Adaptive cropping and deskewing of scanned documents based on high accuracy estimation of skew angle and cropping value

Cai, Chengtao; Meng, Huan; Qiao, Renjie

doi:10.1007/s00371-020-01952-z

Cited by 5 publications

(1 citation statement)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All regions of the document image are clustered using a KNN, which makes the orientation in the frequency domain easier to be detected. Considering that there are different kinds of redundant edges in document images, Cai et al [ 21 ] proposed an improved algorithm, which can automatically crop and estimate the skew angle of the document image. Hyung IL Koo et al [ 22 ] proposed a salient line detect-based method that highlights the edges representing the skew degree by improving the edge detection method, and then the edge line is extracted through Progressive Probabilistic Hough Transform (PPHT) [ 23 ].…”

Section: Related Workmentioning

confidence: 99%

A Novel Adaptive Deskewing Algorithm for Document Images

Bao

Yang

et al. 2022

Sensors

View full text Add to dashboard Cite

Document scanning often suffers from skewing, which may seriously influence the efficiency of Optical Character Recognition (OCR). Therefore, it is necessary to correct the skewed document before document image information analysis. In this article, we propose a novel adaptive deskewing algorithm for document images, which mainly includes Skeleton Line Detection (SKLD), Piecewise Projection Profile (PPP), Morphological Clustering (MC), and the image classification method. The image type is determined firstly based on the image’s layout feature. Thus, adaptive correcting is applied to deskew the image according to its type. Our method maintains high accuracy on the Document Image Skew Estimation Contest (DISEC’2013) and PubLayNet datasets, which achieved 97.6% and 80.1% accuracy, respectively. Meanwhile, extensive experiments show the superiority of the proposed algorithm.

show abstract

Section: Related Workmentioning

confidence: 99%