Building Data Sets for Indian Language OCR Research

Jawahar, C. V.; Kumar, Anand; Phaneendra, A.; Jinesh, K. J.

doi:10.1007/978-1-84800-330-9_1

Cited by 5 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…APIs are provided for C/C++ to effectively use the annotated data with OCR's for training and evaluation. Annotation is done with the help of a specially designed tool [4]. The annotation schema is broadly classified into four categories based on the type of meta-information and annotation data to be stored.…”

Section: Content Level Annotation and Access:mentioning

confidence: 99%

“…In addition to the above image and text corpus, document image suited for various other tasks (like text-graphics separation) is also prepared with corresponding annotation. All meta details of the scanned documents are stored as in [4].…”

Section: Corpus Of Images and Text:mentioning

confidence: 99%

“…The effectiveness of algorithm depends largely on the data on which it is trained. Like in case of handwriting systems [1,2] effective use of XML for storage of data as demonstrated in [5,4] is chosen for storage of the annotation. It will make the semantic relationship between the components exploitable for developing user-friendly access modalities for these document images.…”

Section: Ground Truth Managementmentioning

confidence: 99%

“…Devising a representation mechanism for deployment of script specific OCR for all or part of the document page for conversion of a multilingual page to an electronic format in a multi-script multilingual environment. 4. Representation scheme for the final OCR'ed output so that it can be rendered electronically preserving the layout amenable for electronic editing, searching and browsing.…”

Section: Introductionmentioning

confidence: 99%

“…UPX format is based on W3C developed InkML [12]. For printed document analysis, XML has been used earlier for tasks such as representation of annotated data sets [5,4]. Specific problems related to developing and representing datasets for Indian language OCR research is addressed in [4].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Managing multilingual OCR project using XML

Harit

Jinesh

Garg

et al. 2009

Proceedings of the International Workshop on Multilingual OCR

View full text Add to dashboard Cite

This paper presents an XML-based scheme for managing a large multilingual OCR project. In particular we describe how a new XML based tagging scheme has been exploited to achieve the objectives of the project. Managing a large multi-lingual OCR project involving multiple research groups, developing script specific and script independent technologies in a collaborative fashion is a challenging problem. In this paper, we present some of the software and data management strategies designed for the project aimed at developing OCR for 11 scripts of Indian origin for which mature OCR technology was not available.

show abstract

Section: Content Level Annotation and Access:mentioning

confidence: 99%

Section: Corpus Of Images and Text:mentioning

confidence: 99%

Section: Ground Truth Managementmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Managing multilingual OCR project using XML

Harit

Jinesh

Garg

et al. 2009

Proceedings of the International Workshop on Multilingual OCR

View full text Add to dashboard Cite

show abstract

TAMIZHİ: Historical Tamil Brahmi Handwritten Dataset

Dhivya

Devi

2021

Sustainable Communication Networks and Application

View full text Add to dashboard Cite

Towards a Robust OCR System for Indic Scripts

Krishnan

Sankaran

Singh

et al. 2014

2014 11th IAPR International Workshop on Document Analysis Systems

Self Cite

View full text Add to dashboard Cite

Abstract-The current Optical Character Recognition (OCR) systems for Indic scripts are not robust enough for recognizing arbitrary collection of printed documents. Reasons for this limitation includes the lack of resources (e.g. not enough examples with natural variations, lack of documentation available about the possible font/style variations) and the architecture which necessitates hard segmentation of word images followed by an isolated symbol recognition. Variations among scripts, latent symbol to UNICODE conversion rules, non-standard fonts/styles and large degradations are some of the major reasons for the unavailability of robust solutions. In this paper, we propose a web based OCR system which (i) follows a unified architecture for seven Indian languages, (ii) is robust against popular degradations, (iii) follows a segmentation free approach, (iv) addresses the UNICODE re-ordering issues, and (v) can enable continuous learning with user inputs and feedbacks. Our system is designed to aid the continuous learning while being usable i.e., we capture the user inputs (say example images) for further improving the OCRs. We use the popular BLSTM based transcription scheme to achieve our target. This also enables incremental training and refinement in a seamless manner. We report superior accuracy rates in comparison with the available OCRs for the seven Indian languages.

show abstract

Building Data Sets for Indian Language OCR Research

Cited by 5 publications

References 8 publications

Managing multilingual OCR project using XML

Managing multilingual OCR project using XML

TAMIZHİ: Historical Tamil Brahmi Handwritten Dataset

Towards a Robust OCR System for Indic Scripts

Contact Info

Product

Resources

About