Uyghur new text character recognition generally use the large dimension feature for the recognition work. This kind of recognition method will be more time-consuming

but the accuracy is often higher.Nevertheless

recognition based on small dimension feature can be more time-saving but lower evaluation accuracy. The ideal recognition requires not only a high speed but also need high accuracy. In order to solve this problem

this paper chose the whole word recognition method to avoid the shortcoming of word recognition after recognize each letter in the word. Therefore

this research selected outlines including outer contour on the baseline

the inner contour in the baseline and the outer contour behind the baseline as main feature to realize the feature extraction work. For the words that couldn't be recognized in a unique identification

the second recognition test using complimentary characteristics was carried out.After testing

this method not merely ensured the high speed of small dimension but also got high precision in high dimension. The experiment result shows that the recognition rate of this system is about 90%

and its average recognition time and its speed are in the acceptable range of the accrual requirements.