Fast and robust recognition of orbit and sinus drawings using histograms of forces

Authors:
Laurent Wendling;Salvatore Tabbone;Pascal Matsakis
Affiliations:
LORIA-UMR 7503, Campus Scientifique, BP 239, 54506 Vandoeuvre-les-Nancy Cedex, France;LORIA-UMR 7503, Campus Scientifique, BP 239, 54506 Vandoeuvre-les-Nancy Cedex, France;CECS Department, University of Missouri-Columbia, Columbia, MO
Venue:
Pattern Recognition Letters
Year:
2002

Citing 7
Cited 3

Polygonal shape recognition using string-matching techniques

Pattern Recognition
Fast computation of moment invariants

Pattern Recognition
Pattern recognition with moment invariants: a comparative study and new results

Pattern Recognition
Spatial organization in 2D segmented images: representation and recognition of primitive spatial relations

Fuzzy Sets and Systems - Special issue on fuzzy methods for computer vision and pattern recognition
A complete invariant description for gray-level images by the harmonic analysis approach

Pattern Recognition Letters
Fast and robust recognition and localization of 2-D objects

Machine Vision and Applications
A New Way to Represent the Relative Position between Areal Objects

IEEE Transactions on Pattern Analysis and Machine Intelligence

Understanding the spatial organization of image regions by means of force histograms: a guided tour

Applying soft computing in defining spatial relations
An equivalent definition of the histogram of forces: Theoretical and algorithmic implications

Pattern Recognition
Modeling multi-object spatial relationships for satellite image database indexing and retrieval

CIVR'05 Proceedings of the 4th international conference on Image and Video Retrieval

Quantified Score

Hi-index	0.10

Visualization

Abstract

The notion of the histogram of forces was introduced in a previous work with the aim of modeling spatial relations between image objects. In this paper, we show that it can also be useful in pattern recognition. Drawings of cranial orbits and sinuses are classified using force histograms. The results are consistent with human responses, and our method compares favorably with classical methods based on geometric criteria and Fourier descriptors.