SIGIR '95 Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval
Degraded text recognition using visual and linguistic context
Degraded text recognition using visual and linguistic context
Optical Character Recognition: An Illustrated Guide to the Frontier
Optical Character Recognition: An Illustrated Guide to the Frontier
Computational Statistics & Data Analysis - Nonlinear methods and data mining
Text Categorization with Suport Vector Machines: Learning with Many Relevant Features
ECML '98 Proceedings of the 10th European Conference on Machine Learning
Probabilistic Retrieval of OCR Degraded Text Using N-Grams
ECDL '97 Proceedings of the First European Conference on Research and Advanced Technology for Digital Libraries
Video OCR: indexing digital new libraries by recognition of superimposed captions
Multimedia Systems - Special section on video libraries
An Evaluation of Information Retrieval Accuracy with Simulated OCR Output
An Evaluation of Information Retrieval Accuracy with Simulated OCR Output
Towards automatic sign translation
HLT '01 Proceedings of the first international conference on Human language technology research
BLEU: a method for automatic evaluation of machine translation
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
OCR error correction using a noisy channel model
HLT '02 Proceedings of the second international conference on Human Language Technology Research
Automatic detection and recognition of signs from natural scenes
IEEE Transactions on Image Processing
A line-based representation for matching words in historical manuscripts
Pattern Recognition Letters
Hi-index | 0.01 |
In this paper, we present a system that automatically translates Arabic text embedded in images into English. The system consists of three components: text detection from images, character recognition, and machine translation. We formulate the text detection as a binary classification problem and apply gradient boosting tree (GBT), support vector machine (SVM), and location-based prior knowledge to improve the F1 score of text detection from 78.95% to 87.05%. The detected text images are processed by off-the-shelf optical character recognition (OCR) software. We employ an error correction model to post-process the noisy OCR output, and apply a bigram language model to reduce word segmentation errors. The translation module is tailored with compact data structure for hand-held devices. The experimental results show substantial improvements in both word recognition accuracy and translation quality. For instance, in the experiment of Arabic transparent font, the BLEU score increases from 18.70 to 33.47 with use of the error correction module.