An intelligent artificial vision system is developed which employs biologically inspired techniques for image processing and an artificial neural network for object recognition. Particular emphasis is placed on the identification and classification of objects and visual features in manufacturing environments.
Past and current research into the physiological structure and function of the mammalian vision system are review, and the relationships between this research and neural-network based models of visual processing are developed. The psychological research on the subject of human visual cognition is also reviewed, with the goal of shedding some light on the processes that humans use to identify and classify features and objects. Several vision system models are reviewed, with the emphasis on recently developed models based on artificial neural networks.
A new neural network based vision model is developed based on this research, and this model is implemented as part of an artificial vision system. The system is designed to be robust, practical, and fast. The performance of the system is evaluated on a variety of objects. The ability of neural networks to learn is exploited, with the emphasis being placed on learning from examples and experience rather than on programming based in a priori knowledge or object models. The system is shown to be capable of learning and later recognizing two-dimensional and three-dimensional objects under varying conditions. Potential applications for this system include the sorting of three-dimensional manufactured objects and the identification and classification of surface defects in manufactured materials.
Return to Dissertations.
Last update: January 18, 1996.