> REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) <

Copyright (c) 2013 IEEE. Personal use of this material is permitted. However, permission to use this material for any other purposes must be obtained from the IEEE by sending an email to pubs-permissions@ieee.org Abstract — Although a large number of methods for video text detection and recognition have been proposed over the past years, it is hard to find the best state-of-art method because of non-availability of standard dataset, ground truth and common evaluation measures. Therefore, in this paper, we propose a semi-automatic system for ground truth generation of video text detection and recognition, which includes English and Chinese text of different orientation. The system has a facility to allow the user for manual correction of the ground truth if the automatic method produces wrong results. We propose nine attributes at word level namely: line index, word index