On-line handwritten segmentation in linear drawings
de Brucq, D., Amara, M. and Ruiz, V. F. (1997) On-line handwritten segmentation in linear drawings. Pattern Recognition Letters, 18 (2). pp. 193-202. ISSN 0167-8655
Full text not archived in this repository.
To link to this item DOI: 10.1016/S0167-8655(96)00126-2
This paper addresses the problem of tracking line segments corresponding to on-line handwritten obtained through a digitizer tablet. The approach is based on Kalman filtering to model linear portions of on-line handwritten, particularly, handwritten numerals, and to detect abrupt changes in handwritten direction underlying a model change. This approach uses a Kalman filter framework constrained by a normalized line equation, where quadratic terms are linearized through a first-order Taylor expansion. The modeling is then carried out under the assumption that the state is deterministic and time-invariant, while the detection relies on double thresholding mechanism which tests for a violation of this assumption. The first threshold is based on an approach of layout kinetics. The second one takes into account the jump in angle between the past observed direction of layout and its current direction. The method proposed enables real-time processing. To illustrate the methodology proposed, some results obtained from handwritten numerals are presented.