@inproceedings{nakarmi-etal-2024-nepal,
title = "{N}epal Script Text Recognition Using {CRNN} {CTC} Architecture",
author = "Nakarmi, Swornim and
Sthapit, Sarin and
Shakya, Arya and
Chulyadyo, Rajani and
Bal, Bal Krishna",
editor = "Melero, Maite and
Sakti, Sakriani and
Soria, Claudia",
booktitle = "Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.sigul-1.29",
pages = "244--251",
abstract = "Nepal Script (also known as Prachalit Script) is the widely used script of Nepal Bhasa, the native language of the Kathmandu Valley in Nepal. Derived from the Brahmi Script, the Nepal Script was developed in the 9th century and was extensively used till the 20th century, before being replaced by the Devanagari script. Numerous ancient manuscripts, inscriptions, and documents written in the Nepal Script are still available containing immense knowledge on architecture, arts, astrology, ayurveda, literature, music, tantrism, etc. To preserve and revive Nepal Bhasa, digitizing such documents plays a crucial role. This paper presents our work on text recognition for the Nepal Script. The implementation includes the Nepal Script text recognizer based on CRNN CTC architecture aided by line and word segmentations. Leveraging a carefully curated dataset that encompasses handwritten and printed texts in the Nepal Script, our work has achieved CER of 6.65{\%} and WER of 13.11{\%}. The dataset used for this work is available as Nepal Script Text Dataset on Kaggle. The paper further explores the associated challenges due to the complex nature of the script such as conjuncts, modifiers and variations; and the current state of the script.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nakarmi-etal-2024-nepal">
<titleInfo>
<title>Nepal Script Text Recognition Using CRNN CTC Architecture</title>
</titleInfo>
<name type="personal">
<namePart type="given">Swornim</namePart>
<namePart type="family">Nakarmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarin</namePart>
<namePart type="family">Sthapit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arya</namePart>
<namePart type="family">Shakya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajani</namePart>
<namePart type="family">Chulyadyo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bal</namePart>
<namePart type="given">Krishna</namePart>
<namePart type="family">Bal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maite</namePart>
<namePart type="family">Melero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Soria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Nepal Script (also known as Prachalit Script) is the widely used script of Nepal Bhasa, the native language of the Kathmandu Valley in Nepal. Derived from the Brahmi Script, the Nepal Script was developed in the 9th century and was extensively used till the 20th century, before being replaced by the Devanagari script. Numerous ancient manuscripts, inscriptions, and documents written in the Nepal Script are still available containing immense knowledge on architecture, arts, astrology, ayurveda, literature, music, tantrism, etc. To preserve and revive Nepal Bhasa, digitizing such documents plays a crucial role. This paper presents our work on text recognition for the Nepal Script. The implementation includes the Nepal Script text recognizer based on CRNN CTC architecture aided by line and word segmentations. Leveraging a carefully curated dataset that encompasses handwritten and printed texts in the Nepal Script, our work has achieved CER of 6.65% and WER of 13.11%. The dataset used for this work is available as Nepal Script Text Dataset on Kaggle. The paper further explores the associated challenges due to the complex nature of the script such as conjuncts, modifiers and variations; and the current state of the script.</abstract>
<identifier type="citekey">nakarmi-etal-2024-nepal</identifier>
<location>
<url>https://aclanthology.org/2024.sigul-1.29</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>244</start>
<end>251</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Nepal Script Text Recognition Using CRNN CTC Architecture
%A Nakarmi, Swornim
%A Sthapit, Sarin
%A Shakya, Arya
%A Chulyadyo, Rajani
%A Bal, Bal Krishna
%Y Melero, Maite
%Y Sakti, Sakriani
%Y Soria, Claudia
%S Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F nakarmi-etal-2024-nepal
%X Nepal Script (also known as Prachalit Script) is the widely used script of Nepal Bhasa, the native language of the Kathmandu Valley in Nepal. Derived from the Brahmi Script, the Nepal Script was developed in the 9th century and was extensively used till the 20th century, before being replaced by the Devanagari script. Numerous ancient manuscripts, inscriptions, and documents written in the Nepal Script are still available containing immense knowledge on architecture, arts, astrology, ayurveda, literature, music, tantrism, etc. To preserve and revive Nepal Bhasa, digitizing such documents plays a crucial role. This paper presents our work on text recognition for the Nepal Script. The implementation includes the Nepal Script text recognizer based on CRNN CTC architecture aided by line and word segmentations. Leveraging a carefully curated dataset that encompasses handwritten and printed texts in the Nepal Script, our work has achieved CER of 6.65% and WER of 13.11%. The dataset used for this work is available as Nepal Script Text Dataset on Kaggle. The paper further explores the associated challenges due to the complex nature of the script such as conjuncts, modifiers and variations; and the current state of the script.
%U https://aclanthology.org/2024.sigul-1.29
%P 244-251
Markdown (Informal)
[Nepal Script Text Recognition Using CRNN CTC Architecture](https://aclanthology.org/2024.sigul-1.29) (Nakarmi et al., SIGUL-WS 2024)
ACL
- Swornim Nakarmi, Sarin Sthapit, Arya Shakya, Rajani Chulyadyo, and Bal Krishna Bal. 2024. Nepal Script Text Recognition Using CRNN CTC Architecture. In Proceedings of the 3rd Annual Meeting of the Special Interest Group on Under-resourced Languages @ LREC-COLING 2024, pages 244–251, Torino, Italia. ELRA and ICCL.