The IAM-database: an English sentence database for offline handwriting recognition

Marti, Urs-Viktor; Bunke, Horst

doi:10.1007/s100320200071

Cited by 1,180 publications

(560 citation statements)

References 14 publications

Supporting

Mentioning

550

Contrasting

Unclassified

Order By: Relevance

“…Similar percentages also apply for the number of lines. In terms of lexicons, it is worth noting that Spanish and, to a lesser extent, Catalan and Latin, have lexicons comparable in size to standard databases, such as IAM [13]. Also note that the sum of individual lexicon sizes (29.9K) is larger than the size of the global lexicon (27.1K).…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Character-Based Handwritten Text Recognition of Multilingual Documents

Agua

Serrano

Civera

et al. 2012

Advances in Speech and Language Technologies for Iberian Languages

View full text Add to dashboard Cite

Abstract. An effective approach to transcribe handwritten text documents is to follow a sequential interactive approach. During the supervision phase, user corrections are incorporated into the system through an ongoing retraining process. In the case of multilingual documents with a high percentage of out-of-vocabulary (OOV) words, two principal issues arise. On the one hand, a minor yet important matter for this interactive approach is to identify the language of the current text line image to be transcribed, as a language dependent recognisers typically performs better than a monolingual recogniser. On the other hand, word-based language models suffer from data scarcity in the presence of a large number of OOV words, degrading their estimation and affecting the performance of the transcription system. In this paper, we successfully tackle both issues deploying character-based language models combined with language identification techniques on an entire 764-page multilingual document. The results obtained significantly reduce previously reported results in terms of transcription error on the same task, but showed that a language dependent approach is not effective on top of character-based recognition of similar languages.

show abstract

Section: Methodsmentioning

confidence: 99%

“…However, character-based language models were not superior to their word-based counterparts. A hybrid approach between a standard character-based n-gram language model and a character-based connectionist language model is proposed in [12], which obtain similar results to word-based systems on the IAM corpus [13].…”

Section: Previous Workmentioning

confidence: 99%

Character-Based Handwritten Text Recognition of Multilingual Documents

Agua

Serrano

Civera

et al. 2012

Advances in Speech and Language Technologies for Iberian Languages

View full text Add to dashboard Cite

show abstract

“…Datasets: We evaluate our method in two public datasets of handwritten text documents: the IAM off-line database 2 [19] and the George Washington (GW) database 3 [22]. The IAM is a large database comprised of 1, 539 pages of modern handwritten English text written by 657 different writers.…”

Section: Methodsmentioning

confidence: 99%

Handwritten Word Spotting with Corrected Attributes

Almazán

Gordo

Fornés

et al. 2013

2013 IEEE International Conference on Computer Vision

View full text Add to dashboard Cite

We propose an approach to multi-writer word spotting, where the goal is to find a query word in a dataset comprised of document images. We propose an attributes-based approach that leads to a low-dimensional, fixed-length representation of the word images that is fast to compute and, especially, fast to compare. This approach naturally leads to an unified representation of word images and strings, which seamlessly allows one to indistinctly perform queryby-example, where the query is an image, and query-bystring, where the query is a string. We also propose a calibration scheme to correct the attributes scores based on Canonical Correlation Analysis that greatly improves the results on a challenging dataset. We test our approach on two public datasets showing state-of-the-art results.

show abstract

“…Middle-zone component modelling using HMM: The middle-zone word components from source script are considered for HMM [21] training. Except cursive and touching behavior of handwriting, another major reason behind choosing HMM is that it can model sequential dependencies.…”

Section: Character Modeling Using Source Scriptsmentioning

confidence: 99%

“…Researchers have created numerous public datasets in different scripts for developing tasks, such as, word recognition, word retrieval, etc. [21,24,25].…”

Section: Introductionmentioning

confidence: 99%

Cross-language framework for word recognition and spotting of Indic scripts

Bhunia

Roy

Mohta

et al. 2018

Pattern Recognition

View full text Add to dashboard Cite

Handwritten word recognition and spotting of low-resource scripts are difficult as sufficient training data is not available and it is often expensive for collecting data of such scripts. This paper presents a novel cross language platform for handwritten word recognition and spotting for such low-resource scripts where training is performed with a sufficiently large dataset of an available script (considered as source script) and testing is done on other scripts (considered as target script). Training with one source script and testing with another script to have a reasonable result is not easy in handwriting domain due to the complex nature of handwriting variability among scripts. Also it is difficult in mapping between source and target characters when they appear in cursive word images. The proposed Indic cross language framework exploits a large resource of dataset for training and uses it for recognizing and spotting text of other target scripts where sufficient amount of training data is not available. Since, Indic scripts are mostly written in 3 zones, namely, upper, middle and lower, we employ zone-wise character (or component) mapping for efficient learning purpose. The performance of our crosslanguage framework depends on the extent of similarity between the source and target scripts. Hence, we devise an entropy based script similarity score using source to target character mapping that will provide a feasibility of cross language transcription. We have tested our approach in three Indic scripts, namely, Bangla, Devanagari and Gurumukhi, and the corresponding results are reported.

show abstract

The IAM-database: an English sentence database for offline handwriting recognition

Cited by 1,180 publications

References 14 publications

Character-Based Handwritten Text Recognition of Multilingual Documents

Character-Based Handwritten Text Recognition of Multilingual Documents

Handwritten Word Spotting with Corrected Attributes

Cross-language framework for word recognition and spotting of Indic scripts

Contact Info

Product

Resources

About