The identification and division of different components rock image are of great significance in the field of geological research. It is time-consuming and subjective to identify the rock thin sections artificially under the microscope, and the analysis results are difficult to quantify and characterize. Therefore, the use of digital image processing technology to analyse the rock image has become a hot topic in current research. It is difficult to obtain the ideal result by applying the image segmentation algorithm to the rock image for component division directly, and it can’t meet the requirements of rock image analysis. Therefore, in this paper, some weights are used to combine the color features of the rock components with the texture features, and the FCM clustering algorithm is used to achieve the division and identification of rock components. The experimental results show that the algorithm can more accurately classify sandstone particles, pores, feldspar and other minerals.