Plasmodium Parasite Detection on Thin Blood Smear Image using Double Thresholding and BLOB Analysis

Indonesia is one of the regions that contribute to the increasing number of malaria cases. In 2019, more than 250 million malaria cases were found in Indonesia. This phenomenon is caused by several factors, including the examination procedure. In Indonesia, the digital microscopic examination has become the gold standard procedure in detecting and diagnosing malaria, whereas this procedure requires considerable expertise. Hence, the rapid examination is difficult to ensure. In order to overcome this problem, several methods of malaria detection have been proposed with a different approach. Image processing and computer vision techniques have become a powerful approach in the development of early detection systems called computer-aided detection (CADe) and computer-aided diagnosis (CADx). Several previous findings reported their contributions in detecting Plasmodium parasites using image processing and computer vision. Recently, artificial intelligence, including machine learning and deep learning, also offered outstanding results in detecting the Plasmodium parasite. This paper aims to present a scientific review of recent image processing and computer vision applications for the development of CADe or CADx in order to assist the doctor in doing rapid detection and diagnosis.

show abstract

Plasmodium Parasite Detection on Thin Blood Smear Image using Double Thresholding and BLOB Analysis

Cited by 3 publications

References 16 publications

Plasmodium Parasite Detection Using Combination of Image Processing and Deep Learning Approach

Plasmodium Parasite Detection Using Combination of Image Processing and Deep Learning Approach

Deep Learning for Detecting Malaria Parasites of Infected Red Blood Cells in Thin Blood Smear Images

A Review on Digital Microscopic Images for Plasmodium Parasite Detection

Contact Info

Product

Resources

About