BANKNOTE RECOGNITION AND CLASSIFICATION METHOD AND SYSTEM

摘要

Disclosed are a banknote recognition and classification method and system. In the method and system, a large number of reliable samples which are easy to acquire currently are used to establish a sample signal degradation model which meets application requirements by means of a statistical method, to simulate banknote states such as completely new in fineness, 80%-90% new in fineness, 70%-80% new in fineness, less than 70% new in fineness, existence of different degrees of dirt, existence of different degrees of incompletion, existence of different degrees of cracks, and existence of folds in some areas, then a classifier learns to perform classification and recognition on a sample to be recognized, thereby accurately obtaining a classification result, and reducing the cost as well as the efficiency of the development of banknote recognition products while ensuring improved classifier accuracy.