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 difficult 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 find a different 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 five guesses, the network will tightly bound the address delivery information in 98.2% of the cases.

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 difficult 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 find a different 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 five guesses, the network will tightly bound the address delivery information in 98.2% of the cases.

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 difficult 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 find a different 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 five guesses, the network will tightly bound the address delivery information in 98.2% of the cases. 1 INTRODUCTION The U.S. Postal Service delivers about 350 million mail pieces a day.

Commercial AI Trends Seen at AAAI-Extracting the Knowledge of 87 8(4): (Winter 19871, 93-95.

An important task in postal automation technology is determining the position and orientation of the destination address block in the image of a mail piece such as a letter, magazine, or parcel. Analysis of physical characteristics of mail pieces indicates that in order to automate the address finding task, several different image analysis operations are necessary. Some examples are locating a rectangular white address label on a multicolor background, progressively grouping characters into text lines and text lines into text blocks, eliminating candidate regions by specialized detectors (for example, detecting regions such as postage stamps), and identifying handwritten regions. Described here are several operations, their utility as predicted by statistics of mail piece characteristics, and the results of applying the operations to a task set of mail piece images.

Sargur N. Srihari is a professor and acting chairman of the Department of Computer Science, State University of New York (SUNY) at Buffalo. The author of "Recognizing Address Blocks on Mail Pieces," Srihari is an associate editor of the journal Pattern Recognition and is chairman of the technical committee on text-processing applications of the International Mike Baird, who coauthored the tribute to Kvetoslav Prazdny, is manager of Association for Pattern Recognition. Srihari is also currently directing two Intelligence Center 1185 Coleman Avenue, Santa Clara, California 95052. Jeffrey Stone is a consultant who watches the computer industry and Jonathan J. Hull is a research assistant Digital Equipment Corporation that reports new developments and trends. The opinions expressed "Recognizing Address Blocks on Mail address is Knowledge Systems Corporation, in his article are his own. Jeffrey Stout is on the research staff of computer vision, and artificial intelligence. An Expert Elevator report on AI and education, is an Buffalo, where he is also currently Designer that Uses Knowledge-Based associate professor in the Department working on his Ph.D. His research Backtracking." of Mathematics and Computer Science interests include image processing, at Millersville University, computer graphics, and computer segmentation Jay M. Tenenbaum, who coauthored Millersville, Pennsylvania 1755 1. Palumbo is a the tribute to Kvetoslav Prazdny, is a coauthor of "Recognizing Address Schlumberger Fellow at the Schlumberger John McDermott is a principal scientist Blocks on Mail Pieces."

An important task in postal automation technology is determining the position and orientation of the destination address block in the image of a mail piece such as a letter, magazine, or parcel. The corresponding subimage is then presented to a human operator or a machine reader (optical character reader) that can read the zip code and, if necessary, other address information and direct the mail piece to the appropriate sorting bin. Analysis of physical characteristics of mail pieces indicates that in order to automate the address finding task, several different image analysis operations are necessary. Some examples are locating a rectangular white address label on a multicolor background, progressively grouping characters into text lines and text lines into text blocks, eliminating candidate regions by specialized detectors (for example, detecting regions such as postage stamps), and identifying handwritten regions. Described here are several operations, their utility as predicted by statistics of mail piece characteristics, and the results of applying the operations to a task set of mail piece images. A problem-solving architecture based on the blackboard model of problem solving for appropriately invoking the tools and combining their results is described.