Matching Elastic Templates

This paper describes a new efficient algorithm for elastic template matching. The algorithm is based on a coarse to fine matching strategy which iteratively improves the correspondence between images. The high cost of elastic matching is greatly reduced by incorporating efficient techniques for image representation and search. Recognition accuracy of 99% was achieved when using the elastic technique for handprinted character recognition.

[1]  Harvey F. Silverman,et al.  A Class of Algorithms for Fast Digital Image Registration , 1972, IEEE Transactions on Computers.

[2]  David Joseph Burr.  On computer stereo vision with wire frame models. , 1978 .

[3]  Theodosios Pavlidis,et al.  A Hierarchical Syntactic Shape Analyzer , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  T. Poggio,et al.  A computational theory of human stereo vision , 1979, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[5]  D. Burr.  A dynamic model for image registration , 1981 .

[6]  David J. Burr,et al.  Elastic Matching of Line Drawings , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.