TY - GEN
T1 - Reducing language barriers for tourists using handwriting recognition enabled mobile application
AU - Chammas, Edgard
AU - Mokbel, Chafic
AU - Al Hajj Mohamad, Rami
AU - Oprean, Christina
AU - Sulem, Laurence Likforman
AU - Chollet, Gérard
PY - 2012/12/1
Y1 - 2012/12/1
N2 - Modern mobile devices and networks permit to develop applications that reduce the language barrier for tourists and visitors in foreign countries. This paper describes a mobile application built on a distributed architecture that allows tourists to obtain additional information about location names and menu entries in Arabic language. By simply taking a photo, translation and additional information are displayed to users in their preferred language. While several mobile applications exist to translate the texts into photos, the present application offers the advantage of translating both handwritten and printed texts. The work was focused on two important aspects: the recognition system and the mobile application. The major challenge was to build a recognition system able to recognize handwritten or printed texts of various writing styles or fonts. Therefore, we propose an original approach consisting of recognizing handwritten and printed words using the Balamand-ENST handwriting recognition system, trained on handwritten texts. Experiments conducted on a collected database have shown that the recognition system trained on handwritten text provides excellent performance when used in recognizing printed text. This recognition system and its performance in both modalities are briefly described in this paper. In addition, a full description on how the mobile application was designed and its functionality is presented.
AB - Modern mobile devices and networks permit to develop applications that reduce the language barrier for tourists and visitors in foreign countries. This paper describes a mobile application built on a distributed architecture that allows tourists to obtain additional information about location names and menu entries in Arabic language. By simply taking a photo, translation and additional information are displayed to users in their preferred language. While several mobile applications exist to translate the texts into photos, the present application offers the advantage of translating both handwritten and printed texts. The work was focused on two important aspects: the recognition system and the mobile application. The major challenge was to build a recognition system able to recognize handwritten or printed texts of various writing styles or fonts. Therefore, we propose an original approach consisting of recognizing handwritten and printed words using the Balamand-ENST handwriting recognition system, trained on handwritten texts. Experiments conducted on a collected database have shown that the recognition system trained on handwritten text provides excellent performance when used in recognizing printed text. This recognition system and its performance in both modalities are briefly described in this paper. In addition, a full description on how the mobile application was designed and its functionality is presented.
KW - Handwriting Recognition
KW - Mobile Application
KW - Optical Characters Recognition
U2 - 10.1109/ICTEA.2012.6462868
DO - 10.1109/ICTEA.2012.6462868
M3 - Conference contribution
AN - SCOPUS:84874691932
SN - 9781467324892
T3 - 2012 2nd International Conference on Advances in Computational Tools for Engineering Applications, ACTEA 2012
SP - 20
EP - 23
BT - 2012 2nd International Conference on Advances in Computational Tools for Engineering Applications, ACTEA 2012
T2 - 2012 2nd International Conference on Advances in Computational Tools for Engineering Applications, ACTEA 2012
Y2 - 12 December 2012 through 15 December 2012
ER -