Elsevier

Image and Vision Computing

Volume 5, Issue 4, November 1987, Pages 287-295
Image and Vision Computing

Measures of correspondence between binary patterns

https://doi.org/10.1016/0262-8856(87)90005-9Get rights and content

Abstract

Some measures for the quantitative description of correspondence relations between binary patterns are proposed and analysed. Some of these are based upon measures of area for finite grid point sets, and others on distance mappings indicating the minimum distance of a grid point from a given grid point set. For the second type of measure, two algorithms for computing the degree of correspondence are described. Some examples of their application to real binary images, and the processing time required, are given.

References (11)

  • A Rosenfeld et al.

    Degree of adjacency or surroundedness

    Pattern Recogn.

    (1985)
  • PE Danielsson

    Euclidean distance mapping

    Comput. Graph. Image Process

    (1980)
  • M Nagayo et al.

    Automatic figure decomposition into elementary features by similarity principle

  • SK Parui et al.

    How to quantify shape distance for 2-dimensional regions

  • A Rosenfeld et al.

    Digital picture processing, I and II

    (1982)
There are more references available in the full text version of this article.

Cited by (17)

  • Binary-image comparison with local-dissimilarity quantification

    2008, Pattern Recognition
    Citation Excerpt :

    Therefore, binary image comparison can be considered as a comparison between a set of foreground points. In Ref. [15], several measures of correspondence between binary images are described and compared. This study shows that distance-based measures perform better comparisons of binary images than measures based on set memberships.

  • Distance-based functions for image comparison

    1999, Pattern Recognition Letters
View all citing articles on Scopus
View full text