Optimized Text Extraction and E-Repository Development of Hindi and Punjabi Documents Using OCR and NLP Techniques

[{“box”:0,”content”:”n[if 992 equals=”Open Access”]n

n

n

n

Open Access

nn

n

n[/if 992]n[if 2704 equals=”Yes”]n

n

Notice

nThis is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.n

n[/if 2704]n

n

Year : 2025 [if 2224 equals=””]12/09/2025 at 4:47 PM[/if 2224] | [if 1553 equals=””] Volume : 12 [else] Volume : 12[/if 1553] | [if 424 equals=”Regular Issue”]Issue : [/if 424][if 424 equals=”Special Issue”]Special Issue[/if 424] [if 424 equals=”Conference”][/if 424] 03 | Page : 35 43

n

n

nn

n

n

n

    By

    n

    [foreach 286]n

    n

    Jitesh Pubreja, Vishal Goyal, Rajeev Puri,

    n t

  • n

    n[/foreach]

    n

n[if 2099 not_equal=”Yes”]n

    [foreach 286] [if 1175 not_equal=””]n t

  1. Student, Professor, Associate Professor, Department of Computer Science, Punjabi University, Patiala, Department of Computer Science, Punjabi University, Patiala, Department of Computer Science, DAV College, Jalandhar, Punjab, Punjab, Punjab, India, India, India

    2. n[/if 1175][/foreach]

n[/if 2099][if 2099 equals=”Yes”][/if 2099]n

n

Abstract

n

n

nIncrease in digitalization of content in the form of text content necessitates powerful document and text extraction systems, particularly for Indian languages such as Hindi and Punjabi. The existing Optical Character Recognition (OCR) solutions support major scripts such as English, leaving a research opportunity for effective recognition of Devanagari and Gurmukhi scripts. This study recommends a modified text extraction algorithm based on Tesseract OCR, accompanied by preprocessing steps of conversion of input images to grayscale, reduction of noise, and adjustment of skew for improved output. The post-processing chain of spell correction, Named Entity Recognition (NER), and normalization of diacritical signs was proposed for fine-grain processing of extracted content. An e-repository based on a schema-based database and Elasticsearch-powered full-text search functionality was developed for convenient document storage, indexing, and document retrieval. The system was compared on parameters of OCR recognition, Word Error Rate (WER), Character Error Rate (CER), document retrieval time, search results, and scalability. The proposed system reached an OCR recognition of 92.5%, minimal error levels of WER of 7.5% and CER of 4.2%, and time of document retrievals of 186 ms. The result establishes the success of the proposed system in document and text content extraction and processing, which is a scalable solution for language studies, archive purposes, and reference material management.nn

n

n

n

Keywords: OCR, NLP, text, NER, Gurmukhi, Hindi

n[if 424 equals=”Regular Issue”][This article belongs to Journal of Web Engineering & Technology ]

n

[/if 424][if 424 equals=”Special Issue”][This article belongs to Special Issue under section in Journal of Web Engineering & Technology (jowet)][/if 424][if 424 equals=”Conference”]This article belongs to Conference [/if 424]

n

n

n

How to cite this article:
nJitesh Pubreja, Vishal Goyal, Rajeev Puri. [if 2584 equals=”][226 wpautop=0 striphtml=1][else]Optimized Text Extraction and E-Repository Development of Hindi and Punjabi Documents Using OCR and NLP Techniques[/if 2584]. Journal of Web Engineering & Technology. 12/09/2025; 12(03):35-43.

n

How to cite this URL:
nJitesh Pubreja, Vishal Goyal, Rajeev Puri. [if 2584 equals=”][226 striphtml=1][else]Optimized Text Extraction and E-Repository Development of Hindi and Punjabi Documents Using OCR and NLP Techniques[/if 2584]. Journal of Web Engineering & Technology. 12/09/2025; 12(03):35-43. Available from: https://journals.stmjournals.com/jowet/article=12/09/2025/view=0

nn

n

n[if 992 equals=”Open Access”]Full Text PDF[/if 992]n

n

n[if 992 not_equal=”Open Access”]n

n

n[/if 992]n

nn

nnn

n[if 379 not_equal=””]nn

Browse Figures

n

n

n[foreach 379]

figures

[/foreach]n

n

n

n[/if 379]

