Deep filter bridge for malaria identification and classification in microscopic blood smear images. (2nd September 2021)

• Record Type: Journal Article
• Authors: Pattanaik, Priyadarshini Adyasha; Swarnkar, Tripti; Swain, Debabala
• Is Part Of: International journal of advanced intelligence paradigms. Volume 20:Number 1/2(2021)
• Page Start: 126
• Page End: 137
• Publication Date: 2021-09-02
• Subjects: deep filter bridge -- fisher vector pooling layer -- malaria classification -- stacked sparse autoencoder; Artificial intelligence -- Periodicals; Machine theory -- Periodicals; Fuzzy logic -- Periodicals; 006.305
• Languages: English
• ISSNs: 1755-0386

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.