Document digitization lifecycle for complex magazine collection

Computer, 1992

Intelligent document segmentation can bring electronic browsing within the reach of most users. The authors show how this is achieved through document processing, analysis, and parsing the graphic sentence. L et's quickly calculate the requirements of electronic data storage and access for a standard library of technical journals. A medium-sized research library subscribes to about 2,000 periodicals, each averaging about 500 pages per volume, for a total of one million pages per year. Although this article was output to film at 1,270 dpi (dots per inch) by an imagesetter, reproduction on a 300-dpi laser printer or display would be marginally acceptable to most readers (at least for the text and some of the art). At 300 dpi, each page contains about six million pixels (picture elements). At a conservative compression ratio of 1O:l (using existing facsimile methods), this yields 80 gigabytes per year for the entire collection of periodicals. While this volume is well beyond the storage capabilities of individual workstations, it is acceptable for a library file server. (Of course, unformatted text requires only about 6 kilobytes per page even without compression, but it is not an acceptable vehicle for technical material.) A 10-page article can be transmitted over a high-speed network, and printed or displayed in image form in far less time than it takes to walk to a nearby library. Furthermore, while Computer may be available in most research libraries, you may have to wait several days for an interlibrary loan through facsimile or courier. There is, therefore, ample motivation to develop systems for the electronic distribution of digitized technical material. However, even if the material is available in digital image form, not everyone has convenient access to a high-speed line, a laser printer, or a 2,100 x 3,000-dot display. We show how intelligent document segmentation can bring electronic browsing within the reach of readers equipped with only a modem and a personal computer. Document analysis constitutes a domain of about the right degree of difficultj for current research on knowledge-based image-processing algorithms. This is important because document analysis itself is a transient application: There is no question that eventually information producers and consumers must be digitally linked. But there are also practical advantages to recognizing the location and extent of significant blocks of information on the page. This is also true for segmenting and 10

Comput. Sci. J. Moldova, 2020

The paper discusses problems of heterogeneous texts digitization. The archives of scanned printed documents grow dramatically by results of projects concerning cultural heritage preserving. Manual annotations of scanned document images and per page screen reading make the usage of these archives difficult and, sometimes, impossible. Existing document processing systems cannot automatically display content correctly due to the presence of heterogeneous content. We proposed a Web platform to maximize the support of semi-automated work of all used tools for recognition of heterogeneous documents. Maximizing support means both creating the convenient “single window” access to all tools, and reducing the manual part of the process as much as possible. For implementation, the convergent technology is used, which assembles complex software systems from ready-made heterogeneous modules on a single platform.

The 15 th International Scientific Conference eLearning and Software for Education, 2019

We live in the century of technology, where the enormous evolution of data and science has recently favored a strong interest in processing, transmitting, and storing information. If, in the past, only a human mind could extract meaningful information from image data, after decades of dedicated research, scientists have managed to build complex systems that can identify different areas, tables, and texts from scanned documents, all the obtained information being easily accessed and passed by one to another. Books, newspapers, maps, letters, drawings-all types of documents can be scanned and processed in order to become available in a digital format. In the digital world, the storage space is very small compared to physical documents, so these applications will replace millions of old paper volumes with a single memory disk and will be accessible at the same time for anyone using just Internet access and without having a risk of deterioration. Other problems, such as ecological issues, accessibility and flexibility constraints can be solved by the use of document image analysis systems. This article presents the methods and techniques used to process on-paper documents and convert them to electronic ones, starting from pixel level and getting to the level of the entire document. The main purpose of Document Image Analysis Systems is to recognize texts and graphical interpretations from images, extract, format and present their contained information accordingly to the people's needs. We will also try to provide solid ground for practitioners that implement systems from this category to enhance the unsupervised processing features in order to make physical documents easily available to the masses.

2007

Large quantities of historical newspapers are being digitized and OCRd. We describe a framework for processing the OCRd text to identify articles and extract metadata for them. We describe the article schema and provide examples of features that facilitate automatic indexing of them. For this processing, we employ lexical semantics, structural models, and community content. Furthermore, we describe visualization and summarization techniques that can be used to present the extracted events.

Document Analysis Systems VI, 2004

The 15 th International Scientific Conference eLearning and Software for Education, 2019

We live in the century of technology, where the enormous evolution of data and science has recently favored a strong interest in processing, transmitting, and storing information. If, in the past, only a human mind could extract meaningful information from image data, after decades of dedicated research, scientists have managed to build complex systems that can identify different areas, tables, and texts from scanned documents, all the obtained information being easily accessed and passed by one to another. Books, newspapers, maps, letters, drawings-all types of documents can be scanned and processed in order to become available in a digital format. In the digital world, the storage space is very small compared to physical documents, so these applications will replace millions of old paper volumes with a single memory disk and will be accessible at the same time for anyone using just Internet access and without having a risk of deterioration. Other problems, such as ecological issues, accessibility and flexibility constraints can be solved by the use of document image analysis systems. This article presents the methods and techniques used to process on-paper documents and convert them to electronic ones, starting from pixel level and getting to the level of the entire document. The main purpose of Document Image Analysis Systems is to recognize texts and graphical interpretations from images, extract, format and present their contained information accordingly to the people's needs. We will also try to provide solid ground for practitioners that implement systems from this category to enhance the unsupervised processing features in order to make physical documents easily available to the masses.

Spie Newsroom, 2011

1995

The conversion of documents into electronic form has proved more difficult than anticipated. Document image analysis still accounts for only a small fraction of the rapidly-expanding document imaging market. Nevertheless, the optimism manifested over the last thirty years has not dissipated. Driven partly by document distribution on CD-ROM and via the World Wide Web, there is more interest in the preservation of layout and format attributes to increase legibility (sometimes called "page reconstruction") rather than just text/non-text separation. The realization that accurate document image analysis requires fairly specific pre-stored information has resulted in the investigation of new data structures for knowledge bases and for the representation of the results of partial analysis. At the same time, the requirements of downstream software, such as word processing, information retrieval and computer-aided design applications, favor turning the results of the analysis and recognition into some standard format like SGML or DXF. There is increased emphasis on large-scale, automated comparative evaluation, using laboriously compiled test databases. The cost of generating these databases has stimulated new research on synthetic noise models. According to recent publications, the accurate conversion of business letters, technical reports, large typeset repositories like patents, postal addresses, specialized line drawings, and office forms containing a mix of handprinted, handwritten and printed material, is finally on the verge of success.

Journal of Computer Science and Technology, 2005

The handwritten manuscript recognizing process belongs to a set of initiatives which lean to the preservation of cultural patrimony gathered in libraries and archives, where there exist a great wealth in documents and even handwritten cards that accompany incunabula books. This work is the starting point of a research and development project oriented to digitalization and recognition of manuscript materials. The paper presented here discuss different algorithms used in the first stage dedicated to “image noise-cleaning” in order to improve it before the character recognition process begins. In order to make the handwritten-text recognition and image digitalization process efficient, it must be preceded by a preprocessing stage of the image to be treated, which includes thresholding, noise cleaning, thinning, base-line alignment and image segmentation, among others. Each of these steps will allow us to reduce the injurious variability when recognizing manuscripts (noise, random gray ...

2009

This paper present a new method to extract areas of interest in drop caps and particularly the most important shape: Letter itself. This method relies on a combination of a Aujol and Chambolle algorithm and a Segmentation using a Zipf Law and can be enhanced as a three-step process: 1)Decomposition in layers 2)Segmentation using a Zipf Law 3)Selection of the connected components.