Abstract :
The state of the art in handwriting recognition, especially in cursive word recognition, is surveyed, and some basic notions are reviewed in the field of picture recognition, particularly, line image recognition. The usefulness of `regular´ versus `singular´ classes of features is stressed. These notions are applied to obtain a graph, G , representing a line image, and also to find an `axis´ as the regular part of G. The complements to G of the axis are the `tarsi´, singular parts of G, which correspond to informative features of a cursive word. A segmentation of the graph is obtained, giving a symbolic description chain (SDC). Using one or more as robust anchors, possible words in a list of words are selected. Candidate words are examined to see if the other letters fit the rest of the SDC. Good results are obtained for clean images of words written by several persons
Keywords :
graph theory; optical character recognition; cursive word recognition; graph; handwriting recognition; line image recognition; picture recognition; segmentation; symbolic description chain; Background noise; Character recognition; Graphics; Handwriting recognition; Image recognition; Image segmentation; Pattern recognition; Pixel; Robustness; Speech recognition;
