International Journal of Computer Vision
Document Image De-warping for Text/Graphics Recognition
Proceedings of the Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
Binarising Camera Images for OCR
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Rectifying the Bound Document Image Captured by the Camera: A Model Based Approach
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Correcting Document Image Warping Based on Regression of Curved Text Lines
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 1
Image Restoration of Arbitrarily Warped Documents
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Robust Algorithm of Principal Curve Detection
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
Restoring Warped Document Images through 3D Shape Modeling
IEEE Transactions on Pattern Analysis and Machine Intelligence
Warped Image restoration with Applications to Digital Libraries
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Dewarping of document image by global optimization
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Document Image Dewarping using Robust Estimation of Curled Text Lines
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Hi-index | 0.01 |
Geometric distortion often occurs when taking images of bound documents. This phenomenon greatly impairs recognition accuracy. In this paper, a new one-image based method is proposed to correct geometric distortion in bound document images. According to this method, the document image is binarized first. Next, curved text-line features are extracted. Thirdly, locally optimized text curves are detected using a graph model. Finally, the technique of texture warping is applied to correct the image. Experimental results show that images restored by our proposed method can achieve good perception and recognition results.