Recovering drawing order of single-stroke handwritten images using probabilistic tabu search

This paper considers the problem for recovering a drawing order of static handwritten images with single stroke. Such a stroke may include the so-called double-traced lines (D-lines). The problem is analyzed and solved by employing the graph theoretic approach. Then the central issue is to obtain the smoothest path of stroke from a graph model of input handwritten images. First, the graph model is constructed from an input images by image processing techniques. Then, we locally analyze the structure of graph. In particular, the method to identify D-lines is developed by introducing the idea of 'D-line index'. The method enables us to transform any graphs with D-lines to semi-Eulerian graphs. Then, the restoration problem reduces to the problem of globally computing the maximum weight collection of perfect matchings. For solving such a problem, we propose a method using a probabilistic tabu search algorithm. The effectiveness and usefulness of the proposed method are examined by some experimental studies.