Combined approach for large-scale pattern recognition with translational, rotational, and scaling invariances

Qing Xu; Rafael M. Inigo; Eugene S. McVey

doi:10.1117/12.44895

1 August 1991 Combined approach for large-scale pattern recognition with translational, rotational, and scaling invariances

Qing Xu, Rafael M. Inigo, Eugene S. McVey

Author Affiliations +

Proceedings Volume 1471, Automatic Object Recognition; (1991) https://doi.org/10.1117/12.44895
Event: Orlando '91, 1991, Orlando, FL, United States

Abstract

Translational, rotational, and scaling invariant (TRSI) pattern recognition is a third-order problem encountered frequently in real-world applications. But neither traditional image processing/pattern recognition algorithms nor artificial neural networks have yet provided satisfactory solutions for this problem after years of study. Recent research has shown that a higher-order neural network (HONN), of order three with built-in invariances, can effectively achieve TRSI pattern recognition. For an N X N image, the memory needed to store the connections is proportional to N⁶. This huge memory requirement limits the HONNs application to large-scale images. To solve this problem the authors first adapt edge detection and log-spiral mapping algorithms to preprocess the image so that the problem is converted into a second-order one. This reduces the HONN memory requirement to O(N⁴). Second, the authors modified the second-order HONN architecture to further reduce the memory size to O(N²). Synthetic and real images with resolution 256 X 256 have been used for simulation. The training samples are noise free, and the testing samples are rotated, translated, scaled, or noise-corrupted versions of the training patterns. Simulation results show that this system can indeed achieve TRSI pattern classification. In addition, its high robustness to noise and pattern deformation makes it very useful for real-world applications.

Citation Download Citation

Qing Xu, Rafael M. Inigo, and Eugene S. McVey "Combined approach for large-scale pattern recognition with translational, rotational, and scaling invariances", Proc. SPIE 1471, Automatic Object Recognition, (1 August 1991); https://doi.org/10.1117/12.44895

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