n

n

n

n

n

References n

n[if 1104 equals=””]n

  1. Jain A, Arora A, Yadav D, Morato J, Kaur A. Text summarization technique for punjabi language using neural networks. Int Arab J Inf Technol. 2021 Nov 1; 18(6): 807–18.
  2. Singh A, Bansal J. Neural machine transliteration of indian languages. In 2021 IEEE 4th International Conference on Computing and Communications Technologies (ICCCT). 2021 Dec 16; 91–96.
  3. Siripragada S, Philip J, Namboodiri VP, Jawahar CV. A multilingual parallel corpora collection effort for Indian languages. arXiv preprint arXiv:2007.07691. 2020 Jul 15.
  4. Sarma B, Nath C. Analysis Of Inflectional Behaviour In Indian Languages Using Features Extraction Techniques. In 2023 IEEE International Conference on Advancement in Computation & Computer Technologies (InCACCT). 2023 May 5; 1–5.
  5. Jain A, Yadav D, Arora A. Particle swarm optimization for Punjabi text summarization. Int J Oper Res Inf Syst. 2021 Jul 1; 12(3): 1–7.
  6. Garg KD, Khullar V, Agarwal AK. Unsupervised machine learning approach for extractive Punjabi text summarization. In 2021 IEEE 8th International Conference on Signal Processing and Integrated Networks (SPIN). 2021 Aug 26; 750–754.
  7. Bafna PB, Saini JR. An application of Zipf’s law for prose and verse corpora neutrality for hindi and Marathi languages. Int J Adv Comput Sci Appl. 2020; 11(3): 261–265.
  8. Singh M, Kumar R, Chana I. Corpus based machine translation system with deep neural network for Sanskrit to Hindi translation. Procedia Comput Sci. 2020 Jan 1; 167: 2534–44.
  9. Haq S, Sharma A, Bhattacharyya P. Indicirsuite: Multilingual dataset and neural information models for indian languages. arXiv preprint arXiv:2312.09508. 2023 Dec 15.
  10. Bakrola V, Nasariwala J. SAHAAYAK 2023–the Multi Domain Bilingual Parallel Corpus of Sanskrit to Hindi for Machine Translation. arXiv preprint arXiv:2307.00021. 2023 Jun 27.
  11. Kumar Y, Kaur K, Kaur S. Study of automatic text summarization approaches in different languages. Artif Intell Rev. 2021 Dec; 54(8): 5897–929.
  12. Garg KD, Khullar V, Agarwal AK. Unsupervised machine learning approach for extractive Punjabi text summarization. In 2021 IEEE 8th International Conference on Signal Processing and Integrated Networks (SPIN). 2021 Aug 26; 750–754.
  13. Khepra S, Kumari P, Gupta R, Bramhe VS. A Survey of Punjabi Language Translation using OCR and ML. In 2023 IEEE 10th International Conference on Computing for Sustainable Global Development (INDIACom). 2023 Mar 15; 136–144.
  14. Kaur D, Singh S. Building English-Punjabi Aligned Parallel Corpora of Nouns from Comparable Corpora. Appl Comput Syst. 2023 Dec 1; 28(2): 245–51.
  15. Mahi GS, Verma A. Development of Focused Crawlers for Building Large Punjabi News Corpus. J ICT Res Appl. 2021 Dec 1; 15(3): 205–215.
  16. Dendukuri A, Goyal S, Arora J, Pradeep A. Extractive summarization in Hindi using BERT-based ensemble model. In 2022 IEEE 13th International Conference on Computing Communication and Networking Technologies (ICCCNT). 2022 Oct 3; 1–7.
  17. Garg U, Goyal V. Maulik: A plagiarism detection tool for hindi documents. Indian J Sci Technol. 2016 Mar; 9(12): 1–11.
  18. Agarwal B. Cross-lingual plagiarism detection techniques for English-Hindi language pairs. J Discrete Math Sci Cryptogr. 2019 May 19; 22(4): 679–86.
  19. Kaur A, Singh P, Rani S. Spell Checking and Error Correcting System for text paragraphs written in Punjabi Language using Hybrid approach. Int J Eng Comput Sci. 2014 Sep; 3(9): 8030–2.
  20. Kaur M, Gupta V, Kaur R. Review of recent plagiarism detection techniques and their performance comparison. In Proceedings of International Conference on Recent Trends in Machine Learning, IoT, Smart Cities and Applications: ICMISC 2020. Singapore: Springer Singapore; 2020 Oct 18; 157–170.

nn[/if 1104][if 1104 not_equal=””]n

    [foreach 1102]n t

  1. [if 1106 equals=””], [/if 1106][if 1106 not_equal=””],[/if 1106]

    2. n[/foreach]

n[/if 1104]

n

nn[if 1114 equals=”Yes”]n

n[/if 1114]

n

n

[if 424 not_equal=””]Regular Issue[else]Published[/if 424] Subscription Review Article

n

n

[if 2146 equals=”Yes”][/if 2146][if 2146 not_equal=”Yes”][/if 2146]n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n

n[if 1748 not_equal=””]

[else]

[/if 1748]n

n[if 1746 equals=”Retracted”]n

n

n

n

[/if 1746]n[if 4734 not_equal=””]

n

n

n

[/if 4734]n

n

Volume 12
[if 424 equals=”Regular Issue”]Issue[/if 424][if 424 equals=”Special Issue”]Special Issue[/if 424] [if 424 equals=”Conference”][/if 424] 03
Received 28/04/2025
Accepted 04/08/2025
Published 12/09/2025
Retracted
Publication Time 137 Days

n

n

24

nn

n

n
My IP
n

PlumX Metrics

nn

n

n

n[if 1746 equals=”Retracted”]n

[/if 1746]nnn

nnn”}]