Title :
Two-Layer Method of Image Retrieval Based on Global Color Histogram and Local Color Spatial Features
Author :
Zhao, Jie ; Yan, Dong-ming ; Men, Guo-zun ; Zhang, Ying-Kang
Author_Institution :
Hebei Univ., Baoding
Abstract :
A new method based on two layers image retrieval is proposed. The first layer retrieval feature is global color histogram and the second one consists of the local color histogram, the averages and variances of the multi-scaling 2D wavelet decomposition coefficients. Difference weights are assigned to every block according to the importance of its spatial distribution. This method combines the advantages of the global and the local color histogram, thereby achieving the better retrieval performance.
Keywords :
image colour analysis; image retrieval; wavelet transforms; 2D wavelet decomposition; global color histogram; image retrieval; local color spatial features; Content based retrieval; Cybernetics; Educational institutions; Feature extraction; Histograms; Image databases; Image retrieval; Information retrieval; Machine learning; Multimedia databases; Color histogram; Feature extraction; Image retrieval; Spatial feature;
Conference_Titel :
Machine Learning and Cybernetics, 2007 International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-0973-0
Electronic_ISBN :
978-1-4244-0973-0
DOI :
10.1109/ICMLC.2007.4370849
