Repository logo
Log in(current)
Repository logoMIT Open ScholarshipDSpace@MIT
  1. Home
  2. Computer Science and Artificial Intelligence Lab (CSAIL)
  3. Artificial Intelligence Lab Publications
  4. AI Memos (1959 - 2004)
  5. An Extremum Principle for Shape from Contour

An Extremum Principle for Shape from Contour

Thumbnail Image
Download
Name

AIM-711.pdf

Size

3.29 MB

Format

Adobe PDF

Checksum (MD5)

97a6ee3a49eae847bc823557d76669a5

Thumbnail Image
Download
Name

AIM-711.ps

Size

4.21 MB

Format

PostScript

Checksum (MD5)

ebda643e6fdd286b759a8843169e4814

Author(s)
Brady, Michael
•
Yuille, Alan
Date Issued
June 1, 1983
Series/Report no.
AIM-711
Abstract
An extremum principle is developed that determines three-dimensional surface orientation from a two-dimensional contour. The principle maximizes the ratio of the area to the square of the perimeter, a measure of the compactness or symmetry of the three-dimensional surface. The principle interprets regular figures correctly and it interprets skew symmetries as oriented real symmetries. The maximum likelihood method approximates the principle on irregular figures, but we show that it consistently overestimates the slant of an ellipse.
Persistent DSpace Link
http://hdl.handle.net/1721.1/6382
Repository logo
PrivacyPermissionsAccessibilityContact us
Repository logo
Notify us about copyright concerns.