Visual communication is important for a deft and/or mute person. It is also one of the tools for the communication between human and machines. In this paper, we develop an automatic Thai finger-spelling sign language translation system using Fuzzy C-Means (FCM) and Scale Invariant Feature Transform (SIFT) algorithms. We collect key frames from several subjects at different times of day and for several days. We also collect testing Thai finger-spelling words video from 4 subjects. The system achieves 79.90% and 51.17% correct alphabet translation and the correct word translation, respectively, with the SIFT threshold of 0.7 and 1 nearest neighbor prototype. However, when we change the number of nearest neighbor prototypes to 3, the system yields 82.19% and 55.08% correct alphabet and correct word translation, respectively, at the same SIFT threshold. These results are comparable with the manually-picked Rframe translation system.