Title :
Geometric Rectification of Camera-Captured Document Images
Author :
Liang, Jian ; DeMenthon, Daniel ; Doermann, David
Author_Institution :
Amazon.com, Seattle
fDate :
4/1/2008 12:00:00 AM
Abstract :
Compared to typical scanners, handheld cameras offer convenient, flexible, portable, and noncontact image capture, which enables many new applications and breathes new life into existing ones. However, camera-captured documents may suffer from distortions caused by a nonplanar document shape and perspective projection, which lead to the failure of current optical character recognition (OCR) technologies. We present a geometric rectification framework for restoring the frontal-flat view of a document from a single camera-captured image. Our approach estimates the 3D document shape from texture flow information obtained directly from the image without requiring additional 3D/metric data or prior camera calibration. Our framework provides a unified solution for both planar and curved documents and can be applied in many, especially mobile, camera-based document analysis applications. Experiments show that our method produces results that are significantly more OCR compatible than the original images.
Keywords :
document image processing; image sensors; image texture; optical character recognition; OCR; camera-based document analysis; camera-captured document images; geometric rectification; nonplanar document shape; optical character recognition; texture flow information; Camera-based OCR; image rectification; shape estimation; texture flow analysis.; Algorithms; Artifacts; Artificial Intelligence; Automatic Data Processing; Documentation; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Pattern Recognition, Automated; Photography; Reproducibility of Results; Sensitivity and Specificity;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2007.70724