[PDF] The segmentation of cursive handwriting: an approach based on off-line recovery of the motor-temporal information | Semantic Scholar (2024)

A new approach to the temporal order restoration of the off-line handwriting by developing a genetic algorithm GA in order to optimize the best trajectory of segments in three types of strokes.

A system of restoration of temporal order in the offline Arabic handwritten tracing is presented, improved by an algorithm that treats the particular cases concerning the starting point, the ambiguous zone analysis and the progression of the system at the time of the follow-up of the contour.

By recovering a drawing order of a handwritten script, the temporal information can be recovered from a static 2D image and this method will be used as a bridge from the offline handwriting character recognition problem to the online one.

This work addresses the trajectory recovery by combining a general graph traversal algorithm with knowledge about the processes involved in human learning of motor skills to perform voluntary and complex movements, and shows that the approach outperforms the existing ones in terms of Root Mean Square Error and Dynamic Time Warping distance.

Experimental results show that the constructed writing sequence using UWM is close to the actual writing sequence, which is due to the availability of the dynamic information, especially thewriting sequence of the strokes.

An approach to processing static handwriting’s objects, including edges, vertices and loops, as the important aspects of any handwritten image is provided and a detailed tracing algorithm on global stroke reconstruction is presented.

A new approach for recovering the time order of the off-line writing signal, based on a graph description of the handwriting signal and a recognition process using Hidden Markov Models (HMM), and a complete omni-scriptor isolated word recognition system has been developed.

A 3-phase approach to restore a writing order is proposed within the framework of the edge continuity relation (ECR) and finds all the candidates of single-stroked paths by depth first search and selects the best one by evaluating SLALOM smoothness.

A novel approach is proposed to solve the recovery problem within the framework of the edge contiguous relation (ECR) by making local analyses to obtain the possible ECRs at each of the nodes and executing a global trace to find all of the candidate Euler paths.

...

...

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, which plausibly composes the original intended movement.

A model-based segmentation framework for the partitioning of handwriting in terms of response patterns that result from the activation by the central nervous system of curvilinear and angular velocity generators, characterized by log-normal impulse responses.

A handwriting generation model that takes advantage of the asymptotic impulse response of neuromuscular networks to produce and control complex two-dimensional synergistic movements and shows how basic handwriting characteristics are affected and controlled using an action plan made up of virtual targets fed into a neuromoscular synergy that is governed by a delta-lognormal law.

It is demonstrated how many seemingly ambiguous situations can be resolved by the derived clues and the knowledge of the writing process, and several examples to illustrate the approach.

This study tackles the problem of extracting handwritten information by means of an intuitive approach that is close to human visual perception, defining a topological criterion specific to handwritten lines which is called filiformity.

The findings suggest that perceivers are able to extract information relating to production from the static trace of the handwritten letter and can use this information in conjunction with their knowledge of a common production process, shared by both producers and perceivers, to aid character recognition.

Results show that velocity-controlled models produce the best outputs, with no significant difference between second- and third-order systems, and are of interest for a number of applications, from pattern recognition to handwriting education.

...

...