13 April 2018 Fast words boundaries localization in text fields for low quality document images
Author Affiliations +
Proceedings Volume 10696, Tenth International Conference on Machine Vision (ICMV 2017); 106960V (2018) https://doi.org/10.1117/12.2311341
Event: Tenth International Conference on Machine Vision, 2017, Vienna, Austria
Abstract
The paper examines the problem of word boundaries precise localization in document text zones. Document processing on a mobile device consists of document localization, perspective correction, localization of individual fields, finding words in separate zones, segmentation and recognition. While capturing an image with a mobile digital camera under uncontrolled capturing conditions, digital noise, perspective distortions or glares may occur. Further document processing gets complicated because of its specifics: layout elements, complex background, static text, document security elements, variety of text fonts. However, the problem of word boundaries localization has to be solved at runtime on mobile CPU with limited computing capabilities under specified restrictions. At the moment, there are several groups of methods optimized for different conditions. Methods for the scanned printed text are quick but limited only for images of high quality. Methods for text in the wild have an excessively high computational complexity, thus, are hardly suitable for running on mobile devices as part of the mobile document recognition system. The method presented in this paper solves a more specialized problem than the task of finding text on natural images. It uses local features, a sliding window and a lightweight neural network in order to achieve an optimal algorithm speed-precision ratio. The duration of the algorithm is 12 ms per field running on an ARM processor of a mobile device. The error rate for boundaries localization on a test sample of 8000 fields is 0.3
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Dmitry Ilin, Dmitry Ilin, Dmitriy Novikov, Dmitriy Novikov, Dmitry Polevoy, Dmitry Polevoy, Dmitry Nikolaev, Dmitry Nikolaev, } "Fast words boundaries localization in text fields for low quality document images", Proc. SPIE 10696, Tenth International Conference on Machine Vision (ICMV 2017), 106960V (13 April 2018); doi: 10.1117/12.2311341; https://doi.org/10.1117/12.2311341
PROCEEDINGS
8 PAGES


SHARE
Back to Top