Lung Tissue Classification for Lung Disease Diagnosis

Abstract

In this paper, a new method for Lung tissue Classification using Patch adaptive sparse approximation with two feature descriptors is proposed. Operator assisted classification methods are impractical for large amounts of data .High resolution Computed Tomography images contain a noise caused by operator performance which can lead to serious inaccuracies in classification. We design two new feature descriptors for higher feature descriptiveness, namely the rotation-invariant Gabor-local binary patterns (RGLBP) texture descriptor and multi-coordinate histogram of oriented gradients (MCHOG) gradient descriptor. Each image patch is then labeled based on its feature approximation from reference image patches. Decision making was performed in two steps, Feature extraction using the two feature descriptors ii) classification using Patch adaptive sparse approximation.