Document Layout Analysis

BinMakhashen, Galal M.; Mahmoud, Sabri A.

doi:10.1145/3355610

Cited by 123 publications

(26 citation statements)

References 113 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, the Projection Profile method showed a 100% success rate with the confidence of ±0.3 • in the studies by Mahajan and Apoorva [26]. A comparison made by Binmakhashen and Mahmoud [3], about the Singh et al [38] studies show a small error rate of 0.05 • for documents with angles ≤ 150 • using the Hough Transform technique in document analysis.…”

Section: Main Techniques Used In Omr Processingmentioning

confidence: 97%

“…Tilt detection and correction are closely linked to the segmentation phase, that is, to extracting regions from the document. The input images must be defined in a standard format, for example, all images with the skew angle at 0 • [3]. Some approaches use the base of the lines of writing to detect the skew angle [15,29].…”

Section: Main Techniques Used In Omr Processingmentioning

confidence: 99%

“…Rotation or skew correction in images and documents is often performed using the following techniques [5,13]: Cross-Correlation; Fourier Method or Frequency Domain; Gradient Approach; Hough Transform; Line Fitting; Moments with Wavelet transform; Nearest Neighbor Approach; Principal Component Analysis (PCA); Principal Component Analysis with Wavelet transform; Projection Profile; Radon transform. An extensive review of these techniques has been detailed in the work by Binmakhashen and Mahmoud [3] and Mehta and Doshi [27].…”

Section: Main Techniques Used In Omr Processingmentioning

confidence: 99%

See 2 more Smart Citations

Optical Mark Recognition: Advances, Difficulties, and Limitations

2021

View full text Add to dashboard Cite

Performing mass assessment corrections is a tedious and costly task, especially when allocating teachers or instructors to do these corrections. Such task can be facilitated and accelerated by Optical Mark Recognition (OMR) technology, bringing educational institutions to look for this solution. OMR initially appeared as a dedicated hardware solution, but software solutions have emerged with the evolution of technology, gradually replacing dedicated equipment. However, most solutions lack flexibility, mainly for the end-users. The literature proposes several methods, often highlighting the issue of cost and accessibility. The present work reviews 35 papers around OMR subject and lists the reviewed methods' main characteristics, datasets, restrictions, technological challenges, techniques used, processing time, and accuracy. We map and categorize the restrictions to help the reader improve the current software OMR technology state. We also call the community's attention to the lack of a standard dataset that could be used to compare OMR solutions.

show abstract

Section: Main Techniques Used In Omr Processingmentioning

confidence: 97%

Section: Main Techniques Used In Omr Processingmentioning

confidence: 99%

Section: Main Techniques Used In Omr Processingmentioning

confidence: 99%

See 1 more Smart Citation

Optical Mark Recognition: Advances, Difficulties, and Limitations

2021

View full text Add to dashboard Cite

show abstract

“…Tesseract offers a number of pre-processing mechanisms for document images, however, it does not implement the full range of state-of-the-art OCR. Image pre-processing as proposed and implemented by the OCR-D project (Binmakhashen and Mahmoud, 2019;Neudecker et al, 2019), is beneficial to additionally extend the tool with the latest developments in OCR.…”

Section: Foundations and Related Workmentioning

confidence: 99%

Supporting Land Reuse of Former Open Pit Mining Sites using Text Classification and Active Learning

Schröder¹,

Annanias²,

Niekler³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Open pit mines left many regions worldwide inhospitable or uninhabitable. Many sites are left behind in a hazardous or contaminated state, show remnants of waste, or have other restrictions imposed upon them, e.g., for the protection of human or nature. Such information has to be permanently managed in order to reuse those areas in the future. In this work we present and evaluate an automated workflow for supporting the post-mining management of former lignite open pit mines in the eastern part of Germany, where prior to any planned land reuse, aforementioned information has to be acquired to ensure the safety and validity of such an endeavor. Usually, this information is found in expert reports, either in the form of paper documents, or in the best case as digitized unstructured text-all of them in German language. However, due to the size and complexity of these documents, any inquiry is tedious and time-consuming, thereby slowing down or even obstructing the reuse of related areas. Since no training data is available, we employ active learning in order to perform multi-label sentence classification for two categories of restrictions and seven categories of topics. The final system integrates optical character recognition (OCR), active-learningbased text classification, and geographic information system visualization in order to effectively extract, query, and visualize this information for any area of interest. Active learning and text classification results are twofold: Whereas the restriction categories were reasonably accurate (>0.85 F1), the seven topicoriented categories seemed to be complex even for human annotators and achieved mediocre evaluation scores (<0.70 F1).

show abstract

“…Although difficult, layout analysis is however essential for historical newspaper understanding and exploitation, and their quality has a direct impact on downstream processes [Binmakhashen and Mahmoud, 2019]. From an information retrieval and user viewpoint, being able to query at the level of meaningful segments such as articles -instead of whole pages-, and to facet over different types of segments are undeniable advantages.…”

Section: Introductionmentioning

confidence: 99%

Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers

Barman¹,

Ehrmann²,

Clematide³

et al. 2021

Journal of Data Mining &Amp; Digital Humanities

View full text Add to dashboard Cite

The massive amounts of digitized historical documents acquired over the last decades naturally lend themselves to automatic processing and exploration. Research work seeking to automatically process facsimiles and extract information thereby are multiplying with, as a first essential step, document layout analysis. If the identification and categorization of segments of interest in document images have seen significant progress over the last years thanks to deep learning techniques, many challenges remain with, among others, the use of finer-grained segmentation typologies and the consideration of complex, heterogeneous documents such as historical newspapers. Besides, most approaches consider visual features only, ignoring textual signal. In this context, we introduce a multimodal approach for the semantic segmentation of historical newspapers that combines visual and textual features. Based on a series of experiments on diachronic Swiss and Luxembourgish newspapers, we investigate, among others, the predictive power of visual and textual features and their capacity to generalize across time and sources. Results show consistent improvement of multimodal models in comparison to a strong visual baseline, as well as better robustness to high material variance.

show abstract

Document Layout Analysis

Cited by 123 publications

References 113 publications

Optical Mark Recognition: Advances, Difficulties, and Limitations

Optical Mark Recognition: Advances, Difficulties, and Limitations

Supporting Land Reuse of Former Open Pit Mining Sites using Text Classification and Active Learning

Combining Visual and Textual Features for Semantic Segmentation of Historical Newspapers

Contact Info

Product

Resources

About