Tattoos, a soft biometrie trait, are gradually being used to identify suspects in forensic science. Based on LAB color space and K-mean clustering, we propose a novel segmentation algorithm to improve the segmentation accuracy of color tattoos. The process consists of three parts. Firstly, we use K-mean clustering and human skin color segmentation in LAB color space to detect the skin area. Then, we employ the mathematical morphology processing to smooth the clear graphic image of the tattoo segment. Finally, we extract and detect the color tattoos segmentation according to the connectivity of tattoo regions. Compared with the existing methods, this method has low computational complexity. And results of extensive experiments show that the proposed algorithm not only overcomes the limitations of single algorithm, but also improves segmentation accuracy.