Experimental and Theoretical Verification: Detection of Exact Ten Disease from Real Blood Sample
Date
2019-04-30
Student ID
Research Supervisor
Editor
Journal Title
Volume
Issue
Journal Title
Journal ISSN
Volume Title
Abstract
This project is implemented using machine learning technique to classify different disease by determining various shapes of red blood cells. Microscopic images of real red blood cells smears are used to train our software. A deep convolutional neural network is used for the implementation. Compared to traditional methods that use tedious hand engineering feature extraction, the proposed method uses deep learning in an end-to-end arrangement that performs both feature extraction and classification directly from the raw segmented patches of the red blood smears. So we developed a system by using deep convolutional networks in order to find the classification of RBC & cell segmentation which may help us to measure patient’s disease type. We first take microscopic images of diseased RBC and created rbc patch. Than we use deep convolutional neural network (CNN) to realize RBC classification. The proposed model gives an accuracy of 97.64% on the hold out test. Our method can detect 10 blood shape variance.
Description
Keywords
Citation
Department Name
Electrical and Computer Engineering
Publisher
North South University