论文标题
使用新型质量估计器的多阶段曲线坐标基于转换的文档图像露水
Multistage Curvilinear Coordinate Transform Based Document Image Dewarping using a Novel Quality Estimator
论文作者
论文摘要
目前的工作展示了一种快速，改进的技术，用于脱瓦非线性扭曲的文档图像。首先，通过使用曲线同型估算最佳的反向投影，首先将图像脱水。然后，通过评估与文本线和直线对象的特征相关的一组指标来估算该过程的质量，以测量并行性，正交性等。这些都是专门设计的，目的是估计脱瓦过程的质量，而无需任何地面真理。如果估计质量不令人满意，则使用更近近似值重复页面级脱水过程。接下来是线条脱水过程，在单个文本线上对扭曲进行了颗粒状的校正。该方法已在CBDAR 2007 / IUPR 2011文档图像脱瓦数据集上进行了测试，并且可以在最短的时间内产生最佳的OCR准确性。该方法的实用性还在Docunet 2018数据集上进行了一些较小的调整，并被认为会产生可比的结果。
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.
