publication . Article . 1992

Reading handwritten digits: a ZIP code recognition system

Matan, Ofer; Baird, Henry S.; Bromley, Jane M.; Burges, Christopher J. C.; Denker, John S.; Jackel, Lawrence D.; Le Cun, Yann; Pednault, Edwin P. D.; Satterfield, William D.; Stenard, Charles E.; ...
Open Access
  • Published: 01 Jan 1992 Journal: Computer, volume 25, pages 59-63 (issn: 0018-9162, Copyright policy)
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
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 approx...
Subjects
ACM Computing Classification System: ComputingMethodologies_PATTERNRECOGNITION
free text keywords: Preprocessor, Pattern recognition, Handwriting recognition, Robustness (computer science), Segmentation, Connected component, Computer science, Speech recognition, Recognition system, Image processing, Artificial intelligence, business.industry, business, Artificial neural network
Related Organizations
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue