Shape Matching by Elastic Deformation
نویسندگان
چکیده
In this paper we present a new one-dimensional shape matching technique based on elastic deformation of a model or template. Deformations of the given template are introduced as a way to improve the matching with the image data. A trade-o is made between the amount of deformation and a gure of merit that accounts for the match. This approach yields a new optimization functional so that the optimal match for a given shape is expressed as a solution of a variational problem. Numerical methods are presented to solve the resulting system of ordinary di erential equations. This new matching technique can be used for pattern recognition applications where binarizing images s hard or impossible. An illustration of the nre shape matching method is shown for several optical character recognition problems.
منابع مشابه
Real-time simulation of large elasto-plastic deformation with shape matching
Shape matching is a popular method for simulating deformable objects in real time as it is fast and stable at large time steps. Although shape matching can simulate large elastic deformation and ductile fracturing, until now, they are limited to scenarios with relatively small plastic deformation. In this work, we present a method for simulating deformable solids undergoing large plastic deform...
متن کاملElastic Matching Techniques for Handwritten Character Recognition
This chapter reviews various elastic matching techniques for handwritten character recognition. Elastic matching is formulated as an optimization problem of planar matching, or pixel-to-pixel correspondence, between two character images under a certain matching model, such as affine and nonlinear. Use of elastic matching instead of rigid matching improves the robustness of recognition systems a...
متن کاملMarie-Paule Cani’s Visit
Title : An optimization method for elastic shape matching. Applications to forensic facial reconstruction. Abstract : Shape morphing or matching arises in a wide variety of situations in areas from biomedical engineering to computer graphics and scientific computing. Beyond the specific stakes to each particular application, the general issue is to find one transformation from a given ‘template...
متن کاملStereo Matching of Curves
This paper describes a stereo algorithm which matches connected chains of edgels (curves) between images. It is based on representing the curves as elastic strings and measuring the amount of deformation the strings have to undergo to transform between corresponding curves, and incorporates the ideas of the disparity gradient and the fact that matching sections of curve have to be of a similar ...
متن کامل3D Face Recognition Using Geodesic Facial Curves to Handle Expression, Occlusion and Pose Variations
this paper illustrates the use of radial facial curves on 3D meshes to mode facial deformation caused by expression, occlusion and variation in poses and to recognize faces despite large expression, in presence of occlusion and pose variations. Here we represent facial surface by indexed collection of radial geodesic curves on 3D face meshes emanating from nose tip to the boundary of mesh and c...
متن کامل