Multiple Geometry Transform Estimation from Single Camera-Captured Text Image

This article proposes a new approach to jointly rectify multi-distorted text image planes using a single image. Without extracting text lines or analyzing the text layout, the algorithm build a Multi-Distortion Dewarping (MDD) model based on modified text transform invariant low-rank textures. Harnessing the fact that two-intersection text plane share a same vanishing point, MDD algorithm greatly increase the estimation accuracy of geometry distortion. To further enhance the robustness of the propose method, a distorted text detection algorithm is used as pre-process to remove non-text region. With the accurately estimated geometry distortion of each plane, the input image can be well projected onto a single image plane and generate a good dewarping results. The MDD is robust to noise and works well for both short phrase and multiple text lines. Extensive compare experiments show the robustness and efficiency of MDD algorithm.