A data base for Arabic handwritten text recognition research

S. Al-Ma'adeed1, D. Elliman1, C.A. Higgins1
1School of Computer Science and Information Technology, University of Nottingham, Jubilee Campus, Nottingham, UK

Tóm tắt

In this paper we present a new database for off-line Arabic handwriting recognition, together with associated preprocessing procedures. We have developed a new database for the collection, storage and retrieval of Arabic handwritten text (AHDB). This is an advance both in terms of the size of the database as well as the number of different writers involved. We further designed an innovative, simple yet powerful, in place tagging procedure for our database. It enables us to easily extract the bitmaps of words. We also constructed a preprocessing class, which contains some useful preprocessing operations. In this paper the most popular words in Arabic writing were identified for the first time, using an associated program.

Từ khóa

#Text recognition #Handwriting recognition #Character recognition #Writing #Image databases #Information retrieval #Computer science #Information technology #Tagging #Natural languages

Tài liệu tham khảo

10.1109/34.667887 parker, 1997, Algorithms for Image Processing and Computer Vision cracknell, 1997, A colour approach to form dropout, A. Downton and S. Impedovo, Progress in Handwriting Recognition, World Scientific howell, 2000, Getting to Grips with Graphic File Format 0 downton, 1997, Progress in handwriting recognition, World Scientific johansson, 1978, Manual of information to accompany the lancaster-oslo/bergen corpus of british english, for use with digital computers, Department of Engineering 0 10.1109/5.156472 10.1109/ICDAR.1999.791885 rafuel, 1992, Digital Image Processing saadallah, 1985, Design of an arabic character reading machine, Proc of Computer Processing of Arabic Language almaadeed, 2001, A new preprocessing system for the recognition of off-line handwritten arabic words, IEEE International Symposium on Signal Processing and Information Technology 10.1109/TPAMI.1987.4767970 10.1109/34.295912 suen, 1990, Presented at the int. Workshop frontiers handwriting recogn, Montreal freitas, 2000, Brazilian bank check handwritten legal amount, Proceedings of the XIII Brizilian Symposium on Computer Graphics and Image Processing (SIBGRAPI'00, 10.1109/SIBGRA.2000.883901 10.1016/0167-8655(94)90118-X obaid, 1994, Arabic handwritten character recognition by neural nets, Journal on Communications, 45, 90 10.1016/0031-3203(95)00110-7 10.1109/34.291440 10.1109/34.291449