10.46243/jst.2020.v5.i3.pp248-250 registered

Malaria is one in all the life threatening diseases. Diagnosis of diseases like malaria is very hooked in to the identification of parasites in blood. Various methods are applied for this process. The majority of all method uses machine learning to identify the malarial parasites. This method has shortcomings in long training time and also the must be retrained if a replacement data emerged. Among all of the other various methods that are used, identification using feature based recognition is likely to be rarely used. This method is powerful within the term that it doesn't require training process, but only an image sample from which the feature are visiting be extracted. During this paper, we design an identification process for blood parasites using one all told the famous local feature extraction algorithms, i.e. SURF (Speeded-Up Robust Features). In our experiment, we evaluate the system to spot Plasmodium parasites. During this experiment, we are focusing only on parasite’s gametocyte stage. Here, we use the system to spot whether or not the parasite is Plasmodium falciparum, Plasmodium malariae, Plasmodium ovale, or Plasmodium vivax.