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 dierent 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.

• Type: Conference
• Year: 1993
• Where: NIPS
• Authors: Ralph Wolf, John C. Platt
• Keywords: Address Block, Address Block Location, Convolutional Neural Network, NIPS 1993, NIPS 2007