A new courtesy amount recognition module of a Check Reading System

A new courtesy amount recognition module of CENPARMI’s Check Reading System (CRS) is proposed in this paper. The module consists of 3 main segments: pre-processing, segmentation and recognition, and post-processing. A new feedbackbased segmentation algorithm is adopted for the segmentation task. Besides one individual numeral recognizer for numerals from ‘0’ to ‘9’, one convolutional neural network(CNN) recognizer for “00” and “000” numeral strings is also integrated into our module for the recognition task. The experimental results on the Quebec Bell Check database show that the recognition rate of the courtesy

• Type: Conference
• Year: 2008
• Where: ICPR
• Authors: Wu Ding, Ching Y. Suen, Adam Krzyzak
• Keywords: Amount Recognition Module, Computer Vision, Feedbackbased Segmentation Algorithm, ICPR 2008, Individual Numeral Recognizer