Character Keypoint-based Homography Estimation in Scanned Documents for Efficient Information Extraction
This addresses the challenge of precise document alignment for efficient information extraction in domains like insurance, though it is incremental as it builds on existing OCR and keypoint methods.
The paper tackles the problem of aligning scanned or camera-captured document images for information extraction by proposing a novel algorithm that uses character-based keypoints from OCR, achieving fast and accurate homography estimation as validated on real-world health insurance claim form datasets.
Precise homography estimation between multiple images is a pre-requisite for many computer vision applications. One application that is particularly relevant in today's digital era is the alignment of scanned or camera-captured document images such as insurance claim forms for information extraction. Traditional learning based approaches perform poorly due to the absence of an appropriate gradient. Feature based keypoint extraction techniques for homography estimation in real scene images either detect an extremely large number of inconsistent keypoints due to sharp textual edges, or produce inaccurate keypoint correspondences due to variations in illumination and viewpoint differences between document images. In this paper, we propose a novel algorithm for aligning scanned or camera-captured document images using character based keypoints and a reference template. The algorithm is both fast and accurate and utilizes a standard Optical character recognition (OCR) engine such as Tesseract to find character based unambiguous keypoints, which are utilized to identify precise keypoint correspondences between two images. Finally, the keypoints are used to compute the homography mapping between a test document and a template. We evaluated the proposed approach for information extraction on two real world anonymized datasets comprised of health insurance claim forms and the results support the viability of the proposed technique.