A Line-Oriented Approach to Word Spotting in Handwritten Documents

Kołcz, Aleksander; Alspector, Joshua; Augusteijn, Marijke F.; Carlson, Robert; Popescu, George V.

doi:10.1007/s100440070020

Cited by 84 publications

(50 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Kolcz et al [4] used a line-oriented search strategy, where each document page was treated as a sequence of lines of text and each line was represented by a sequence of pixel columns. Matching was performed on profile-oriented features using DTW.…”

Section: Related Workmentioning

confidence: 99%

“…that combining different features yields better results [13], [2], [4], [11]. We have to define how to use the DTW on a feature combination.…”

Section: Feature Combinationsmentioning

confidence: 99%

“…Inspecting Figure 6 it is clear that the best cost function is (3). 3 To study which feature combination best suits Hebrew square letters, we run the DTW with a combination of the 3 Notice the significant gap between the performances of DTW that uses Euclidean distance (3) and DTW that uses squared Euclidean distance (4). The latter performs worse.…”

Section: Feature Combinationsmentioning

confidence: 99%

See 2 more Smart Citations

Case Study in Hebrew Character Searching

Rabaev

Biller

El-Sana

et al. 2011

2011 International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

Abstract-Searching for a letter or a word in historical documents is a practical challenge due to the various degradations present in such documents and the wide variance of handwriting. Searching in historical Hebrew documents is somewhat harder because of high similarities among Hebrew characters. In order to determine the features and their combinations appropriate for recognizing Hebrew script, we study a range of known features using a Dynamic Time Warping algorithm. In addition we describe a novel method for feature-based searching, which uses a number of models for the same character. This method is based on our original DTW algorithm that can match fragments of several models of the same character to match a query character. Consequently, we are not limited to any particular model of the character set. Application of this method leads to a significant improvement, even when using a small set of models.

show abstract

Section: Related Workmentioning

confidence: 99%

“…that combining different features yields better results [13], [2], [4], [11]. We have to define how to use the DTW on a feature combination.…”

Section: Feature Combinationsmentioning

confidence: 99%

Section: Feature Combinationsmentioning

confidence: 99%

See 1 more Smart Citation

Case Study in Hebrew Character Searching

Rabaev

Biller

El-Sana

et al. 2011

2011 International Conference on Document Analysis and Recognition

View full text Add to dashboard Cite

show abstract

“…When dealing with documents, such as those addressed in this paper, where the word segmentation is difficult or even impossible, techniques that search a query word in whole text-lines are required. In [30], the text-lines of historical handwritten documents are represented as ordered sequences of pixel columns. Each column is described with three features based on upper and lower profiles and on the number of black-white transitions.…”

Section: Previous Workmentioning

confidence: 99%

Text retrieval from early printed books

Marinai

2011

IJDAR

View full text Add to dashboard Cite

Retrieving text from early printed books is particularly difficult because in these documents, the words are very close one to the other and, similarly to medieval manuscripts, there is a large use of ligatures and abbreviations.To address these problems, we propose a word indexing and retrieval technique that does not require word segmentation and is tolerant to errors in character segmentation. Two main principles characterize the approach. First, characters are identified in the pages and clustered with self-organizing map (SOM). During the retrieval, the similarity of characters is estimated considering the proximity of cluster centroids in the SOM space, rather than directly comparing the character images. Second, query words are matched with the indexed sequence of characters by means of a dynamic time warping (DTW)-based approach. The proposed technique integrates the SOM similarity and the information about the width of characters in the string matching process. The best path in the DTW array is identified considering the widths of matching words with respect to the query so as to deal with broken or touching symbols. The proposed method is tested on four copies of the Gutenberg Bibles.

show abstract

“…This work focuses on the case where queries are presented to the system as strings typed by the user (known as Query-by-String) [21,4,6,29,1,26,12,16,17,25], although an alternative formulation of KWS, where queries are presented as example images (known as Query-by-Example) is also very popular in the literature [10,19,11,7,22,5,3,27]. Query-by-Example approaches are typically training-free and are based on template (image) matching between the query (example image) and word-sized image regions of the documents.…”

Section: Introductionmentioning

confidence: 99%

Querying out-of-vocabulary words in lexicon-based keyword spotting

Puigcerver

Toselli

Vidal

2016

Neural Comput & Applic

View full text Add to dashboard Cite

Puigcerver, J.; Toselli, AH.; Vidal, E. (2016). Querying out-of-vocabulary words in lexiconbased keyword spotting. Neural Computing and Applications. 1-10. doi:10.1007/s00521-016-2197-8. Abstract Lexicon-based handwritten text keyword spotting (KWS) has proven to be a faster and more accurate alternative to lexicon-free methods. Nevertheless, since lexicon-based KWS relies on a predefined vocabulary, fixed in the training phase, it does not support queries involving out-of-vocabulary (OOV) keywords. In this paper, we outline previous work aimed at solving this problem and present a new approach based on smoothing the (null) scores of OOV keywords by means of the information provided by "similar" in-vocabulary words. Good results achieved using this approach are compared with previously published alternatives on different data sets.

show abstract

A Line-Oriented Approach to Word Spotting in Handwritten Documents

Cited by 84 publications

References 24 publications

Case Study in Hebrew Character Searching

Case Study in Hebrew Character Searching

Text retrieval from early printed books

Querying out-of-vocabulary words in lexicon-based keyword spotting

Contact Info

Product

Resources

About