|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
| ASCII Text | x | ||
| Ofer Matan, Henry S. Baird, Jane Bromley, Christopher J.C. Burges, John S. Denker, Lawrence D. Jackel, Yann Le Cun, Edwin P.D. Pednault, William D. Satterfield, Charles E. Stenard, Timothy J. Thompson, "Reading Handwritten Digits: A ZIP Code Recognition System," Computer, vol. 25, no. 7, pp. 59-63, July, 1992. | |||
| BibTex | x | ||
| @article{ 10.1109/2.144441, author = {Ofer Matan and Henry S. Baird and Jane Bromley and Christopher J.C. Burges and John S. Denker and Lawrence D. Jackel and Yann Le Cun and Edwin P.D. Pednault and William D. Satterfield and Charles E. Stenard and Timothy J. Thompson}, title = {Reading Handwritten Digits: A ZIP Code Recognition System}, journal ={Computer}, volume = {25}, number = {7}, issn = {0018-9162}, year = {1992}, pages = {59-63}, doi = {http://doi.ieeecomputersociety.org/10.1109/2.144441}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - MGZN JO - Computer TI - Reading Handwritten Digits: A ZIP Code Recognition System IS - 7 SN - 0018-9162 SP59 EP63 EPD - 59-63 A1 - Ofer Matan, A1 - Henry S. Baird, A1 - Jane Bromley, A1 - Christopher J.C. Burges, A1 - John S. Denker, A1 - Lawrence D. Jackel, A1 - Yann Le Cun, A1 - Edwin P.D. Pednault, A1 - William D. Satterfield, A1 - Charles E. Stenard, A1 - Timothy J. Thompson, PY - 1992 VL - 25 JA - Computer ER - | |||
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.