Discriminative Dictionary Learning by Exploiting Inter-Class Similarity for HEp-2 Cell Classi cation

Abstract

In this literature we present an algorithm for automatic classi cation of IIF images of HEp-2 cells into relevant classes. Our algorithm is majorly based on the \Dictionary Learning" algorithm and we have rede ned it's objective function to suit our purpose. The major di culty in HEp-2 cell image classi cation lies in it's low inter-class variability and substantial intra-class variations. To address these issues, we have modi ed the objective function of \Dictionary Learning" to learn inter-class features. Moreover, we used a local feature extractor based pre-processing stage and also a \spatial decomposition" classi er set-up for better classifying test images. We evaluated our algorithm on three most widely accepted bamechmark data-sets for HEp-2 cell classi cation, ICPR 2012, ICIP 2013 and SNP data-sets. Proposed algorithm has achieved superior results than other popular dictionary learning algorithms for HEp-2 cell classi cation. Moreover, when comparing with other algorithms for HEp-2 cell classi cation, including the winners of ICPR 2012, ICIP 2013 and SNP data-set, we show that proposed algorithm reports very competitive result. Though our proposed algorithm is designed to be application speci c to HEp-2 cell, still we evaluated its performance on another popular benchmark data-set, \Diabetic Retinopathy" data-set. Our algorithm provided higher accuarcy than other state-ofthe- art algorithms on that data-set too.