Use this URL to cite or link to this record in EThOS:
Title: Shape classification in computer-aided design
Author: Kyprianou, L. K.
Awarding Body: University of Cambridge
Current Institution: University of Cambridge
Date of Award: 1980
Availability of Full Text:
Full text unavailable from EThOS. Please contact the current institution's library directly if you wish to view the thesis.
The research reported in this dissertation was undertaken to investigate methods for automating the classification of shapes generated using the techniques of computer-aided design. A theory of shape classification has been developed by adapting existing work in biological classification. The most important step in classifying shapes is recognising and extracting shape characteristics. A program is described that analyses part descriptions stored in the computer and then recognizes shape features such as holes, bosses, slots and pockets as well as other shape relationships. The original part description is transformed into a feature data structure which is amenable to interrogation by a specially devised input language. The language can be used to set up programs that utilize feature information to produce classification codes. Classification schemes in use in industry can be automated this way. The feature recognition program can be used to link design and manufacturing data bases and thus to assist in the general organization of other aspects of manufacturing technology such as planning for production and metal cutting by numerically-controlled machine tools. Finally, a survey of current classification schemes has been carried out. The reasons for using classification and how such schemes have developed in industry are explained.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID:  DOI: Not available
Keywords: Pattern recognition & image processing