Abstract
A novel method based on shape morphing is proposed for 2D shape recognition. In this framework, the shape of objects is described by using their contour. Shape recognition involves a morph between the contours of the objects being compared. The morph is quantified by using a physics-based formulation. This quantification is used as a dissimilarity measure to find the reference shape most similar to the input. The dissimilarity measure is shown to have the properties of a metric as well as invariance to Euclidean transformations. The recognition paradigm is applicable to both convex and non-convex shapes. Moreover, the applicability of the method is not constrained to closed shapes. Based on the metric properties of the dissimilarity method, a search strategy is described that obviates an exhaustive search of the template database during recognition experiments. Experimental results on the recognition of various types of shapes are presented.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 1683-1699 |
| Number of pages | 17 |
| Journal | Pattern Recognition |
| Volume | 33 |
| Issue number | 10 |
| DOIs | |
| State | Published - 2000 |
Bibliographical note
Funding Information:Ioannis Pavlidis had participated in the initial phase of this research. The proof of the metric properties has benefited from numerous discussions with Soumyendu Raha. The critique of Richard Voyles was instrumental in developing the segmentation algorithm used for rigid shapes. The presentation of this paper has also improved due to the comments provided by the anonymous reviewer. The authors wish to express their gratitude to each of the aforementioned. The research of Rahul Singh on this project was supported by the National Science Foundation through grants #IRI-9410003 and #IRI-9502245.