Generalizing recognition strategies

Bruce A. Draper

doi:10.1117/12.142798

13 April 1993 Generalizing recognition strategies

Bruce A. Draper

Proceedings Volume 1838, 21st AIPR Workshop on Interdisciplinary Computer Vision: An Exploration of Diverse Applications; (1993) https://doi.org/10.1117/12.142798
Event: Applied Imaging Pattern Recognition, 1992, Washington, DC, United States

Abstract

Most knowledge-directed vision systems are tailored to recognize a fixed set of objects within a known context. Generally, the programmer or knowledge engineer who constructs them begins with an intuitive notion of how each object might be recognized, a notion which is refined by trial-and-error. Eventually the programmer finds a combination of features (e.g., color, shape, or context) and methods (e.g., geometric model matching, minimum-distance classification, or generalized Hough transforms) that allow each object to be reliably identified within the domain. Unfortunately, human engineering is not cost-effective for many real-world applications. Moreover, there is no way to ensure the validity of hand-crafted systems: their performance (in terms of accuracy and reliability) is unknown, as is their efficiency in comparison to other strategies. Worst of all, when the domain is changed, the systems often have to be rebuilt from scratch. The schema learning system (SLS) automates the construction of knowledge-directed recognition strategies. Starting with a set of potential actions called `knowledge sources,' SLS builds a strategy capable of recognizing the first training instance. With each successive training image, SLS generalizes the strategy (if necessary) to account for any new examples, while keeping the strategy as efficient as possible. The final result is a strategy capable of recognizing every instance in a training set at a minimal cost.

Citation Download Citation

Bruce A. Draper "Generalizing recognition strategies", Proc. SPIE 1838, 21st AIPR Workshop on Interdisciplinary Computer Vision: An Exploration of Diverse Applications, (13 April 1993); https://doi.org/10.1117/12.142798

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available