The class imbalance problem in TLC image classification

• Type: Article in International Scientific Journal
• Date: 2006

Authors

Antonio V Sousa (Author) Other; Ana Maria Mendonca (Author) FEUP; Aurelio Campilho (Author) FEUP

Journal

The Journal is awaiting validation by the Administrative Services.

Title: IMAGE ANALYSIS AND RECOGNITION, PT 2

Vol. 13

Pages: 513-523

Indexing

ISI Proceedings

ISI Web of Knowledge - 3 Citations

ISI Web of Science

Scopus - 3 Citations

Scientific classification

FOS: Natural sciences > Computer and information sciences

CORDIS: Technological sciences > Engineering > Biomedical enginnering

Other information

Authenticus ID: P-004-PXN

DOI: 10.1007/11867661_46

Abstract (EN): The paper presents the methodology developed to solve the class imbalanced problem that occurs in the classification of Thin-Layer Chromatography (TLC) images. The proposed methodology is based on resampling, and consists in the undersampling of the majority class (normal class), while the minority classes, which contain Lysosomal Storage Disorders (LSD) samples, are oversampled with the generation of synthetic samples. For image classification two approaches are presented, one based on a hierarchical classifier and another uses a multiclassifier system, where both classifiers are trained and tested using balanced data sets. The results demonstrate a better performance of the multiclassifier system using the balanced sets.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 11