Abstract
In vitro identification and counting of red blood cells (RBCs) is very important to diagnose blood related diseases such as malaria and anemia before a proper treatment can be proposed. The conventional practice for such procedure is executed manually by pathologist under light microscope. However, manual visual inspection is laborious task and depends on subjective assessment which leads to variation in the RBC identification and counting. In this paper a computer-aided systems is proposed to automate the process of detection and identification of RBC from blood smear image. Initially RBCs region are extracted from the background by using global threshold method applied on green channel color image. Next, noise and holes in the RBCs are abolished by utilizing morphological filter and connected component labeling. Following that, information from the RBCs’ are extracted based on its geometrical properties. Eventually, the RBCs were classified as normal/abnormal by using Artificial Neural Network (ANN) classifier. The proposed method has been tested on blood cell images and demonstrates a reliable and effective system for classifying normal and abnormal RBC.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have