Relative Variance and Energy Featured Contourlet-2.3 Texture Retrieval
Contourlet-2.3 can capture texture information in images more efficiently than basic contourlet and has been studied for image retrieval situations,but we are still not satisfied with its retrieval rate due to feature extraction. Focus on improving the retrieval rate of contourlet-2.3 transform retrieval system,a new feature named relative variance was proposed and then contourlet-2.3 retrieval system with new combined features was constructed in this paper. The feature vectors were constructed by cascading the energy and relative variance of each sub-band contourlet-2.3 coefficients,and the similarity measure used here is Canberra distance. Experimental results on 109 brodatz texture images show that using the new features can make a higher retrieval rate than the combination of standard deviation and energy which is most commonly used today under the same retrieval time and hardware complexity,Furthermore,decomposition parameter of contourlet-2.3 transform can make some differences at retrieval rates.
content based image retrieval contourle-2.3 transform texture image retrieval energy relative variance
Xinwu Chen Yixian Shen Yaoxian Li
Xinyang Normal University,China Xinyang Energy Company,China
国际会议
西安
英文
1293-1296
2011-12-23（万方平台首次上网日期，不代表论文的发表时间）