Text recognition of low-resolution document images

Cheap and versatile cameras make it possible to easily and quickly capture a wide variety of documents. However, low resolution cameras present a challenge to OCR because it is virtually impossible to do character segmentation independently from recognition. In this paper we solve these problems sim...

Full description

Saved in:
Bibliographic Details
Published inEighth International Conference on Document Analysis and Recognition (ICDAR'05) pp. 695 - 699 Vol. 2
Main Authors Jacobs, C., Simard, P.Y., Viola, P., Rinker, J.
Format Conference Proceeding
LanguageEnglish
Published IEEE 2005
Subjects
Cameras
Character recognition
Dynamic programming
Handwriting recognition
Image segmentation
Machine learning
Neural networks
Optical character recognition software
Robustness
Text recognition
Online AccessGet full text

Cover

More Information
Summary:Cheap and versatile cameras make it possible to easily and quickly capture a wide variety of documents. However, low resolution cameras present a challenge to OCR because it is virtually impossible to do character segmentation independently from recognition. In this paper we solve these problems simultaneously by applying methods borrowed from cursive handwriting recognition. To achieve maximum robustness, we use a machine learning approach based on a convolutional neural network. When our system is combined with a language model using dynamic programming, the overall performance is in the vicinity of 80-95% word accuracy on pages captured with a 1024/spl times/768 webcam and 10-point text.
ISBN:9780769524207
0769524206
ISSN:1520-5363
2379-2140
DOI:10.1109/ICDAR.2005.233