A New Binarization Algorithm for Historical Documents

Almeida, Marcos de; Lins, Rafael Dueire; Bernardino, Rodrigo Barros; Jesus, Darlisson Marinho de

doi:10.3390/jimaging4020027

Cited by 16 publications

(8 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several methods of automatic thresholding, including statistical methods, global and local thresholding with iterative methods, linear combination, average and standard deviation, and Otsu algorithm described in [39,40,41].…”

Section: Methodsmentioning

confidence: 99%

Improvement of 3D Power Line Extraction from Multiple Low-Cost UAV Imagery Using Wavelet Analysis

Fryśkowska

2019

Sensors

View full text Add to dashboard Cite

Three-dimensional (3D) mapping of power lines is very important for power line inspection. Many remotely-sensed data products like light detection and ranging (LiDAR) have been already studied for power line surveys. More and more data are being obtained via photogrammetric measurements. This increases the need for the implementation of advanced processing techniques. In recent years, there have been several developments in visualisation techniques using UAV (unmanned aerial vehicle) platform photography. The most modern of such imaging systems have the ability to generate dense point clouds. However, image-based point cloud accuracy is very often various (unstable) and dependent on the radiometric quality of images and the efficiency of image processing algorithms. The main factor influencing the point cloud quality is noise. Such problems usually arise with data obtained via low-cost UAV platforms. Therefore, generated point clouds representing power lines are usually incomplete and noisy. To obtain a complete and accurate 3D model of power lines and towers, it is necessary to develop improved data processing algorithms. The experiment tested the algorithms on power lines with different voltages. This paper presents the wavelet-based method of processing data acquired with a low-cost UAV camera. The proposed, original method involves the application of algorithms for coarse filtration and precise filtering. In addition, a new way of calculating the recommended flight height was proposed. At the end, the accuracy assessment of this two-stage filtration process was examined. For this, point quality indices were proposed. The experimental results show that the proposed algorithm improves the quality of low-cost point clouds. The proposed methods improve the accuracy of determining the parameters of the lines by more than twice. About 10% of noise is reduced by using the wavelet-based approach.

show abstract

Section: Methodsmentioning

confidence: 99%

Improvement of 3D Power Line Extraction from Multiple Low-Cost UAV Imagery Using Wavelet Analysis

Fryśkowska

2019

Sensors

View full text Add to dashboard Cite

show abstract

“…Owing to noise, such as irregular background color, paper aging, stains, transludicity, and texture, binarization tasks for historical documents, including architectural drawing images, are signi cantly challenging [4]. Previous research on historical document binarization can be divided into three methods: thresholding-based, contrast-or edge-based, and feature learning-based.…”

Section: Related Workmentioning

confidence: 99%

Machine Learning-based Binarization Technique of Hand-drawn Floor Plans

Suh

Kim

2022

Preprint

View full text Add to dashboard Cite

Purpose: In this study, we propose a two-step binarization method for hand-drawn architectural floor plans to transform them into usable formats for indoor spatial modeling.Methods: First, a Gaussian mixture modeling was adopted to remove texture-like noise from the background. Second, 24 features were extracted to train the random forest model and the remaining line or spot-like noise was removed from the image. Moreover, the proposed method was applied to a completely different architectural drawing set to evaluate its generalization performance.Results: The experimental results indicated that the proposed method outperformed the other binarization techniques. Moreover, binarization result was outperforming with 0.987 F1-score. Conclusion: The experimental results showed that the overall performance of the proposed method was significantly superior to that of the other binarization methods. Moreover, they indicated that the proposed method is applicable to different types of architectural drawing, thereby proving its generalization.

show abstract

“…Some other recent ideas are the use of variational models [79], fast background estimation based on image resampling [19], as well as the application of independent thresholding of the RGB channels of historical document images [80] with the use of Otsu's method. Nevertheless, the latter method requires the additional training of the decision making block with the use of synthetic images.…”

Section: Overview Of Image Binarization Algorithmsmentioning

confidence: 99%

Robust Combined Binarization Method of Non-Uniformly Illuminated Document Images for Alphanumerical Character Recognition

Michalak

Okarma

2020

Sensors

View full text Add to dashboard Cite

Image binarization is one of the key operations decreasing the amount of information used in further analysis of image data, significantly influencing the final results. Although in some applications, where well illuminated images may be easily captured, ensuring a high contrast, even a simple global thresholding may be sufficient, there are some more challenging solutions, e.g., based on the analysis of natural images or assuming the presence of some quality degradations, such as in historical document images. Considering the variety of image binarization methods, as well as their different applications and types of images, one cannot expect a single universal thresholding method that would be the best solution for all images. Nevertheless, since one of the most common operations preceded by the binarization is the Optical Character Recognition (OCR), which may also be applied for non-uniformly illuminated images captured by camera sensors mounted in mobile phones, the development of even better binarization methods in view of the maximization of the OCR accuracy is still expected. Therefore, in this paper, the idea of the use of robust combined measures is presented, making it possible to bring together the advantages of various methods, including some recently proposed approaches based on entropy filtering and a multi-layered stack of regions. The experimental results, obtained for a dataset of 176 non-uniformly illuminated document images, referred to as the WEZUT OCR Dataset, confirm the validity and usefulness of the proposed approach, leading to a significant increase of the recognition accuracy.

show abstract

A New Binarization Algorithm for Historical Documents

Cited by 16 publications

References 29 publications

Improvement of 3D Power Line Extraction from Multiple Low-Cost UAV Imagery Using Wavelet Analysis

Improvement of 3D Power Line Extraction from Multiple Low-Cost UAV Imagery Using Wavelet Analysis

Machine Learning-based Binarization Technique of Hand-drawn Floor Plans

Robust Combined Binarization Method of Non-Uniformly Illuminated Document Images for Alphanumerical Character Recognition

Contact Info

Product

Resources

About