Ancient Tamil character recognition is an important research and application area on pattern recognition theory, which plays an important role on realizing automation of inputting character at all cases. In order to improve the rate of character recognition and decrease the time of recognition training, referencing to immune biological principle, an ancient Tamil character recognition algorithm based on artificial immune is proposed. The simulation results shown that the method has faster speed and higher accuracy than the traditional ancient Tamil character recognition based on neural network. The algorithm steals the merit of self-adaptive learning, and immune memory in the biology immune system, which can also be applied to abnormity detection and pattern recognition. Ancient Tamil character recognition includes complex per-processes such as; segmenting, smoothing filtering , normalizing and other processing. Different algorithms bring many differences in speed and accuracy of recognition.