Title :
Reading handwritten digits: a ZIP code recognition system
Author :
Matan, Ofer ; Baird, Henry S. ; Bromley, Jane ; Burges, Christopher J.C. ; Denker, John S. ; Jackel, Lawrence D. ; Le Cun, Yann ; Pednault, Edwin P D ; Satterfield, William D. ; Stenard, Charles E. ; Thompson, Timothy J.
Author_Institution :
AT&T Bell Lab., Holmdel, NJ, USA
fDate :
7/1/1992 12:00:00 AM
Abstract :
A neural network algorithm-based system that reads handwritten ZIP codes appearing on real US mail is described. The system uses a recognition-based segmenter, that is a hybrid of connected-components analysis (CCA), vertical cuts, and a neural network recognizer. Connected components that are single digits are handled by CCA. CCs that are combined or dissected digits are handled by the vertical-cut segmenter. The four main stages of processing are preprocessing, in which noise is removed and the digits are deslanted, CCA segmentation and recognition, vertical-cut-point estimation and segmentation, and directly lookup. The system was trained and tested on approximately 10000 images, five- and nine-digit ZIP code fields taken from real mail.<>
Keywords :
character recognition; computerised pattern recognition; computerised picture processing; neural nets; ZIP code recognition system; connected-components analysis; directly lookup; handwritten digits reading; neural network algorithm-based system; neural network recognizer; recognition-based segmenter; vertical cuts; vertical-cut-point estimation; Character recognition; Handwriting recognition; Image processing; Image recognition; Information systems; Laboratories; Man machine systems; Pattern recognition; Research and development; Robustness;
