Material Texture Retrieval Using Contourlet-2.3 and Three Statistical Features
To improve the retrieval rate of contourlet transform texture retrieval system, a contourlet-2.3 transform based retrieval system was proposed. Six different features, including mean, standard deviation, absolute mean energy, L2 energy, skewness and kurtosis contributions to retrieval rates were examined. Based on the single feature ability in retrieval system, a contourlet-2.3 retrieval system was proposed. The feature vectors were constructed by cascading the standard deviation, absolute mean energy and kurtosis of each sub-band contourlet coefficients and the similarity measure used here is Canberra distance. Experimental results on 109 brodatz texture images show that the new retrieval algorithm can lead to a higher retrieval rate than several contourlet transform retrieval systems including the original contourlet transform, non-subsampled contourlet transform under the same structure.
Zhong Cao, Lixian Sun, Xueqiang Cao, Yinghe He
X. W. Chen and Z. Q. Ma, "Material Texture Retrieval Using Contourlet-2.3 and Three Statistical Features", Advanced Materials Research, Vols. 233-235, pp. 2495-2498, 2011