A high-accuracy two-stage recognition system for recognizing handwritten Chinese tent with 5401-category is demonstrated. In the first stage of the system, two matchingmodules are applied to recognize an input character simultaneously. A character is rejected at the first stage when the matching results of the two modules are not the same. A bigram Markov language model in the second stage can choose a candidate with high recognition rate for each rejected character according to the cont&ual infomzation.The overall recognition rate for the input ta? is 95.4%. 834 0-8186-4960-7193 $3.00 0 1993 E E E