Keskin, FurkanÇetin, A. EnisErşahin, TülinÇetin-Atalay, Rengül2016-02-082016-02-082012http://hdl.handle.net/11693/28162Date of Conference: 20-23 May 2012In this paper, we present a novel method for classification of cancer cell line images using complex wavelet-based region covariance matrix descriptors. Microscopic images containing irregular carcinoma cell patterns are represented by randomly selected subwindows which possibly correspond to foreground pixels. For each subwindow, a new region descriptor utilizing the dual-tree complex wavelet transform coefficients as pixel features is computed. WT as a feature extraction tool is preferred primarily because of its ability to characterize singularities at multiple orientations, which often arise in carcinoma cell lines, and approximate shift invariance property. We propose new dissimilarity measures between covariance matrices based on Kullback-Leibler (KL) divergence and L 2-norm, which turn out to be as successful as the classical KL divergence, but with much less computational complexity. Experimental results demonstrate the effectiveness of the proposed image classification framework. The proposed algorithm outperforms the recently published eigenvalue-based Bayesian classification method. © 2012 IEEE.EnglishBayesian classificationCancer cell linesCarcinoma cell linesCarcinoma cellsClassification frameworkCovariance matricesDescriptorsDissimilarity measuresDual-tree complex wavelet transformKL-divergenceKullback-Leibler distanceKullback-Leibler divergenceMicroscopic imageMultiple orientationsRegion covariance matrixesShift invarianceCell cultureCovariance matrixEigenvalues and eigenfunctionsFeature extractionImage classificationPixelsConference Paper10.1109/ISCAS.2012.6271692