Digital mountain:from granite archive to global access

Barrett, William A.; Hutchison, Luke A. D.; Quass, Dallan; Nielson, Heath; Kennard, Douglas J.

doi:10.1109/dial.2004.1263243

Cited by 6 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Much of the previous work in form processing assumes the availability of templates for form types of interest [4], [5], [6]. This assumption has been relaxed in later work [7], [8].…”

Section: B Form Processingmentioning

confidence: 99%

Deep Visual Template-Free Form Parsing

Davis

Morse

Cohen

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

Automatic, template-free extraction of information from form images is challenging due to the variety of form layouts. This is even more challenging for historical forms due to noise and degradation. A crucial part of the extraction process is associating input text with pre-printed labels. We present a learned, template-free solution to detecting preprinted text and input text/handwriting and predicting pairwise relationships between them. While previous approaches to this problem have been focused on clean images and clear layouts, we show our approach is effective in the domain of noisy, degraded, and varied form images. We introduce a new dataset of historical form images (late 1800s, early 1900s) for training and validating our approach. Our method uses a convolutional network to detect pre-printed text and input text lines. We pool features from the detection network to classify possible relationships in a language-agnostic way. We show that our proposed pairing method outperforms heuristic rules and that visual features are critical to obtaining high accuracy.

show abstract

“…Much of the previous work in form processing assumes the availability of templates for form types of interest [4], [5], [6]. This assumption has been relaxed in later work [7], [8].…”

Section: B Form Processingmentioning

confidence: 99%

Deep Visual Template-Free Form Parsing

Davis

Morse

Cohen

et al. 2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

show abstract

“…Continuous scanning is followed by automatic frame cropping as an efficient and fast procedure to generate images from microfilm [9]. Fourier-Mellin transform is used to correct rotation/shear, scale and translation errors [28].…”

Section: Dia Challenges In Historical DL Collectionsmentioning

confidence: 99%

“…Layout analysis and metadata extraction is a crucial step in creating an information base for historical DL's. Even as researchers are gaining ground on complete recognition of text content from historical documents (Subsection 2.2), practical systems have been built using only the layout analysis stage of DIA [9,26,35]. Availability of images makes it possible to provide content based image retrieval, using even structural features like color and layout.…”

Section: Dia Challenges In Historical DL Collectionsmentioning

confidence: 99%

Document Analysis Systems for Digital Libraries: Challenges and Opportunities

Baird

Govindaraju

Lopresti

2004

Document Analysis Systems VI

View full text Add to dashboard Cite

Abstract. Implications of technical demands made within digital libraries (DL's) for document image analysis systems are discussed. The state-of-the-art is summarized, including a digest of themes that emerged during the recent International Workshop on Document Image Analysis for Libraries. We attempt to specify, in considerable detail, the essential features of document analysis systems that can assist in: (a) the creation of DL's; (b) automatic indexing and retrieval of doc-images within DL's; (c) the presentation of doc-images to DL users; (d) navigation within and among doc-images in DL's; and (e) effective use of personal and interactive DL's.

show abstract

“…On the other end of the spectrum, relatively modern printed documents do not suffer from significant substrate/ink degradation problems and lend themselves to a higher degree of automated processing, OCR (albeit not trivial) and more sophisticated content extraction and indexing [4]. Finally, there are specific applications such as the conversion of administrative documents, which are typically forms with fixed structure [1].…”

Section: Introductionmentioning

confidence: 99%

A Complete Approach to the Conversion of Typewritten Historical Documents for Digital Archives

Antonacopoulos

Karatzas

2004

Document Analysis Systems VI

View full text Add to dashboard Cite

Abstract. This paper presents a complete system that historians/archivists can use to digitize whole collections of documents relating to personal information. The system integrates tools and processes that facilitate scanning, image indexing, document (physical and logical) structure definition, document image analysis, recognition, proofreading/correction and semantic tagging. The system is described in the context of different types of typewritten documents relating to prisoners in World-War II concentration camps and is the result of a multinational collaboration under the MEMORIAL project funded (¼1.5M) by the European Union (www.memorial-project.info). Results on a representative selection of documents show a significant improvement not only in terms of OCR accuracy but also in terms of overall time/cost involved in converting these documents for digital archives.

show abstract

Digital mountain:from granite archive to global access

Cited by 6 publications

References 21 publications

Deep Visual Template-Free Form Parsing

Deep Visual Template-Free Form Parsing

Document Analysis Systems for Digital Libraries: Challenges and Opportunities

A Complete Approach to the Conversion of Typewritten Historical Documents for Digital Archives

Contact Info

Product

Resources

About