基于多级坐标变换的文档图像质量估计方法
Multistage Curvilinear Coordinate Transform Based Document Image Dewarping using a Novel Quality Estimator
摘要：
目前的工作演示了一种快速和改进的技术去扭曲非线性扭曲的文档图像。首先，通过使用曲线单应性来估计最佳逆投影，在页面级对图像进行去扭曲。然后，通过评估一组与文本行和直线对象的特性相关的度量来估计过程的质量，以测量平行性、正交性等。这些度量是专门设计来估计去扭曲过程的质量的，而不需要任何地面实况。如果质量被估计为不令人满意，则使用更精细的近似来重复页面级去扭曲过程。接下来是行级的变形处理，对单个文本行中的变形进行粒度校正。该方法已在CBDAR 2007 / IUPR 2011文档图像去扭曲数据集上进行了测试，并在最短的时间内获得了最佳的OCR精度。该方法的有用性也在DocUNet 2018数据集上进行了评估，并进行了一些小的调整，并产生了可比较的结果。
英文摘要：
The present work demonstrates a fast and improved technique for dewarping nonlinearly warped document images. The images are first dewarped at the page-level by estimating optimum inverse projections using curvilinear homography. The quality of the process is then estimated by evaluating a set of metrics related to the characteristics of the text lines and rectilinear objects for measuring parallelism, orthogonality, etc. These are designed specifically to estimate the quality of the dewarping process without the need of any ground truth. If the quality is estimated to be unsatisfactory, the page-level dewarping process is repeated with finer approximations. This is followed by a line-level dewarping process that makes granular corrections to the warps in individual text-lines. The methodology has been tested on the CBDAR 2007 / IUPR 2011 document image dewarping dataset and is seen to yield the best OCR accuracy in the shortest amount of time, till date. The usefulness of the methodology has also been evaluated on the DocUNet 2018 dataset with some minor tweaks, and is seen to produce comparable results.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
