Sciweavers

Share
NIPS
1993

Postal Address Block Location Using a Convolutional Locator Network

8 years 9 months ago
Postal Address Block Location Using a Convolutional Locator Network
This paper describes the use of a convolutional neural network to perform address block location on machine-printed mail pieces. Locating the address block is a dicult object recognition problem because there is often a large amount of extraneous printing on a mail piece and because address blocks vary dramatically in size and shape. We used a convolutional locator network with four outputs, each trained to nd a di erent corner of the address block. A simple set of rules was used to generate ABL candidates from the network output. The system performs very well: when allowed ve guesses, the network will tightly bound the address delivery information in 98.2% of the cases.
Ralph Wolf, John C. Platt
Added 02 Nov 2010
Updated 02 Nov 2010
Type Conference
Year 1993
Where NIPS
Authors Ralph Wolf, John C. Platt
Comments (0)
books