Qualitative descriptors for digital contour segments (Invited Paper)

Kathryn Shaker Baummer; Kie Bum Eom; Murray H. Loew

doi:10.1117/12.135155

1 February 1992 Qualitative descriptors for digital contour segments (Invited Paper)

Kathryn Shaker Baummer, Kie Bum Eom, Murray H. Loew

Proceedings Volume 1610, Curves and Surfaces in Computer Vision and Graphics II; (1992) https://doi.org/10.1117/12.135155
Event: Robotics '91, 1991, Boston, MA, United States

Abstract

Earlier studies of the human vision system suggest that a complex object may be recognized from the qualitative features associated with its boundary. Since the human vision system uses qualitative features for object recognition, it is extremely robust to deformation caused by noise, obstruction, scale change, or optical distortion. We considered various qualitative descriptors for digital images. The descriptors developed in this research are based on the estimated curvature function from digital boundaries and can discriminate features such as straightness of a contour segment, perpendicularity of two contour segments, parallelness of two straight contour segments, parallelness of two curved contour segments in a global sense, and the direction of convergence if two straight contour segments are not parallel. We demonstrated that the qualitative descriptors developed in this paper can be applied for identification of elementary shapes, such as cylinders, bricks, cones, etc. We also discussed the recognition of more complex shapes after decomposing them into simpler components.

Citation Download Citation

Kathryn Shaker Baummer, Kie Bum Eom, and Murray H. Loew "Qualitative descriptors for digital contour segments (Invited Paper)", Proc. SPIE 1610, Curves and Surfaces in Computer Vision and Graphics II, (1 February 1992); https://doi.org/10.1117/12.135155

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