Color image feature extraction using color index local correlations and statistics
MI Xiao-li · Journal of Optoelectronics·laser · 2011
In this paper,a new color feature extraction method using color index local correlations and statistics(CILCS) is proposed.Pixels′ color was quantized and represented sparsely in a manner similar to the color indexing of color histograms.The local and overall correlations of color index distribution in a certain image area were calculated,and the correlations can reflect more color texture details than previous methods,and have shown some rotation-invariance,scale-invariance and shift-invariance.The experimental results of image retrieval and image classification demonstrate its effectiveness compared with previous methods.