Name
Abstract | ||
|---|---|---|
We present a restoration framework to reduce undesirable distortions in imaged documents. Our framework is based on two components: (1) an image inpainting procedure that can separate non-uniform illumination (and other) artifacts from the printed content and (2) a shape-from-shading (SfS) formulation that can reconstruct the 3D shape of the document's surface. Used either piecewise or in its entirety, this framework can correct a variety of distortions including shading, shadow, ink-bleed, show-through, perspective and geometric distortions, for both camera-imaged and flatbed-imaged documents. Our overall framework is described in detail. In addition, our SfS formulation can be easily modified to target various illumination conditions to suit different real-world applications. Results on images of synthetic and real documents demonstrate the effectiveness of our approach. OCR results are also used to gauge the performance of our approach. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1016/j.patcog.2009.03.025 | Pattern Recognition |
Keywords | Field | DocType |
geometric warping,digital inpainting,are also used to gauge the performance of our approach. key words: document image restoration,sfs formulation,shading distortion,unified framework,different real-world application,physically based flattening,document restoration,shape-from-shading,flatbed-imaged document,non-uniform illumination,physically-based flattening.,overall framework,perspective distortion,rbf-based smoothing,document image restoration,ocr result,restoration framework,geometric distortion,imaged document,various illumination condition,image restoration,shape from shading | Iterative reconstruction,Computer vision,Perspective distortion,Pattern recognition,Image processing,Optical character recognition,Inpainting,Artificial intelligence,Image restoration,Photometric stereo,Piecewise,Mathematics | Journal |
Volume | Issue | ISSN |
42 | 11 | Pattern Recognition |
Citations | PageRank | References |
16 | 0.68 | 50 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Li Zhang | 1 | 2286 | 151.94 |
| Andy M. Yip | 2 | 232 | 20.65 |
| Michael S. Brown | 3 | 2122 | 129.13 |
| Chew Lim Tan | 4 | 4484 | 284.26 |