Off-campus UMass Amherst users: To download dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.
Non-UMass Amherst users, please click the view more button below to purchase a copy of this dissertation from Proquest.
(Some titles may also be available free of charge in our Open Access Dissertation Collection, so please check there first.)
CAD-based automatic object recognition and determination of symmetric properties of objects
Abstract
Integrating Computer-Aided Design(CAD) and Computer-Aided Manufacturing(CAM) systems has been one of the major aims of research in automation for many years. However, a fully automated system has not been developed yet. Previous research indicate that an automated process planning system which possesses the capacity to reason about geometric properties of objects is an invaluable tool for overcoming many of the obstacles in integrating current CAD/CAM systems. During the past few years, people have proposed alternative methodologies for overcoming these obstacles. These alternative methodologies such as geometric coding systems or feature-based design systems have been widely utilized both in industry and academia. However, these methodologies merely offer an interface process and a storage mechanism. Human beings still perform the essential activity of geometric interpretation. In this research, a robust object recognition process is presented. Preparation of geometric data has been studied. Subsequently, a unique boundary representation scheme is developed to facilitate the recognition process. By using graph theory and search techniques from Artificial Intelligence, the recognition process can realize that two objects are identical or similar. Applications of the recognition process are also introduced. The recognition process can be employed to determine whether two features can be assembled. It can also be included in a geometric coding system to perform the task of searching for geometric data. Symmetry, an important geometric property of objects, can be determined automatically using the recognition process. In conclusion, methods of utilizing and expanding the object recognition algorithm are discussed.
Subject Area
Industrial engineering
Recommended Citation
Yeh, Shuchieh, "CAD-based automatic object recognition and determination of symmetric properties of objects" (1992). Doctoral Dissertations Available from Proquest. AAI9305921.
https://scholarworks.umass.edu/dissertations/AAI9305921