On using dynamic programming for time warping in pattern recognition

Abstract

Abstract Dynamic programming is a mathematical optimization algorithm relied upon by time warping procedures. In general, its use is straightforward and early time warping publications are indeed correct and efficient. However, in sophisticated use of this technique considerable art is required. We discuss here some published sophisticated time warping procedures which are incorrect or inefficient. Since small example problems are sufficient to show incorrectness or inefficiency we restrict our attention to such. While doing so, we try to educate the reader toward the artful use of dynamic programming.