F.  Nayyeri, M.F.  Nasrudin, 
    Sketching Method Based on Earth Mover’s Distance for Image Contour Matching,
    International Journal of Soft Computing,
    Volume 12,Issue 1,
    2017,
    Pages 79-85,
    ISSN 1816-9503,
    ijscomp.2017.79.85,
    (https://makhillpublications.co/view-article.php?doi=ijscomp.2017.79.85)
    Abstract: Finding similar images to a given query image can be computed by different distance measures. One of general distance measures is the Earth Mover&#146;s Distance (EMD). Although, EMD has proven its ability to retrieve similar images in &gt;95% true, high execution time is its major drawback. Therefore, previous algorithms of EMD could not run efficiently when performing retrievals from large databases. A contour-matching algorithm has been presented that quickly estimate the minimum weight matching using an embedding of the EMD into L<sub>1</sub>. This low-distortion algorithm somehow solves the time problem by sacrificing the performance 1 due to generating heavily tailed image feature vector.
    Keywords: dimension reduction;sketching;EMD;Earth Mover`s Distance;statistics;feature vector