Abstract: This paper presents a novel pattern based feature descriptor named as Local Differential Excitation Binary Co- occurrence Pattern (LDEBCoP) for texture and biomedical image retrieval. The proposed method exploits the local structure information using differential excitation. Further, to produce more compact local binary patterns the adjacent neighbourhood pixel pairs are considered in the computation of differential excitation. In the proposed method, the co-occurrence of pixel pairs in local binary map have been observed using gray level co-occurrence matrix(GLCM) in different directions and distances for better feature representation. Previous methods have utilized histogram to obtain the frequency information of local pattern map but co- occurrence of pixel pairs is more robust than frequency of patternss...............
Keywords:Differential excitation, Local binary pattern, Image retrieval, GLCM, Pattern recognition.
[1] Ahonen, T., Hadid, A., and Pietikäinen, M., 2004, "Face recognition with local binary patterns", Computer Vision-ECCV 2004( Springer)., pp. 469–481.
[2] Ning,J., Zhang,D., and Wu,C.,2009 , "Robust object tracking using joint color texture histogram", J. Pattern Recognit. Artif. Intell.,23(7), pp. 1245–1263.
[3] Pietikäinen,M.,and Mäenpää,T.,2005, Texture analysis with local binary patterns, The Handbook of Pattern Recognition and Computer Vision, World Scientific Publishing, Singapore, pp. 197–216.
[4] Fernandez,A., Ghita, O., Gonzalez, E., Bianconi,F., and Whelan, P.F.,2011, "Evaluation of robustness against rotation of LBP, CCR and ILBP features in granite texture classification", Trans.on Mach. Graph. Vision., 22(6), pp. 913–926.
[5] Pietikäinen,M., Hadid, A.,Zhao,G., and Ahonen, T.,2011, Computer vision using local binary patterns, Computational Imaging and Vision(springer),London. doi:10.1007/978-0-85729-748-8.
