Abstract
Recently, several researches were carried on handwritten document analysis field thanks to the evolution of data capture technologies. For a given document, multiple components could be treated as text, signatures and graphics. In this study, we present a new framework for a Multilanguage online handwritten text analysis where both script identification and recognition are made. The proposed system proceeds by segmenting the script into continuous trajectories delimited between two successive pen-down and pen-up moments. These segments are clustered and trained using Time Delay Neural Network (TDNN) according to their beta-elliptic parameters. In script identification process, the segments belonging to the same script are gathered and brought to a Recurrent Neural Network with Long Short Term Memory (RNN-LSTM) in order to identify its language. For script recognition stage, the samples from the already selected language database are trained and tested using the fuzzy output description obtained by the TDNN coupled to a Support Vector Machines (SVM). The Experiments were made on a large multi-language database containing 45686 online handwriting words from Latin, Arabic and digit scripts and shows very promising results that exceed the recognition rate of 99%.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.