Conference Paper

Shape Matching Using a Novel Warping Distance Measure.

DOI: 10.1007/978-3-540-69812-8_46 Conference: Image Analysis and Recognition, 5th International Conference, ICIAR 2008, Póvoa de Varzim, Portugal, June 25-27, 2008. Proceedings
Source: DBLP

ABSTRACT This paper presents a novel distance measure, the Minimum Landscape Distance (MLD). MLD is a warping distance measure that
provides a non-linear mapping between the elements in one sequence to those of another. Each element in one sequence is mapped
to that with the highest neighborhood structural similarity (landscape) in the other sequence within a window. Different window
sizes are tested on a number of datasets and a linear relationship between the window size and the sequence size is discovered.
Experimental results obtained on the Kimia-99 and Kimia-216 datasets show that MLD is superior to the Euclidean, correlation,
and Dynamic Time Warping (DTW) distance measures.

0 Followers
 · 
64 Views
  • Source
    01/1977; Addison-Wesley.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper reports on an optimum dynamic progxamming (DP) based time-normalization algorithm for spoken word recognition. First, a general principle of time-normalization is given using time-warping function. Then, two time-normalized distance definitions, called symmetric and asymmetric forms, are derived from the principle. These two forms are compared with each other through theoretical discussions and experimental studies. The symmetric form algorithm superiority is established. A new technique, called slope constraint, is successfully introduced, in which the warping function slope is restricted so as to improve discrimination between words in different categories. The effective slope constraint characteristic is qualitatively analyzed, and the optimum slope constraint condition is determined through experiments. The optimized algorithm is then extensively subjected to experimental comparison with various DP-algorithms, previously applied to spoken word recognition by different research groups. The experiment shows that the present algorithm gives no more than about two-thirds errors, even compared to the best conventional algorithm.
    IEEE Transactions on Acoustics Speech and Signal Processing 03/1978; 26(1-26):43 - 49. DOI:10.1109/TASSP.1978.1163055
  • [Show abstract] [Hide abstract]
    ABSTRACT: Not Available
    IEEE Transactions on Automatic Control 09/1974; 19(4):462- 463. DOI:10.1109/TAC.1974.1100577 · 3.17 Impact Factor