Script-agnostic reflow of text in document images
By Saurabh Panjwani, Abhinav Uppal, Edward Cutrell
Proceedings of the 13th International Conference on Human Computer Interaction with Mobile Devices and Services (Mobile HCI) | August 2011
DOI
doi.org/10.1145/2037373.2037419
Citation
Panjwani, Saurabh., Uppal, Abhinav., Cutrell, Edward. Script-agnostic reflow of text in document images Proceedings of the 13th International Conference on Human Computer Interaction with Mobile Devices and Services (Mobile HCI) doi.org/10.1145/2037373.2037419.
Copyright
Proceedings of the 13th International Conference on Human Computer Interaction with Mobile Devices and Services (Mobile HCI), 2011
Share:
Abstract
Reading text from document images can be difficult on mobile devices due to the limited screen width available on them. While there exist solutions for reflowing Latin-script texts on such devices, these solutions do not work well for images of other scripts or combinations of scripts, since they rely on script-specific characteristics or OCR. We present a technique that reflows text in document images in a manner that is agnostic to the script used to compose them. Our technique achieved over 95% segmentation accuracy for a corpus of 139 images containing text in 4 genetically-distant languages-English, Hindi, Kannada and Arabic. A preliminary user study with a prototype implementation of the technique provided evidence of some of its usability benefits.

Abhinav Uppal is an assistant professor of Marketing at the Indian School of Business. His research interests lie broadly in using microeconomic theory and game-theory based models to study topical problems in marketing. Currently, his work focuses on two main streams of research: the first is retailing, specifically how traditional retailers can counter modern threats; the second is competitive strategy and pricing, particularly how various market settings, structures, and strategic partnerships influence firms’ competitive behavior and marketing decisions.

Professor Uppal received his PhD and MS in Marketing from the Wharton School, University of Pennsylvania. He has previously worked on algorithmic trading strategies in equity markets at Tower Research Capital and conducted research on technology for emerging markets at Microsoft Research India. He holds a BTech in Computer Science from the Indian Institute of Technology (IIT) Delhi and is a KVPY and NTSE scholar.

Abhinav Uppal (2)
Abhinav Uppal