Introduction to Document Analysis and Recognition

Marinai, Simone

doi:10.1007/978-3-540-76280-5_1

Cited by 54 publications

(39 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Unfortunately, publicly available data sets for document type classification (Marinai, 2008) do not resemble the type of administrative documents that we work with. Therefore we use a data set of real life dossiers acquired from a Dutch anonymous company that provides consumer loans.…”

Section: Datasetmentioning

confidence: 99%

“…Automatic document analysis is the field that deals with the different steps in the document processing pipeline, from the incoming documents to document specific treatment. A mayor part of this field focuses on digital image analysis (Marinai, 2008). Here we focus on the problems occurring at the start of the document processing pipeline and instead of doing image analysis, we concentrate on textual content analysis of OCR-ed versions of the scanned documents.…”

Section: Introductionmentioning

confidence: 99%

“…We refer to Marinai (2008) for a general overview and introduction on document analysis and recognition.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

PaperClip: Automated Dossier Reorganizing

Stoop¹,

Hendrickx

Ees³

2017

Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

Abstract:We investigate the creation of a robust algorithm for document identification and page ordering in a digital mail room in the banking sector. PaperClip is a system that takes dossiers containing pages of various documents as input, and returns multiple files that contain all the pages of one document in the correct order. PaperClip performs (1) document type classification and (2) page number classification on each page, and then (3) merges the results. We experimented with various algorithms and methods for these three steps and we performed an elaborate evaluation to measure different aspects of the methods. The best performing setup achieved a cut F-score of 86% and a V-measure of 0.91%. This performance is sufficient to fulfill business needs of the banking sector.

show abstract

Section: Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

PaperClip: Automated Dossier Reorganizing

Stoop¹,

Hendrickx

Ees³

2017

Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods

View full text Add to dashboard Cite

show abstract

“…In successful DIA systems, the size of the training sets used to develop and tune the system is necessarily far smaller than the volume of data processed over the lifetime of the system. We should apply learning algorithms that use routine feedback from the operator to improve classification [30,31]. Furthermore, reduction of the cost of storage has led to the maintenance of complete records -even of systems as large as the whole web.…”

Section: Green Interactionmentioning

confidence: 99%

Asymptotic cost in document conversion

Blostein

Nagy

2012

SPIE Proceedings

View full text Add to dashboard Cite

In spite of a hundredfold decrease in the cost of relevant technologies, the role of document image processing systems is gradually declining due to the transition to an on-line world. Nevertheless, in some high-volume applications, document image processing software still saves millions of dollars by accelerating workflow, and similarly large savings could be realized by more effective automation of the multitude of low-volume personal document conversions. While potential cost savings, based on estimates of costs and values, are a driving force for new developments, quantifying such savings is difficult. The most important trend is that the cost of computing resources for DIA is becoming insignificant compared to the associated labor costs. An econometric treatment of document processing complements traditional performance evaluation, which focuses on assessing the correctness of the results produced by document conversion software. Researchers should look beyond the error rate for advancing both production and personal document conversion.

show abstract

“…Research on Devanagari [1] character [2][3][4][5][6][7][8][9][10] and word [11][12][13] recognition is very difficult due to its challenging properties. This area of research is still open for further research due to the extent of variation among writing styles, speed, thickness of character and direction of different writers.…”

Section: Introductionmentioning

confidence: 99%

Parallel Implementation of Devanagari Text Line and Word Segmentation Approach on GPU

Singh¹,

Gupta²,

Tyagi³

2011

IJCA

View full text Add to dashboard Cite

Fast and accurate algorithms are necessary for Optical Character Recognition (OCR) systems to perform operations on document images such as pre-processing, segmentation, feature extraction, training and testing of classifiers and post processing. Text line and word segmentation are two important steps in any OCR system. Wrong segmentation may affect the accuracy rate of OCR systems. The segmentation is very challenging in cases of availability of different types of noises, degradations, and variation in writing and script characteristics. However, existing algorithms suffer from a flawed tradeoff between accuracy and speed. In this research work, Devanagri text line and word segmentation are carried out using modified standard profiling based segmentation approach and parallelized it on Graphics Processing Unit (GPU). The main goal of this research work is to make segmentation faster for processing a large number of document images using parallel implementation of algorithms on GPU. GPUs are emerging as powerful parallel systems at a cheaper cost. Our work employs extensive usage of highly multithreaded architecture and shared memory of multi-cored GPU. An efficient use of shared memory is required to optimize parallel reduction in Compute Unified Device Architecture (CUDA). Experimental results show that our method can achieve a speedup of about 20x-30x over the serial implementation when running on a GPU named GeForce 9500 GT having 32 cores.

show abstract

Introduction to Document Analysis and Recognition

Cited by 54 publications

References 24 publications

PaperClip: Automated Dossier Reorganizing

PaperClip: Automated Dossier Reorganizing

Asymptotic cost in document conversion

Parallel Implementation of Devanagari Text Line and Word Segmentation Approach on GPU

Contact Info

Product

Resources

About