No abstract

A neural network model for handwritten script generation is proposed, in which curvilinear velocity signals are approximated by the Beta profiles. For each Beta profile we associate an elliptic arc to fit the initial stroke in the trajectory domain. The network architecture consists of an input layer which uploads the set of Beta-elliptic characteristics as input, hidden layers and the output layer where script coordinates X(t) and Y(t) are estimated. A separate timing network prepares the input data. This latter involves the time-index starting time of each simple stroke for an appropriate handwriting movement signal. The experiments showed that the neural network model could be applied for the case of Latin handwriting scripts as well as Arabic handwriting scripts. New ways are proposed for the application of the neural network model such as: generation of complex handwriting movements, shape and character recognition.

In this work a new technique for global perceptual codes (GPCs) extraction using genetic algorithms (GA) is presented. GAs are employed to extract the GPCs in order to reduce the original number of features and to provide meaningful representations of the original data. In this technique the GPCs are build from a certain combination of elementary perceptual codes (EPCs) which are provided by the Beta-elliptic model for the generation of complex handwriting movements. Indeed, in this model each script is modelled by a set of elliptic arcs. We associate to each arc an EPC. In the proposed technique we defined four types of EPCs. The GPCs can be formed by many possible combinations of EPCs depending on their number and types. So that, the problem of choosing the right combination for each GPC can be regarded as a global optimization problem which is treated in this work using the GAs. Several simulation examples are presented to evaluate the interest and the efficiency of the proposed technique

No abstract

No abstract