A Method to Generate Synthetically Warped Document Image

TL;DR

This paper introduces a method to generate synthetic warped document images from flat scans using controllable warping parameters, aiding in training deep learning models for document dewarping tasks.

Contribution

It presents a novel technique to synthesize warped document images with adjustable parameters, addressing the lack of large benchmark datasets for dewarping research.

Findings

Synthetic images closely resemble real warped images both qualitatively and quantitatively.

The method allows flexible control over the degree and type of warping.

Generated datasets can improve deep learning model training for document dewarping.

Abstract

The digital camera captured document images may often be warped and distorted due to different camera angles or document surfaces. A robust technique is needed to solve this kind of distortion. The research on dewarping of the document suffers due to the limited availability of benchmark public dataset. In recent times, deep learning based approaches are used to solve the problems accurately. To train most of the deep neural networks a large number of document images is required and generating such a large volume of document images manually is difficult. In this paper, we propose a technique to generate a synthetic warped image from a flat-bedded scanned document image. It is done by calculating warping factors for each pixel position using two warping position parameters (WPP) and eight warping control parameters (WCP). These parameters can be specified as needed depending upon the desired warping. The results are compared with similar real captured images both qualitative and quantitative way.