Multistage Curvilinear Coordinate Transform Based Document Image Dewarping using a Novel Quality Estimator
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Optical Character Recognition (OCR)Similar Papers 제목 키워드 기반
Curvilinear-Coordinate-Based Object and Situation Assessment for Highly Automate
This paper presents a novel curvilinear-coordinate-based approach to improve object and situation assessment performance for highly automated vehicles under various curved road conditions. The approach integrates object …
Computational EfficiencyObjectState EstimationExtraction of Virtual Baselines From Distorted Document Images Using Curvilinear Projection
The baselines of a document page are a set of virtual horizontal and parallel lines, to which the printed contents of document, e.g., text lines, tables or inserted photos, are aligned. Accurate baseline extraction is of…
Local Intensity Order Transformation for Robust Curvilinear Object Segmentation
Segmentation of curvilinear structures is important in many applications, such as retinal blood vessel segmentation for early detection of vessel diseases and pavement crack segmentation for road condition evaluation and…
Crack SegmentationObjectSegmentationSemantic SegmentationFlow Matching Meets 3D Curvilinear Structure Segmentation in Medical Imaging
Segmentation of curvilinear anatomical structures in 3D medical images remains challenging due to complex topology, severe class imbalance, weak contrast, and large variations in structure morphology. While deep learning…
Curvilinear object segmentation in medical images based on ODoS filter and deep learning network
Automatic segmentation of curvilinear objects in medical images plays an important role in the diagnosis and evaluation of human diseases, yet it is a challenging uncertainty in the complex segmentation tasks due to diff…
Deep LearningSegmentationSemantic Segmentation