Showing papers on "Sketch recognition published in 1974"

On the recognition of complex structures: Computer software using artificial intelligence applied to pattern recognition

Abstract: An approach to simultaneous interpretation of objects in complex structures so as to maximize a combined utility function is presented. Results of the application of a computer software system to assign meaning to regions in a segmented image based on the principles described in this paper and on a special interactive sequential classification learning system, which is referenced, are demonstrated.

Using context in sketch recognition.

Abstract: A central problem in graphical communication between a human and a computer is the ability of the computer to build an internal representation of the human designer's intentions, something which is not possible if the machine does not have some knowledge of the subject matter being sketched. This thesis describes a system for storing such knowledge in the computer, to be used by the machine in building a model of the user's intentions. This semantic knowledge is stored in a network and matched to the input sketch in a top-down manner, using the knowledge to direct the machine's search for entities in the sketch. The operation of a simple program using these principles is presented in detail along with an account of the complexities involved in applying the scheme to complex sketches. Methods of representing relationships to be looked for in a drawing are described and examples are provided of some descriptions which should prove useful in the next implementation. Two implementatons are described, one on a mini-computer and one on a large time sharing system. Included is a discussion of the requirements such a program makes on the programming environment and their implications for the future of inexpensive mini-computer oriented implementations. THESIS SUPERVISOR: Nicholas P. Negroponte TITLE: Associate Professor of Architecture

B74-19 Pattern Recognition Techniques

Abstract: Pattern Recognition Techniques does just what the doctor ordered; it serves as a broad informal introduction for engineers, computer scientists, and biologists to the field of pattern recognition. All necessary background is developed within the text, which is illustrated in terms of character recognition. It would be difficult to find a more extensive bibliography. This greatly contributes to the usefulness of this book.