A High Variant Blood Smear Image Dataset With Comparative Benchmarks of Deep Learning, Machine Learning and Image Processing Techniques

Date
2020
Research Supervisor
Editor
Journal Title
Volume
Issue
Journal Title
Journal ISSN
Volume Title
Abstract
Along with the technological advancement in the area of computer technologies, billions of computations can be done in minutes. This ability of supercomputing inspires researchers to develop artificial intelligence that can perform human like activities. Application of artificial intelligence in medical image analysis is increasing day by day with the development of new deep learning, machine learning and image processing algorithms. Despite the development, there is shortage of quality and large quality datasets. Large datasets are needed to train, validate and test new and existing algorithms to their fullest potential. To address this issue, we have embarked upon a project of creating a large microscopic blood smear image dataset. Along with the dataset, we have provided benchmark performances of different algorithms in deep learning, machine learning and image processing. We anticipate that the dataset and baseline performances we have provided by this project will contribute to a great extent in research and development of new ideas in the area of medical image analysis.
Description
Keywords
Citation
Department Name
Electrical and Computer Engineering
Publisher
North South University
Printed Thesis
DOI
ISSN
ISBN