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.

Over the past decade, technological innovation has advanced at an increasingly fast pace, creating both opportunities and disruptions in virtually every industry. The postal industry is no exception. According to the report, "Step into Tomorrow: The U.S. Postal Service (USPS) and Emerging Technology," the Postal Service collects massive quantities of data on an ongoing basis. A challenge is putting this data to its most valued use to improve the customer experience. Data-driven advanced algorithms and analytics can play a critical role in the design of these new, last-mile solutions.

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 addressfinding 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 (fol example, detecting regions such as postage stamps), and identifying handwritten regions. A typical mail piece has several regions or blocks that are meaningful to mail processing, for example, address blocks (destination and return), postage [meter mark or stamp) as well as extraneous blocks WINTER 1987 25 Figure 1. The heuristics listed in the previous section suggest that the design of ABLS consist of several specialized tools that are appropriately deployed. Rule R2 suggests the need for a tool to detect postage fluorescence, rule R3 a tool for isolating blocks of a certain color, rule R4 for discriminating between handwriting and print, and so on.

Commercial AI Trends Seen at AAAI-87 8(4): (Winter 19871, 93-95. CSCW '86 Conference Summary Report, 8(3): (Fall 1987), 87-88 Darden, Lindley, Viewing the History of Science as Compiled Hindsight g(2). Schank, Roger C., What Is AI, Anyway! 8(4): (Winter 1987), 59-65. Stone, Jeffrey, Commercial AI Trends Seen at AAAI-87. Sridharan, N. S., 1986 Workshop on Distributed AI. 8(3): (Fall 19871, 75-85.

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.

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.