Deep filter bridge for malaria identification and classification in microscopic blood smear images
by Priyadarshini Adyasha Pattanaik; Tripti Swarnkar; Debabala Swain
International Journal of Advanced Intelligence Paradigms (IJAIP), Vol. 20, No. 1/2, 2021

Abstract: Malaria is a major global infectious health disease threat. The process of identifying and quantifying malaria is one of the most challenging tasks in the field of microscopy image processing due to variations in sample preparation and uncertainty of cell classes. However, motivated by the challenges, we present a novel simplified deep learning model; deep filter bridge, combining multi-rolling stacked denoising autoencoder (SAE) and fisher vector (FV) to automatically classify the different types of single cells in microscopic blood smear images as either infected or uninfected. The results indicate that the proposed model SAE kernels can extract representative malaria features from large unlabelled data and extreme learning machine (ELM) is used as a final ensemble base classifier to improve the learning speed of the algorithm. We have experimentally evaluated performance based on 39000 single cell elements in a ten-fold cross-validation, obtaining average classification F-score and accuracy at 98.36% and 98.12% respectively, on the microscopic blood smear image datasets.

Online publication date: Thu, 16-Sep-2021

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Advanced Intelligence Paradigms (IJAIP):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com