Representing Shape Primitives In Neural Networks

Ted Pawlicki

doi:10.1117/12.976624

22 August 1988 Representing Shape Primitives In Neural Networks

Ted Pawlicki

Proceedings Volume 0938, Digital and Optical Shape Representation and Pattern Recognition; (1988) https://doi.org/10.1117/12.976624
Event: 1988 Technical Symposium on Optics, Electro-Optics, and Sensors, 1988, Orlando, FL, United States

Abstract

Parallel distributed, connectionist, neural networks present powerful computational metaphors for diverse applications ranging from machine perception to artificial intelligence [1-3,6]. Historically, such systems have been appealing for their ability to perform self-organization and learning[7, 8, 11]. However, while simple systems of this type can perform interesting tasks, results from such systems perform little better than existing template matchers in some real world applications [9,10]. The definition of a more complex structure made from simple units can be used to enhance performance of these models [4, 5], but the addition of extra complexity raises representational issues. This paper reports on attempts to code information and features which have classically been useful to shape analysis into a neural network system.

Citation Download Citation

Ted Pawlicki "Representing Shape Primitives In Neural Networks", Proc. SPIE 0938, Digital and Optical Shape Representation and Pattern Recognition, (22 August 1988); https://doi.org/10.1117/12.976624

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