Accession Number:

ADA279841

Title:

Object Recognition by Alignment Using Invariant Projections of Planar Surfaces

Descriptive Note:

Corporate Author:

MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s):

• Nagao, Kenji
• Grimson, Eric

Report Date:

1994-12-01

Pagination or Media Count:

20.0

Abstract:

In order to recognize an object in an image, we must determine the best transformation from object model to the image. In this paper, we show that for features from coplanar surfaces which undergo linear transformations in space, there exist projections invariant to the surface motions up to rotations in the image field. To use this property, we propose a new alignment approach to object recognition based on centroid alignment of corresponding feature groups. This method uses only a single pair of 2D model and data. Experimental results show the robustness of the proposed method against perturbations of feature positions. Object recognition, Invariant properties, Recognition by alignment.

Descriptors:

• *SURFACES
• *RECOGNITION
• *IMAGE PROJECTORS
• MODELS
• TWO DIMENSIONAL
• PERTURBATIONS
• APPROACH
• TRANSFORMATIONS
• IMAGES
• MOTION
• ALIGNMENT

Subject Categories:

• Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE