A word spotting framework for historical machine-printed documents

Kesidis, Anastasios L.; Galiotou, Eleni; Gatos, Basilis; Pratikakis, Ioannis

doi:10.1007/s10032-010-0134-4

Cited by 32 publications

(15 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A. L. Kesidis et.al [1] proposed word spotting structure for accessing the content of historical machine-printed documents, without the use of an optical character recognition. The proposed methodology has evaluated the historical Modern Greek printed documents which was available during the seventeenth and eighteenth century.…”

Section: Related Workmentioning

confidence: 99%

Content Based Text Information Search and Retrieval in Document Images for Digital Library

Sakila¹,

Vijayarani²

2018

jdim

View full text Add to dashboard Cite

Section: Related Workmentioning

confidence: 99%

Content Based Text Information Search and Retrieval in Document Images for Digital Library

Sakila¹,

Vijayarani²

2018

jdim

View full text Add to dashboard Cite

“…Due to its effectiveness, word spotting has been largely used for historical document indexing and retrieval, not only for old printed documents 28 , but also for old handwritten ones 7,17,22,23,30,33 .…”

Section: Related Workmentioning

confidence: 99%

“…This set of features showed better performance than the raw pixels as input features used in their previous work 27 . In a similar way, other approaches also use information about profiles: the QBS approach proposed by Kesidis et al 17 for machine-printed documents compute 90 features based on zoning plus 60 features based on upper and lower profiles. Frinken et al 7,8 proposed a word spotting approach based on neural networks, which use the set of features proposed by Marti and Bunke 29 .…”

Section: Related Workmentioning

confidence: 99%

On the Influence of Word Representations for Handwritten Word Spotting in Historical Documents

Lladós

Rusiñol

Fornés

et al. 2012

Int. J. Patt. Recogn. Artif. Intell.

View full text Add to dashboard Cite

Word spotting is the process of retrieving all instances of a queried keyword from a digital library of document images. In this paper we evaluate the performance of different word descriptors to assess the advantages and disadvantages of statistical and structural models in a framework of query-by-example word spotting in historical documents. We compare four word representation models, namely sequence alignment using DTW as a baseline reference, a bag of visual words approach as statistical model, a pseudo-structural model based on a Loci features representation, and a structural approach where words are represented by graphs. The four approaches have been tested with two collections of historical data: the George Washington database and the marriage records from the Barcelona Cathedral. We experimentally demonstrate that statistical representations generally give a better performance, however it cannot be neglected that large descriptors are difficult to be implemented in a retrieval scenario where word spotting requires the indexation of data with million word images.

show abstract

“…Manmatha et al computed similarity with a dynamic time warping (DTW) technique [13]- [17]. Konidaris et al proposed a technique of keyword spotting in Christian manuscripts [18], [19]. Their aim was to search for typed keywords in a large collection of digitized historical printed documents in which the retrieval result was optimized by user feedback.…”

Section: Introductionmentioning

confidence: 99%

Digital Ink Search Based on Character-Recognition Candidates Compared with Feature-Matching-Based Approach

Cheng

Zhu

Nakagawa

2013

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYThis paper presents an approach based on character recognition to searching for keywords in on-line handwritten Japanese text. It employs an on-line character classifier and an off-line classifier or a combined classifier, which produce recognition candidates, and it searches for keywords in the lattice of candidates. It integrates scores to individually recognize characters and their geometric context. We use quadratic discriminant function(QDF) or support vector machines(SVM) models to evaluate the geometric features of individual characters and the relationships between characters. This paper also presents an approach based on feature matching that employs on-line or off-line features. We evaluate three recognition-based methods, two feature-matching-based methods, as well as ideal cases of the latter and concluded that the approach based on character recognition outperformed that based on feature matching.

show abstract

A word spotting framework for historical machine-printed documents

Cited by 32 publications

References 15 publications

Content Based Text Information Search and Retrieval in Document Images for Digital Library

Content Based Text Information Search and Retrieval in Document Images for Digital Library

On the Influence of Word Representations for Handwritten Word Spotting in Historical Documents

Digital Ink Search Based on Character-Recognition Candidates Compared with Feature-Matching-Based Approach

Contact Info

Product

Resources

About