Handwriting perceptual classification and synthesis using discriminate HMMs and progressive iterative approximation
- PDF / 1,111,391 Bytes
- 22 Pages / 595.276 x 790.866 pts Page_size
- 110 Downloads / 198 Views
IAPR-MEDPRAI
Handwriting perceptual classification and synthesis using discriminate HMMs and progressive iterative approximation Hala Bezine1
· Adel M. Alimi1
Received: 21 October 2018 / Accepted: 11 April 2019 © Springer-Verlag London Ltd., part of Springer Nature 2019
Abstract This paper handles the problem of online handwriting synthesis. Indeed, this work presents a probabilistic model using the embedded hidden Markov models (HMMs) for the classification and modeling of perceptual sequences. At first, we start with a vector of perceptual points as input seeking a class of basic shape probability as output. In fact, these perceptual points are necessary for the drawing and the recovering of each basic shape where each one is designed with an HMM built and trained with its components. Each path through these possibilities of control points represents an observation that serves as input for the following step. Secondly, the already detected sequences of observations which represent a segment formed an initial HMM and the concatenation of multiple ones leads to a global HMM. To classify a global HMM, we should codify it by searching the best path of initial HMM. The best path is obtained by computing the maximum of likelihood of the different basic shapes. In order to synthesize the handwritten trace, and to recover the best control points sequences, we investigated the progressive iterative approximation. The performance of the proposed model was assessed using samples of scripts extracted from IRONOFF and MAYASTROON databases. In fact, these samples served for the generation of the set of control points used for the HMMs training models. In experiments, good quantitative agreement and approximation were found for the generated trajectories and a more reduced representation of the scripts models was designed. Keywords Cursive handwriting synthesis · Embedded hidden Markov models · Visual perceptual codes · Control points · Progressive iterative interpolation
1 Introduction Handling online handwriting, whether for classification or synthesis, has been of great interest in recent years owing to several factors such as the simplicity of writing compared to typing, which is not possible in some environments and difficult in some languages with many alphabetic characters, in addition to the absence of complete keyboards in small computers. Many scientific researchers proved that the generation of handwriting & Hala Bezine [email protected] Adel M. Alimi [email protected] 1
REGIM-Lab: Research Group on Intelligent Machines Laboratory, National School of Engineers, University of Sfax, BP 1173, 3038 Sfax, Tunisia
movements is a task which requires the activation of neuromuscular systems and that learning renders this task an automatic process which does not require any control feedback [49, 50, 53]. Thus, the act of writing can be studied according to three levels: the motor level, the perceptual level and the representation level in which handwriting can be defined as an organized movement that performs expre
Data Loading...
