Image classification independent of orientation and scale

Henri H. Arsenault; Sebastien Parent; Sylvain Moisan

doi:10.1117/12.304959

1 April 1998 Image classification independent of orientation and scale

Henri H. Arsenault, Sebastien Parent, Sylvain Moisan

Proceedings Volume 3402, Optical Information Science and Technology (OIST97): Optical Memory and Neural Networks; (1998) https://doi.org/10.1117/12.304959
Event: Optical Information Science and Technology, 1997, Moscow, Russian Federation

Abstract

The recognition of targets independently of orientation has become fairly well developed in recent years for in-plane rotation. The out-of-plane rotation problem is much less advanced. When both out-of-plane rotations and changes of scale are present, the problem becomes very difficult. In this paper we describe our research on the combined out-of- plane rotation problem and the scale invariance problem. The rotations were limited to rotations about an axis perpendicular to the line of sight. The objects to be classified were three kinds of military vehicles. The inputs used were infrared imagery and photographs. We used a variation of a method proposed by Neiberg and Casasent, where a neural network is trained with a subset of the database and a minimum distances from lines in feature space are used for classification instead of nearest neighbors. Each line in the feature space corresponds to one class of objects, and points on one line correspond to different orientations of the same target. We found that the training samples needed to be closer for some orientations than for others, and that the most difficult orientations are where the target is head-on to the observer. By means of some additional training of the neural network, we were able to achieve 100% correct classification for 360 degree rotation and a range of scales over a factor of five.

Citation Download Citation

Henri H. Arsenault, Sebastien Parent, and Sylvain Moisan "Image classification independent of orientation and scale", Proc. SPIE 3402, Optical Information Science and Technology (OIST97): Optical Memory and Neural Networks, (1 April 1998); https://doi.org/10.1117/12.304959

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Neural networks

Linear filtering

Image processing

Target recognition

Databases

Image classification

Infrared imaging

Show All Keywords

Keywords/Phrases

Search In:

Publication Years