Text Selection by Structured Light Marking for Hand-held Cameras

Authors:
Eve Bertucci;Maurizio Pilu;Majid Mirmehdi
Affiliations:
-;-;-
Venue:
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Year:
2003

Citing 3
Cited 0

SUSAN—A New Approach to Low Level Image Processing

International Journal of Computer Vision
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
CamWorks: A Video-Based Tool for Efficient Capture from Paper Source Documents

ICMCS '99 Proceedings of the 1999 IEEE International Conference on Multimedia Computing and Systems - Volume 02

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe a method to enable the selection of specifictext regions with a hand-held camera by means ofprojecting a structured light pointer on the document.The user indicates the text required by dragging the laserpointer over it while a sequence of images is captured. Bytracking the motion of the camera over the document andmatching the trajectory to the actual text, the system isable to precisely determine the text portion the userintended to capture. By using this selection method alongwith a text-processing pipeline and OCR, a generalpurpose hand-held device (such as a PDA or mobilephone) with a camera could be used as effectively assingle-purpose pen scanning devices. We present ourresults showing successful capture and extraction of text.