Document Rectification and Illumination Correction using a Patch-based CNN
Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
Original language | English |
---|---|
Article number | 168 |
Journal / Publication | ACM Transactions on Graphics |
Volume | 38 |
Issue number | 6 |
Publication status | Published - Nov 2019 |
Link(s)
Abstract
We propose a novel learning method to rectify document images with various distortion types from a single input image. As opposed to previous learning-based methods, our approach seeks to first learn the distortion flow on input image patches rather than the entire image. We then present a robust technique to stitch the patch results into the rectified document by processing in the gradient domain. Furthermore, we propose a second network to correct the uneven illumination, further improving the readability and OCR accuracy. Due to the less complex distortion present on the smaller image patches, our patch-based approach followed by stitching and illumination correction can significantly improve the overall accuracy in both the synthetic and real datasets.
Research Area(s)
- Convolutional neural networks, Deep learning, Document image rectification
Citation Format(s)
Document Rectification and Illumination Correction using a Patch-based CNN. / LI, Xiaoyu; ZHANG, Bo; LIAO, Jing; SANDER, Pedro V.
In: ACM Transactions on Graphics, Vol. 38, No. 6, 168, 11.2019.Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review