<![CDATA[Purpose: Malaria, particularly the Falciparum strain, is a deadly disease caused by Plasmodium falciparum. Malaria diagnosis heavily relies on a microscopist's expertise. To expedite identification, machine learning research has been extensively conducted. However, it has not yet achieved high accuracy, partly due to the use of microscopic images as the dataset. Otsu thresholding, an optimal image segmentation method, maximizes pixel variance to separate the foreground (objects of interest) from the background, which is especially effective in various lighting conditions. Otsu thresholding aims to enhance accuracy and reliability in detecting and classifying Plasmodium falciparum parasites in blood samples.Methods: Dataset of microscopic images of thin blood smears with Plasmodium falciparum, taken from several sources, such as the UC Irvine Machine Learning Repository (UCI), National Institutes of Health (NIH), Kaggle, and Public Health Image Library (PHIL). The methodology combines various image processing techniques, including illumination correction, contrast enhancement, and noise filtering, to prepare the images effectively. The subsequent segmentation using Otsu thresholding method isolates the parasite regions of interest. The classification process involving CNN and SVM evaluates the performance of accuracy to identify different stages of Plasmodium falciparum parasites.Results: The research found the effectiveness of the Otsu thresholding segmentation method in identifying Plasmodium falciparum parasites in microscopic images. By utilizing Convolutional Neural Network (CNN) and Support Vector Machine (SVM) classifiers, the study achieved impressive accuracy rates, with the CNN achieving 96.5% accuracy and the SVM achieving 95.7%.Novelty: This research recorded significant improvement over previous studies that utilized feature extraction and selection methods. At the same time, previous research achieved an accuracy of 82.67. The key innovation here is the adoption of the Otsu thresholding segmentation method, which enhances the identification of Plasmodium falciparum parasites in microscopic images by integrating traditional image processing techniques like Otsu thresholding with modern machine learning methods like CNN and SVM. This significant improvement suggests that the proposed approach offers a more robust and reliable solution for malaria diagnosis.]]>
