matrix (GLCM) textural feature. It is gives us the 12 features like Entropy, Energy (angular second moment), Correlation, mean smoothness, skewness, kurtosis, shade measure to compute results. Finally, after the feature extraction we applied the classifier techniques using artificial neural network used to detecting malaria parasite.

GLCM, Parasite, Histogram, RBC, Plasmodium, Malaria;

"FEATURE EXTRACTION OF MALARIA PLASMODIUM DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.4, Issue 12, page no.997-1001, December-2017, Available :http://www.jetir.org/papers/JETIR1712137.pdf

"FEATURE EXTRACTION OF MALARIA PLASMODIUM DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.4, Issue 12, page no. pp997-1001, December-2017, Available at : http://www.jetir.org/papers/JETIR1712137.pdf