A rule-based optical character recognition system for the recognition of serial number on Renminbi (RMB) banknote is presented. It is based on the observation that the characters, including English letters and numbers, can be classified using two hand-crafted features, which are the opening and the loop. Each character has certain characteristics in terms of those two features and classification is achieved following the proposed scheme. The proposed system has been tested on 2245 RMB bills, which contain 22313 characters, and accomplished 99.35% for horizontal characters and 99.84% for vertical characters under 30ms processing time per banknote.