Abstract The analysis of a handwritten document within the context of the process which created it is proposed. If handwriting is viewed as a parameterized process, then problems such as signature verification can be posed as the recovery of specific process parameters. To demonstrate this approach, the mechanical aspects of instrument grasp are explored and parameters which have stable and meaningful qualitative effects on the static image are shown. A model is developed for the grasping of a writing instrument which makes explicit the forces exerted in the hand/instrument/paper system while the instrument is in motion. This model is used as a theoretical basis for the analysis of the pressure exerted on the writing surface for strokes of different orientations. The results of experiments which show that the relative pressure information is preserved in static handwriting images are presented. It is suggested how this information is a valuable heuristic in recovering the direction of motion of the instrument which created the stroke and its application to the use of on-line recognition techniques in processing off-line data is discussed.
[1]
Murray Eden,et al.
Handwriting and pattern recognition
,
1962,
IRE Trans. Inf. Theory.
[2]
E. H. Dooijes.
Analysis of handwriting movements
,
1983
.
[3]
Murray Eden,et al.
Experiments on Computer Recognition of Connected Handwritten Words
,
1964,
Inf. Control..
[4]
Maan Ammar,et al.
Progress in Verification of Skillfully Simulated Handwritten Signatures
,
1991,
Int. J. Pattern Recognit. Artif. Intell..
[5]
S. Impedovo,et al.
Optical Character Recognition - a Survey
,
1991,
Int. J. Pattern Recognit. Artif. Intell..
[6]
Réjean Plamondon,et al.
An evaluation of motor models of handwriting
,
1989,
IEEE Trans. Syst. Man Cybern..
[7]
Ching Y. Suen,et al.
The State of the Art in Online Handwriting Recognition
,
1990,
IEEE Trans. Pattern Anal. Mach. Intell..