Historical Document Binarization Based on Phase Information of Images

2013 ◽  
pp. 1-12 ◽  
Author(s):  
Hossein Ziaei Nafchi ◽  
Reza Farrahi Moghaddam ◽  
Mohamed Cheriet
Keyword(s):  
Historical Document ◽  
Phase Information ◽  
Document Binarization

Document image binarization using difference of concatenated convolutions

2021 ◽  
pp. 1-14
Author(s):  
R.L. Jyothi ◽  
M. Abdul Rahiman
Keyword(s):  
Parameter Tuning ◽  
Document Image ◽  
Document Images ◽  
Historical Document ◽  
Proposed Model ◽  
Segmentation Methods ◽  
Document Image Binarization ◽  
Low Pass ◽  
Degraded Document ◽  
Document Binarization

Binarization is the most important stage in historical document image processing. Efficient working of character and word recognition algorithms depend on effective segmentation methods. Segmentation algorithms in turn depend on images free of noises and degradations. Most of these historical documents are illegible with degradations like bleeding through degradation, faded ink or faint characters, uneven illumination, contrast variation, etc. For effective processing of these document images, efficient binarization algorithms should be devised. Here a simple modified version of the Convolutional Neural Network (CNN) is proposed for historical document binarization. AOD-Net architecture for generating dehazed images from hazed images is modified to create the proposed network.The new CNN model is created by incorporating Difference of Concatenation layer (DOC), Enhancement layer (EN) and Thresholding layer into AOD-Net to make it suitable for binarization of highly degraded document images. The DOC layer and EN layer work effectively in solving degradation that exists in the form of low pass noises. The complexity of working of the proposed model is reduced by decreasing the number of layers and by introducing filters in convolution layers that work with low inter-pixel dependency. This modified version of CNN works effectively with a variety of highly degraded documents when tested with the benchmark historical datasets. The main highlight of the proposed network is that it works efficiently in a generalized manner for any type of document images without further parameter tuning. Another important highlight of this method is that it can handle most of the degradation categories present in document images. In this work, the performance of the proposed model is compared with Otsu, Sauvola, and three recent Deep Learning-based models.

scholarly journals U-Net-bin: hacking the document image binarization contest

2019 ◽  
Vol 43 (5) ◽  
pp. 825-832 ◽  
Author(s):  
P.V. Bezmaternykh ◽  
D.A. Ilin ◽  
D.P. Nikolaev
Keyword(s):  
Ground Truth ◽  
Document Image ◽  
Training Data ◽  
Data Preparation ◽  
Historical Document ◽  
Image Binarization ◽  
Biomedical Image ◽  
Document Image Binarization ◽  
Binarization Method ◽  
Document Binarization

Image binarization is still a challenging task in a variety of applications. In particular, Document Image Binarization Contest (DIBCO) is organized regularly to track the state-of-the-art techniques for the historical document binarization. In this work we present a binarization method that was ranked first in the DIBCO`17 contest. It is a convolutional neural network (CNN) based method which uses U-Net architecture, originally designed for biomedical image segmentation. We describe our approach to training data preparation and contest ground truth examination and provide multiple insights on its construction (so called hacking). It led to more accurate historical document binarization problem statement with respect to the challenges one could face in the open access datasets. A docker container with the final network along with all the supplementary data we used in the training process has been published on Github.

scholarly journals Degraded Historical Document Binarization: A Review on Issues, Challenges, Techniques, and Future Directions

2019 ◽  
Vol 5 (4) ◽  
pp. 48 ◽  
Author(s):  
Sulaiman ◽  
Omar ◽  
Nasrudin
Keyword(s):  
Hybrid Approach ◽  
Historical Document ◽  
Image Binarization ◽  
Future Directions ◽  
Low Contrast ◽  
Medical Reports ◽  
Digital Formats ◽  
Degraded Document ◽  
Document Binarization

