Tongue inspection is not only main content of four diagnostic methods "observation, auscultation and olfaction, interrogation, palpation" for TCM (Traditional Chinese Medicine), but also one of most important characteristics of TCM diagnostic methods. Traditional tongue inspection mainly depends on doctor's eyesight to diagnose a disease. The diagnostic result is not only restricted by doctor's knowledge level and diagnostic experience, but also influenced by external environment such as light and temperature. It is the only way to combine TCM expert's clinical experience with modern information technology to realize quantitative, objective and standard tongue inspection. Among tongue features, the color of tongue body and tongue coating and the distribution are the main contents for tongue inspection. A novel approach is proposed to separate tongue body and tongue coating of color tongue image based on FCM (fuzzy c-means). The clustering number and initial clustering centers are determined automatically, through analysis and processing of the hue histogram of tongue image. The experimental result indicates that this algorithm speeds up the clustering iteration enormously and reduces the system operation expenses comparing with standard FCM. The tongue body and tongue coating separation effect conforms to the view point of TCM better than that by threshold value segmentation method.