Research On Handwritten Chinese Characters Recognition System Based On Feedback Structure

The conventional method of handwritten Chinese characters recognition is usually a open-loop system. And the further improvement of the performance seems difficult. One of the difficulties lies in the trade-off between the recognition rate and the rejection rate. In another words, rejection methods are applied to increase the system's accuracy, but decrease the system's overall recognition rate and performance at the meantime. In this paper, a new system of handwritten character recognition is proposed to increase the system's accuracy without decreasing the recognition rate, which is based on feedback structure.(1)A system of handwritten Chinese characters recognition based on feedback structure is constructed. Three kinds of general characters recognition error are defined. Qualitative analysis of their types and quantitative analysis of their numberical values are made.(2)Decision-making and evaluation mechanism is established on the condition of the three kinds of general characters recognition error. The decision machine can judge whether the recognized characters are correct, and it can carry out the feedback correction of recognition method. The correction of recognition result can be gained. This system can improve the recognition rate and reduce the rejection rate at the same time, which are a couple of incompatible parameters.(3) The pretreatment of Chinese characters image is given to adapt the abstracting of the general characters recognition error.Handwritten Chinese characters in SCUT-IRAC are tested. The experiment results have shown that this method is effective. It can improve the recognition rate and reduce the rejection rate at the same time.