Fig 1 - uploaded by Antonio Parziale
Content may be subject to copyright.
Source publication
Lognormality has proven to be an effective way for handwriting modeling. It assumes that handwriting is a time superimposition of a sequence of commands issued by the central nervous system, each command producing a stroke, i.e. a movement with a lognormal velocity profile. Motor control theories, however, suggest that handwriting movements result...
Context in source publication
Context 1
... algorithm for extracting the motor plan we have developed, hereinafter MPE, adopts the Sigma-Lognormal Model for describing the shape and the same structure of the parameter extractor algorithm proposed in [11], hereinafter RX0, but incorporates heuristic criteria to detect local generated movements, disregards them and estimates the parameters of the strokes of the motor plan. Figure 1 reports the general structure of the RX0 algorithm that is adopted also by the MPE algorithm, while the MPE implementation of the building blocks is described next. ...
Citations
... In this work we have used the multiresolution algorithm described in [4] , where the desired segmentation points are the points corresponding to the most salient changes in curvature. We have also considered to perform this step by using the algorithm proposed in [21] , which exploits dynamic information, but experiments have shown that it tends to segment multiple executions of the same motor plan into a different number of strokes [22] , and thus does not allow to reliably infer the stability regions as it is described next. ...
... As proposed in [8] , each point of the pen-tip trajectory is represented by eight features: the pen position ( x, y ), the pressure ( p ), the velocity ( ˙ x , ˙ y ) , the pressure derivative ( ˙ p ) , and the acceleration ( ẍ , ÿ ) . To compare features vectors by means of an Euclidean distance, the dynamic range of the features was normalized by a z -score as in Eq. (22) . ...
Building upon findings in computational model of handwriting learning and execution, we introduce the concept of stability to explain the difference between the actual movements performed during multiple execution of the subject’s signature, and conjecture that the most stable parts of the signature should play a paramount role in evaluating the similarity between a questioned signature and the reference ones during signature verification. We then introduce the Stability Modulated Dynamic Time Warping algorithm for incorporating the stability regions, i.e. the most similar parts between two signatures, into the distance measure between a pair of signatures computed by the Dynamic Time Warping for signature verification. Experiments were conducted on two datasets largely adopted for performance evaluation. Experimental results show that the proposed algorithm improves the performance of the baseline system and compares favourably with other top performing signature verification systems.
Background: The analysis of handwriting movements to quantify motor and cognitive impairments in neurodegenerative diseases is increasingly attracting interest. Non-invasive and quick-to-administer tools using handwriting movement analysis can be used in early screening of Parkinson’s disease (PD) and maybe in the diagnosis of other neurodegenerative disease. Theaim of this work is to identify the distinctive signs characterizing handwriting in the early stage of PD, in order to provide a diagnostic tool for the early detection of the disease. Compared to previous studies, here, we analyzed handwriting movements of patients on which the disease affects the contralateral side with respect to the one used for writing. Methods: We collected and analyzed a set of handwriting samples by PD patients and healthy subjects. Participants were asked to follow a novel protocol, containing handwriting patterns of various levels of complexity, using both familiar and unfamiliar movements. Results: We found that the signs characterizing the early stage of PD differ from those appearing in later stages. Our work provides evidence that early detection of PD, even when the disease affects mainly the contralateral side with respect to the one used for writing, could be achieved by analyzing specific features measured during the execution of specific handwriting tasks. Eventually, we found that patients’ performance benefits from the execution of handwriting in specific conditions. Conclusions: The analysis provides the guidelines for the design of a diagnostic tool for the early detection of PD and some suggestions for reducing motor impairments in PD patients.
