A Kalman approach for stroke order recovering from off-line handwriting

Non-constrained handwriting recognition is still faced with very difficult problems. However, on-line recognition methods exhibit better results than off-line methods which lose all temporal information. The aim of the work is to recover the strokes ordering from static 2-D images as it is inherently available from on-line systems. The approach is innovative because it uses extensively gray-level information, and uses Kalman filtering in the prediction of the writing stroke trajectory