The segmentation of cursive handwriting: an approach based on off-line recovery of the motor-temporal information

• Published in: IEEE transactions on image processing 1999-01, Vol.8 (1), p.80-91
• Main Authors: Plamondon, R., Privitera, C.M.
• Format: Article
• Language: English
• Subjects: Algorithms; Angular velocity; Applied sciences; Computer science; Curvature; Exact sciences and technology; Graphics; Humans; Image processing; Image segmentation; Information, signal and communications theory; Iris; Mathematical analysis; Movement; Nervous system; Process planning; Segmentation; Shape; Signal processing; Telecommunications and information theory; Temporal logic
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/83.736691

This paper presents a segmentation method that partly mimics the cognitive-behavioral process used by human subjects to recover motor-temporal information from the image of a handwritten word. The approach does not exploit any thinning or skeletonization procedure, but rather a different type of information is manipulated concerning the curvature function of the word contour. In this way, it is possible to detect the parts of the image where the original odometric information is lost or ambiguous (such as, for example, at an intersection of the handwritten lines) and interpret them to finally recover a part of the original temporal information. The algorithm scans the word, following the natural course of the line, and attempts to reproduce the same movement as executed by the writer during the generation of the word. It segments the cursive trace where the contour shows the slow-down of the original movement (corresponding to the maximum curvature points of the curve). At the end of the scanning process, a temporal sequence of motor strokes is obtained which plausibly composed the original intended movement.