Class-prototype extraction from a finite number of input patterns as a generalization of their distortion-level ordering

Ranko Babic

doi:10.1117/12.152631

19 August 1993 Class-prototype extraction from a finite number of input patterns as a generalization of their distortion-level ordering

Ranko Babic

Author Affiliations +

Proceedings Volume 1966, Science of Artificial Neural Networks II; (1993) https://doi.org/10.1117/12.152631
Event: Optical Engineering and Photonics in Aerospace Sensing, 1993, Orlando, FL, United States

Abstract

Based on mathematical interpretation of fundamental principles related to human visual perception in the case of contour as a general geometrical figure, it is proposed a procedure for class-prototype reconstruction from a limited number of contour-samples belonging to the class. The procedure itself comprises the ordering of given contour-samples into a sequence according to the criterion and value of their mutual distortion, defining adequate mathematical characteristic of distortion trend within the sequence and subsequent reconstruction of approximate class-prototype shape, that is refined afterward by taking into account the assumed property of prototype symmetry. Finally, a global structure of artificial neural system is presented, that could be capable to fulfill the described procedure.

Citation Download Citation

Ranko Babic "Class-prototype extraction from a finite number of input patterns as a generalization of their distortion-level ordering", Proc. SPIE 1966, Science of Artificial Neural Networks II, (19 August 1993); https://doi.org/10.1117/12.152631

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