Red blood cell segmentation and classification method using MATLAB

Ali Al Gamili, Abdullah Saleh (2016) Red blood cell segmentation and classification method using MATLAB. Masters thesis, Universiti Tun Hussein Onn Malaysia.

[img]
Preview
PDF
1074Kb

Abstract

Red blood cells (RBCs) are the most important kind of blood cell. Its diagnosis is very important process for early detection of related disease such as malaria and anemia before suitable follow up treatment can be proceed. Some of the human disease can be showed by counting the number of red blood cells. Red blood cell count gives the vital information that help diagnosis many of the patient’s sickness. Conventional method under blood smears RBC diagnosis is applying light microscope conducted by pathologist. This method is time-consuming and laborious. In this project an automated RBC counting is proposed to speed up the time consumption and to reduce the potential of the wrongly identified RBC. Initially the RBC goes for image pre-processing which involved global thresholding. Then it continues with RBCs counting by using two different algorithms which are the watershed segmentation based on distance transform, and the second one is the artificial neural network (ANN) classification with fitting application depend on regression method. Before applying ANN classification there are step needed to get feature extraction data that are the data extraction using moment invariant. There are still weaknesses and constraints due to the image itself such as color similarity, weak edge boundary, overlapping condition, and image quality. Thus, more study must be done to handle those matters to produce strong analysis approach for medical diagnosis purpose. This project build a better solution and help to improve the current methods so that it can be more capable, robust, and effective whenever any sample of blood cell is analyzed. At the end of this project it conducted comparison between 20 images of blood samples taken from the medical electronic laboratory in Universiti Tun Hussein Onn Malaysia (UTHM). The proposed method has been tested on blood cell images and the effectiveness and reliability of each of the counting method has been demonstrated.

Item Type:Thesis (Masters)
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800-8360 Electronics
ID Code:9197
Deposited By:Mr. Mohammad Shaifulrip Ithnin
Deposited On:27 Jul 2017 13:37
Last Modified:27 Jul 2017 13:37

Repository Staff Only: item control page