@inproceedings{moumita-sujan-kumar-2023-handwritten,
title = "Handwritten Text Segmentation Using {U}-Net and Shuffled Frog-Leaping Algorithm with Scale Space Technique",
author = "Moumita, Moitra and
Sujan Kumar, Saha",
editor = "Jyoti, D. Pawar and
Sobha, Lalitha Devi",
booktitle = "Proceedings of the 20th International Conference on Natural Language Processing (ICON)",
month = dec,
year = "2023",
address = "Goa University, Goa, India",
publisher = "NLP Association of India (NLPAI)",
url = "https://aclanthology.org/2023.icon-1.73",
pages = "729--737",
abstract = "The paper introduces a new method for segmenting words from handwritten Bangla documents. We found that the available handwritten character recognition (HCR) systems do not provide the desired accuracy in recognizing the text written by school students. Recognizing students{'} handwritten text becomes challenging due to certain factors, including a non-uniform gap between lines and words, and ambiguous, overlapping characters. The performance may be improved if the words in the text are segmented correctly before recognition. For the segmentation, we propose a combination of U-Net and a modified Scale Space method enhanced by the Shuffled Frog-Leaping Algorithm (SFLA). We employ the U-Net model for line segmentation; it effectively handles the variable spacing and skewed lines. After line segmentation, for segmenting the words, we use SFLA with Scale Space, allowing adaptive scaling and optimized parameter tuning. The proposed technique has been tested on two datasets: the openly available BN-HTR dataset and an in-house dataset prepared by collecting Bengali handwritten answer books from schools. In our experiments, we found that the proposed technique achieved promising performance on both datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="moumita-sujan-kumar-2023-handwritten">
<titleInfo>
<title>Handwritten Text Segmentation Using U-Net and Shuffled Frog-Leaping Algorithm with Scale Space Technique</title>
</titleInfo>
<name type="personal">
<namePart type="given">Moitra</namePart>
<namePart type="family">Moumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saha</namePart>
<namePart type="family">Sujan Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Natural Language Processing (ICON)</title>
</titleInfo>
<name type="personal">
<namePart type="given">D</namePart>
<namePart type="given">Pawar</namePart>
<namePart type="family">Jyoti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lalitha</namePart>
<namePart type="given">Devi</namePart>
<namePart type="family">Sobha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>NLP Association of India (NLPAI)</publisher>
<place>
<placeTerm type="text">Goa University, Goa, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper introduces a new method for segmenting words from handwritten Bangla documents. We found that the available handwritten character recognition (HCR) systems do not provide the desired accuracy in recognizing the text written by school students. Recognizing students’ handwritten text becomes challenging due to certain factors, including a non-uniform gap between lines and words, and ambiguous, overlapping characters. The performance may be improved if the words in the text are segmented correctly before recognition. For the segmentation, we propose a combination of U-Net and a modified Scale Space method enhanced by the Shuffled Frog-Leaping Algorithm (SFLA). We employ the U-Net model for line segmentation; it effectively handles the variable spacing and skewed lines. After line segmentation, for segmenting the words, we use SFLA with Scale Space, allowing adaptive scaling and optimized parameter tuning. The proposed technique has been tested on two datasets: the openly available BN-HTR dataset and an in-house dataset prepared by collecting Bengali handwritten answer books from schools. In our experiments, we found that the proposed technique achieved promising performance on both datasets.</abstract>
<identifier type="citekey">moumita-sujan-kumar-2023-handwritten</identifier>
<location>
<url>https://aclanthology.org/2023.icon-1.73</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>729</start>
<end>737</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Handwritten Text Segmentation Using U-Net and Shuffled Frog-Leaping Algorithm with Scale Space Technique
%A Moumita, Moitra
%A Sujan Kumar, Saha
%Y Jyoti, D. Pawar
%Y Sobha, Lalitha Devi
%S Proceedings of the 20th International Conference on Natural Language Processing (ICON)
%D 2023
%8 December
%I NLP Association of India (NLPAI)
%C Goa University, Goa, India
%F moumita-sujan-kumar-2023-handwritten
%X The paper introduces a new method for segmenting words from handwritten Bangla documents. We found that the available handwritten character recognition (HCR) systems do not provide the desired accuracy in recognizing the text written by school students. Recognizing students’ handwritten text becomes challenging due to certain factors, including a non-uniform gap between lines and words, and ambiguous, overlapping characters. The performance may be improved if the words in the text are segmented correctly before recognition. For the segmentation, we propose a combination of U-Net and a modified Scale Space method enhanced by the Shuffled Frog-Leaping Algorithm (SFLA). We employ the U-Net model for line segmentation; it effectively handles the variable spacing and skewed lines. After line segmentation, for segmenting the words, we use SFLA with Scale Space, allowing adaptive scaling and optimized parameter tuning. The proposed technique has been tested on two datasets: the openly available BN-HTR dataset and an in-house dataset prepared by collecting Bengali handwritten answer books from schools. In our experiments, we found that the proposed technique achieved promising performance on both datasets.
%U https://aclanthology.org/2023.icon-1.73
%P 729-737
Markdown (Informal)
[Handwritten Text Segmentation Using U-Net and Shuffled Frog-Leaping Algorithm with Scale Space Technique](https://aclanthology.org/2023.icon-1.73) (Moumita & Sujan Kumar, ICON 2023)
ACL