In this era of digitization, most hardcopy documents are being transformed into digital formats. In the process of transformation, large quantities of documents are stored and preserved through electronic scanning. These documents are available from various sources such as ancient documentation, old legal records, medical reports, music scores, palm leaf, and reports on security-related issues. In particular, ancient and historical documents are hard to read due to their degradation in terms of low contrast and existence of corrupted artefacts. In recent times, degraded document binarization has been studied widely and several approaches were developed to deal with issues and challenges in document binarization. In this paper, a comprehensive review is conducted on the issues and challenges faced during the image binarization process, followed by insights on various methods used for image binarization. This paper also discusses the advanced methods used for the enhancement of degraded documents that improves the quality of documents during the binarization process. Further discussions are made on the effectiveness and robustness of existing methods, and there is still a scope to develop a hybrid approach that can deal with degraded document binarization more effectively.

Electron holography of catalysts

1995 ◽  
Vol 53 ◽  
pp. 416-417
Author(s):  
A. K. Datye ◽  
D. S. Kalakkad ◽  
L. F. Allard ◽  
E. Völkl
Keyword(s):  
Heterogeneous Catalysts ◽  
High Surface ◽  
High Surface Area ◽  
Atomic Scale ◽  
Nano Particles ◽  
Phase Image ◽  
Electron Holography ◽  
Specimen Thickness ◽  
Phase Information ◽  
Particle Structure

The active phase in heterogeneous catalysts consists of nanometer-sized metal or oxide particles dispersed within the tortuous pore structure of a high surface area matrix. Such catalysts are extensively used for controlling emissions from automobile exhausts or in industrial processes such as the refining of crude oil to produce gasoline. The morphology of these nano-particles is of great interest to catalytic chemists since it affects the activity and selectivity for a class of reactions known as structure-sensitive reactions. In this paper, we describe some of the challenges in the study of heterogeneous catalysts, and provide examples of how electron holography can help in extracting details of particle structure and morphology on an atomic scale.Conventional high-resolution TEM imaging methods permit the image intensity to be recorded, but the phase information in the complex image wave is lost. However, it is the phase information which is sensitive at the atomic scale to changes in specimen thickness and composition, and thus analysis of the phase image can yield important information on morphological details at the nanometer level.

Overview Of Story- Le Morte D' Arthur

Think India ◽  
2019 ◽  
Vol 22 (3) ◽  
pp. 500-505
Author(s):  
Anindita Naha ◽  
Dr. Mirza Maqsood Baig
Keyword(s):  
Round Table ◽  
Western Society ◽  
Western Civilization ◽  
Geoffrey Of Monmouth ◽  
King Arthur ◽  
Historical Document ◽  
Arthurian Legend ◽  
Great Literature ◽  
Over Time

The legend of King Arthur and his knights of the Round Table is immemorial. The heroic knights and their king’s tales contribute western society a great literature that is still well- known today. King Arthur along with the theme of chivalry greatly impacted not only western civilization, but all of society throughout the centuries. King Arthur and his Knights of the Round Table have been around for thousands of years but are only legends. The first reference to King Arthur was in the Historia Brittonum written by Nennius a Welsh monk around 830A.D. The fascinating legends however did not come until 1133 A.D in the work Historia Regum Britaniae written by a Welsh cleric, Geoffrey of Monmouth. His work was actually meant to be a historical document, but over time many other writers added on fictional tales. The Round Table was added in 1155 A.D by a French poet Maistre Wace. Both the English and French cycles of Arthurian Legend are controlled by three inter-related themes:

Tłumacz wobec przekazu wspomnieniowego (na materiale Dziennika warszawskiego Zinaidy Gippius w tłumaczeniu Henryka Chłystowskiego)

2017 ◽  
Vol 1 (XXII) ◽  
pp. 153-166
Author(s):  
Kinga Perużyńska
Keyword(s):  
Historical Document ◽  
Four Dimensions ◽  
Zinaida Gippius

The aim of the article is to present The Warsaw Diary by Zinaida Gippius, published in 1969 and translated into Polish by Henryk Chłystowski (2010). Based on the analysis of Russian and Polish versions of the book, it can be concluded that Chłystowski retains in his translation four dimensions of the diary as a historical document: facts, opinions, author’s personal feelings and her subjective mentality.

Sign in / Sign up

Export Citation Format

Share Document