Share Email Print

Proceedings Paper

Retrieving images by 2D shape: a comparison of computation methods with human perceptual judgments
Author(s): Brian M. Scassellati; Sophoclis Alexopoulos; Myron D. Flickner
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In content based image retrieval, systems allow users to ask for objects similar in shape to a query object. However, there is no clear understanding of how computational shape similarity corresponds to human shape similarity. In this paper several shape similarity measures were evaluated on planar, connected, non-occluded binary shapes. Shape similarity using algebraic moments, spline curve distances, cumulative turning angle, signal of curvature and Hausdorff- distance were compared to human similarity judgments on twenty test shapes against a large image database.

Paper Details

Date Published: 1 April 1994
PDF: 13 pages
Proc. SPIE 2185, Storage and Retrieval for Image and Video Databases II, (1 April 1994); doi: 10.1117/12.171777
Show Author Affiliations
Brian M. Scassellati, Massachusetts Institute of Technology (United States)
Sophoclis Alexopoulos, Univ. of California/San Diego (United States)
Myron D. Flickner, IBM Almaden Research Ctr. (United States)

Published in SPIE Proceedings Vol. 2185:
Storage and Retrieval for Image and Video Databases II
Carlton Wayne Niblack; Ramesh C. Jain, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?