The aim of this work is to find the best way for describing a given texture using a Local Binary Pattern (LBP) based approach. First several different approaches are compared, then the best fusion approach is tested on different datasets and compared with several approaches proposed in the literature (for fair comparisons, when possible we have used code shared by the original authors). Our experiments show that a fusion approach based on uniform Local Quinary Pattern (LQP) and a rotation invariant Local Quinary Pattern, where a bin selection based on variance is performed and Neighborhood Preserving Embedding (NPE) feature transform is applied, obtains a method that performs well on all tested datasets. As the classifier, we have tested a stand-alone support vector machine (SVM) and a random subspace ensemble of SVM. We compare several texture descriptors and show that our proposed approach coupled with random subspace ensemble outperforms other recent state-of-the-art approaches. This conclusion is based on extensive experiments conducted in several domains using six benchmark databases.
L. Nanni, S. Brahnam, A. Lumini (2012). Survey on LBP based texture descriptors for image classification. EXPERT SYSTEMS WITH APPLICATIONS, 39(3), 3634-3641 [10.1016/j.eswa.2011.09.054].
Survey on LBP based texture descriptors for image classification
LUMINI, ALESSANDRA
2012
Abstract
The aim of this work is to find the best way for describing a given texture using a Local Binary Pattern (LBP) based approach. First several different approaches are compared, then the best fusion approach is tested on different datasets and compared with several approaches proposed in the literature (for fair comparisons, when possible we have used code shared by the original authors). Our experiments show that a fusion approach based on uniform Local Quinary Pattern (LQP) and a rotation invariant Local Quinary Pattern, where a bin selection based on variance is performed and Neighborhood Preserving Embedding (NPE) feature transform is applied, obtains a method that performs well on all tested datasets. As the classifier, we have tested a stand-alone support vector machine (SVM) and a random subspace ensemble of SVM. We compare several texture descriptors and show that our proposed approach coupled with random subspace ensemble outperforms other recent state-of-the-art approaches. This conclusion is based on extensive experiments conducted in several domains using six benchmark databases.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.