HEp-2 Cell Classification: The Role of Gaussian Scale Space Theory as A Pre-processing Approach

摘要

\textit{Indirect Immunofluorescence Imaging of Human Epithelial Type 2}(HEp-2) cells is an effective way to identify the presence of Anti-NuclearAntibody (ANA). Most existing works on HEp-2 cell classification mainly focuson feature extraction, feature encoding and classifier design. Very few effortshave been devoted to study the importance of the pre-processing techniques. Inthis paper, we analyze the importance of the pre-processing, and investigatethe role of Gaussian Scale Space (GSS) theory as a pre-processing approach forthe HEp-2 cell classification task. We validate the GSS pre-processing underthe Local Binary Pattern (LBP) and the Bag-of-Words (BoW) frameworks. Under theBoW framework, the introduced pre-processing approach, using only one LocalOrientation Adaptive Descriptor (LOAD), achieved superior performance on theExecutable Thematic on Pattern Recognition Techniques for IndirectImmunofluorescence (ET-PRT-IIF) image analysis. Our system, using only onefeature, outperformed the winner of the ICPR 2014 contest that combined fourtypes of features. Meanwhile, the proposed pre-processing method is notrestricted to this work; it can be generalized to many existing works.