Experiments in processing pictorial information with a digital computer

Abstract

In almost all digital data processing machine applications, the input data made available to the machine are the result of some prior processing. This processing is done manually in many applications. Thus, such inputs as punched cards, magnetic tape, and punched paper tape often are the result of a manual processing operation in which a human being is required to inspect visually an array of printed characters and to describe these data in a form capable of being processed by machine. In recognition of the importance of automating such operations, many investigations have been undertaken to devise automatic character sensing equipment. Suppose, however, that we attempt to view such efforts in proper perspective. We find a more fundamental problem that has, heretofore, failed to receive the attention that it warrants. The problem is one of making directly available to a computer pictorial information which would ordinarily be visually processed by human beings before being fed to a data processing system. This pictorial information may range from such highly stylized forms as printed characters, diagrams, schematic drawings, emblems, and designs through less stylized forms in cartoons and handwritten characters to such highly amorphous forms as photographs of real objects, e.g., people, aerial views, and microscopic and telescopic images.