Papers Published
Abstract:
This paper describes the design of a labeled object classification system to be used for product classification at the final inspection stage of an IBM personal computer manufacturing line. The classification problem is broken down into pattern extraction, feature extraction, and feature classification levels. Pattern extraction and normalization are performed by image processing. Normalized images of the labels so obtained are compressed using an autoassociative network. Features extracted in this manner are used as inputs to a second learning vector quantization (LVQ) network trained to classify the labels. The system so designed is shown to satisfy the primary requirements of a typical industrial classification system
Keywords:
automatic optical inspection;DP industry;feature extraction;image classification;neural nets;object recognition;vector quantisation;
The mission of Duke's Mechanical Engineering and Materials Science educational programs is to provide the knowledge, skills, and credentials needed to be successful in the practice of engineering; the preparation necessary to undertake professional registration; an educational preparation for graduate or professional study; and an education background that is the basis for professional growth and leadership throughout a career that may encompass a broad range of endeavors, both technical and non-technical.