SwiftPost — A vision-based fast postal envelope identification system

A vision-based fast postal envelope identification system for moving machine printed Chinese postal envelopes is proposed. Our system uses a high-speed camera to capture the image of envelopes running on the convey device and then recognizes the postal address and postcode on the envelopes. A vocabulary of 4590 categories of characters are supported, which include 4516 frequently used Chinese characters defined in GB2312-80, 62 alphanumeric characters, and 12 punctuation marks and symbols. The supported font styles include Song, Fang Song, Kai, Hei, etc. with the printed font size of no less than 7.5 points. The experimental results on 761 mail images representing 25,060 characters show that an envelope with an average of 32.9 characters can be processed and recognized within 81.38 milliseconds and the character recognition rate of postal address is 98.72%. Furthermore, our system also provides the function to store the envelope images and their recognition results into database in real time, which can be used in subsequent envelopes tracking and management. The experimental results with live mails on site indicate that our system can reach a speed of 21,000 mails per hour, and the character recognition rate of postal address is as high as 98.92%. Besides, our system can be conveniently equipped on the envelope processing devices in postal service center.