Recognition Research of Offline-handwritten Chinese Character Based on Biomimetic Pattern

AbstractNeurons of the basic strokes in handwritten Chinese character are built to coverage handwritten Chinese character image by using pattern recognition extraction of the nearest neighbor method. And then by analyzed neurons in the coverage of the situation during the traversal, imitated character codes input method which human generalized, strokes of the type,quantity, location, the number and the type of consistency and intersection points are counted, Characteristic knowledge data-base tables of recognized handwritten are established. Simple and more complex handwritten Chinese characters in SCUT-IRAC database are tested. The method is proved to be close to human fault tolerance and veracity