A blackboard-based approach to handwritten ZIP code recognition

A methodology for recognizing ZIP codes @ostal codes) in handwritten addresses is presented. The method uses many diverse pattern recognition and image processing algorithms. Given a high-resolution image of a hand-written address block, the solution invokes routines capable of hypothesizing the location of the ZIP Code, segmenting and recognizing ZIP Code digits, locating and recognizing City and State names, and looking-up the results in a dictionaq. The control structure is not strictly sequential, but in the form of a black-board architecture that opportunistically invokes routines as needed. An implementation of the methodology is described as well as results with a data-base of grey level images of handwritten addresses (taken from live mail in a US. Postal Service mail processing facility). Future extensions of the approach are also discussed.