Using skeleton and Hough transform variant to correct skew in historical documents

Boudraa, Omar; Hidouci, Walid Khaled; Michelucci, Dominique

doi:10.1016/j.matcom.2019.05.009

Cited by 21 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 6 shows that the ATOP80 value of our method is 0.081, which is much smaller than that of the SHT method and PP method, and is only 0.3 larger than that of the-state-of-art method (Boudraa's method). In addition, from the experimental results of [38], we can see that the computational time of Boudraa's method is greater than that of SHT method and similar to the computational time of PP method. From Figure 6, we can see that our method is much faster than SHT method and PP method.…”

Section: Comparison Of Accuracymentioning

confidence: 73%

“…In Boudraa's method [38], to validate the inclination angle estimation performance, they used some indicators to valuate and compare their experiment results. In our experiment, we used the same indicators.…”

Section: Evaluation Criteriamentioning

confidence: 99%

“…Here, we compare our approach with the existing related skew correction methods, which are standard Hough transform (SHT) method in [39], projection profile analysis method [11], and Boudraa's method [38]. The SHT method is applied on extracted contours of objects using Canny filter.…”

Section: Comparison Of Accuracymentioning

confidence: 99%

See 2 more Smart Citations

An Efficient Document Skew Detection Method Using Probability Model and Q Test

Huang

Chen

et al. 2019

Electronics

View full text Add to dashboard Cite

Document skew detection is one of the key technologies in most of the document analysis systems. However, existing skew detection methods either have low accuracy or require a large amount of computation. To achieve a good tradeoff between efficiency and performance, we propose a novel skew detection approach based on bounding boxes, probability model, and Dixon’s Q test. Firstly, bounding boxes are used to pick out the eligible connected components (ECC). Then, we calculate the slopes of the skew document with the probability model. Finally, we find the optimal result with Dixon’s Q test and projection profile method. Moreover, the proposed method can detect the skew angle in a wider range. The experimental results show that our skew detection algorithm can achieve high speed and accuracy simultaneously compared with existing algorithms.

show abstract

Section: Comparison Of Accuracymentioning

confidence: 73%

Section: Evaluation Criteriamentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Document Skew Detection Method Using Probability Model and Q Test

Huang

Chen

et al. 2019

Electronics

View full text Add to dashboard Cite

show abstract

“…The Hough Line Detection algorithm [6,7,8,9,10], utilised in the aforementioned algorithm, involves the following steps:…”

Section: Related Workmentioning

confidence: 99%

Automated Document Orientation Correction Using Skew and Inversion Rectification With Hough Line Transformation and Machine Learning

shafi¹,

Atif²,

Shafi³

2023

Preprint

View full text Add to dashboard Cite

Document deskewing is a fundamental problem in document image processing. While existing methods have limitations, such as Hough Line Transformation that can deskew images upside down, and Deep Learning models that require huge amounts of human labour and computational resources and still fail to deskew while taking care of orientation, OCR-based methods also struggle to read text when it is tilted. In this paper, we propose a novel, simple, cost-effective deep learning method for fixing the skew and orientation of documents. Our approach reduces the search space for the machine learning model to predict whether an image is upside down or not, avoiding the huge search space of predicting an angle between 0 and 360. We finetuned a MobileNetV2 model, which was pre-trained on imagenet, using only 200 images and achieve good results. This method is useful for automation-based tasks, such as data extraction using OCR technology, and can greatly reduce manual labour.

show abstract

“…This is non-contact angle detection from a digital image. For example, while Hough transform has been frequently applied to detect the skew angle of the characters in documents (Amin and Fischer, 2000;Singh et al, 2008;Boukharouba, 2017;Boudraa et al, 2020) and to evaluate the rotation of loosened bolts (Park et al, 2015;Cha et al, 2016;Pham et al, 2020;Ta and Kim, 2020), it has found applications in the measurement of contact angle between liquid and solid interface (Xu et al, 2013) and in the estimation of muscle fiber orientation in the medical field (Zhou and Zheng, 2008).…”

Section: Introductionmentioning

confidence: 99%

Non-contact detection of degradation of in-service steel sheet piles due to buckling phenomena by using digital image analysis with Hough transform

Hagiwara

Shimamoto

Suzuki

2022

Front. Built Environ.

View full text Add to dashboard Cite

Steel sheet pile materials are primarily used for canal structure construction for irrigation and drainage of agricultural fields in Japan. Recently, accelerated corrosion of steel materials and buckling phenomena in pitting corrosion parts have been detected in in-service steel sheet pile canals. In this study, we focus on the buckling phenomenon of in-service steel sheet pile canals, which is detected by non-contact monitoring using digital image analysis. The buckling phenomenon index is evaluated as the inclination angle of the steel sheet pile due to deformation. As a digital image analysis, Hough transform is applied, which is a figure detection method in digital images, to detect a straight line that describes the distance and angle parameters. The angle parameter corresponds to the inclination angle index of in-service steel sheet pile with a buckling phenomenon. As a result, the maximum difference between the analyzed angles by Hough transform and the measured angles is evaluated as 0.9° after the image rotation correction. The relation of the analyzed angles by Hough transform and the measured angles of the buckling phenomenon is correlated. Therefore, the degradation of steel sheet pile canals is quantitatively evaluated by using digital image analysis with unmanned aerial vehicle monitoring. This study’s significance is non-contact and simple measurement by using a digital image which can reduce a working time and perform quick diagnosis in extensive areas.

show abstract

Using skeleton and Hough transform variant to correct skew in historical documents

Cited by 21 publications

References 30 publications

An Efficient Document Skew Detection Method Using Probability Model and Q Test

An Efficient Document Skew Detection Method Using Probability Model and Q Test

Automated Document Orientation Correction Using Skew and Inversion Rectification With Hough Line Transformation and Machine Learning

Non-contact detection of degradation of in-service steel sheet piles due to buckling phenomena by using digital image analysis with Hough transform

Contact Info

Product

Resources

About