Abstract: In the applications of converting color images into grayscale images,conventional Color2Gray algorithm fails to convey the visual information reflected by color difference,high time complexity,or human computing interaction,etc.Thus it is not ready for nowadays practical applications.To overcome these problems,a novel color2grey algorithm based on Gaussian mixture model (GMM) is presented.With the guidance of human eyes' perceptual mechanism for color images, the visual information modeling in color image is treated as a multidimensional data clustering problem.Firstly,re-sampling is carried out to get training data points.Then GMM is introduced to model these data points.Through a modified Gibbs sampling algorithm,the parameters of GMM and the number of Gaussian component are obtained automatically.Experimental results demonstrate that the proposed approach can perform color to gray rapidly and automatically.The visual information in the color image is preserved well in the resulted gray image.