{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T07:47:45Z","timestamp":1770018465013,"version":"3.49.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-026-21145-5","type":"journal-article","created":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T21:09:21Z","timestamp":1769980161000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal book reader with multilingual support"],"prefix":"10.1007","volume":"85","author":[{"given":"Rajalakshmi","family":"S","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4643-8775","authenticated-orcid":false,"given":"Nishaanth","family":"R","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shrijith","family":"M R","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Angeldeborah","family":"S","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,1]]},"reference":[{"issue":"4","key":"21145_CR1","first-page":"5761","volume":"40","author":"JA Alzubi","year":"2021","unstructured":"Alzubi JA, Jain R, Nagrath P et al (2021) Deep image captioning using an ensemble of CNN and LSTM based deep neural networks. J Intell Fuzzy Syst 40(4):5761\u20135769","journal-title":"J Intell Fuzzy Syst"},{"key":"21145_CR2","unstructured":"Cao TT, Ngo NK, Le TD et al (2021) Hcmus at mediaeval 2021: Fine-tuning clip for automatic news-images re-matching. In: MediaEval"},{"key":"21145_CR3","unstructured":"Carlsson F, Eisen P, Rekathati F et al (2022) Cross-lingual and multilingual CLIP. In: Calzolari N, B\u00e9chet F, Blache P et al (eds) Proceedings of the 13th language resources and evaluation conference. European Language Resources Association, Marseille, France, pp 6848\u20136854. https:\/\/aclanthology.org\/2022.lrec-1.739"},{"key":"21145_CR4","unstructured":"Feng F, Yang Y, Cer D et al (2020) Language-agnostic bert sentence embedding. CoRR, arXiv preprint arXiv:2007.01852"},{"issue":"2","key":"21145_CR5","doi-asserted-by":"publisher","first-page":"135","DOI":"10.3233\/TAD-2008-20208","volume":"20","author":"D Freitas","year":"2008","unstructured":"Freitas D, Kouroupetroglou G (2008) Speech technologies for blind and low vision persons. Technol Disabil 20(2):135\u2013156","journal-title":"Technol Disabil"},{"key":"21145_CR6","doi-asserted-by":"publisher","unstructured":"Gaikwad P, Doshi M, Deoghare S et al (2023) Machine translation advancements for low-resource Indian languages in WMT23: CFILT-IITB\u2019s effort for bridging the gap. In: Koehn P, Haddow B, Kocmi T et al (eds) Proceedings of the 18th conference on machine translation. Association for Computational Linguistics, Singapore, pp 950\u2013953. https:\/\/doi.org\/10.18653\/v1\/2023.wmt-1.89, https:\/\/aclanthology.org\/2023.wmt-1.89","DOI":"10.18653\/v1\/2023.wmt-1.89"},{"key":"21145_CR7","unstructured":"Gala J, Chitale PA, AK R et al (2023) Indictrans2: Towards high-quality and accessible machine translation models for all 22 scheduled indian languages. arXiv preprint arXiv:2305.16307"},{"key":"21145_CR8","doi-asserted-by":"publisher","unstructured":"Ganesan J, Azar AT, Alsenan S et al (2022) Deep learning reader for visually impaired. Electronics 11(20). https:\/\/doi.org\/10.3390\/electronics11203335, https:\/\/www.mdpi.com\/2079-9292\/11\/20\/3335","DOI":"10.3390\/electronics11203335"},{"key":"21145_CR9","doi-asserted-by":"crossref","unstructured":"Gumma V, Hada R, Yadavalli A et al (2024) Muntts: A text-to-speech system for mundari. arXiv preprint arXiv:2401.15579","DOI":"10.18653\/v1\/2024.computel-1.11"},{"key":"21145_CR10","doi-asserted-by":"publisher","unstructured":"Huang C, Jiang H (2019) Image indexing and content analysis in children\u2019s picture books using a large-scale database. Multimedia Tools Appl 78(15):20679\u201320695. https:\/\/doi.org\/10.1007\/s11042-019-7440-8","DOI":"10.1007\/s11042-019-7440-8"},{"key":"21145_CR11","unstructured":"Jia Y, Zhang Y, Weiss R et al (2018) Transfer learning from speaker verification to multispeaker text-to-speech synthesis. Adv Neural Inf Process Syst 31"},{"key":"21145_CR12","doi-asserted-by":"publisher","unstructured":"Karthi M, Muthulakshmi V, Priscilla R et al (2021) Evolution of yolo-v5 algorithm for object detection: Automated detection of library books and performace validation of dataset. In: 2021 International conference on innovative computing, intelligent communication and smart electrical systems (ICSES), pp 1\u20136, https:\/\/doi.org\/10.1109\/ICSES52305.2021.9633834","DOI":"10.1109\/ICSES52305.2021.9633834"},{"key":"21145_CR13","doi-asserted-by":"crossref","unstructured":"Kurlekar S, Deshpande O, Kamble A et al (2020) Reading device for blind people using python, OCR and GTTS. Intl J Sci Eng Appl 9(4)","DOI":"10.7753\/IJSEA0904.1003"},{"key":"21145_CR14","unstructured":"Li D, Li J, Le H et al (2022a) Lavis: A library for language-vision intelligence. arXiv preprint arXiv:2209.09019"},{"key":"21145_CR15","unstructured":"Li J, Li D, Xiong C et al (2022b) BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Chaudhuri K, Jegelka S, Song L et al (eds) Proceedings of the 39th international conference on machine learning, proceedings of machine learning research, vol 162. PMLR, pp 12888\u201312900. https:\/\/proceedings.mlr.press\/v162\/li22n.html"},{"key":"21145_CR16","doi-asserted-by":"publisher","unstructured":"Li J, Xu Y, Lv T et al (2022c) Dit: Self-supervised pre-training for document image transformer. In: Proceedings of the 30th ACM International conference on multimedia. Association for computing machinery, New York, NY, USA, MM \u201922, pp 3530\u20133539. https:\/\/doi.org\/10.1145\/3503161.3547911, https:\/\/doi.org\/10.1145\/3503161.3547911","DOI":"10.1145\/3503161.3547911"},{"key":"21145_CR17","unstructured":"Li J, Li D, Savarese S et al (2023) BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: Krause A, Brunskill E, Cho K et al (eds) Proceedings of the 40th international conference on machine learning, proceedings of machine learning research, vol 202. PMLR, pp 19730\u201319742. https:\/\/proceedings.mlr.press\/v202\/li23q.html"},{"key":"21145_CR18","unstructured":"Lommatzsch A, Kille B, \u00d6zg\u00f6bek \u00d6 et al (2023) News images in mediaeval 2023. Proceedings of the MediaEval benchmarking initiative"},{"key":"21145_CR19","unstructured":"Okamoto Y, Toyonaga H, Ijiri Y et al (2023) Constructing image-text pair dataset from books. arXiv preprint arXiv:2310.01936"},{"key":"21145_CR20","doi-asserted-by":"publisher","unstructured":"Orji EZ, Haydar A, Ersan I et al (2023) Advancing ocr accuracy in image-to-latex conversion\u2014a critical and creative exploration. Appl Sci 13(22). https:\/\/doi.org\/10.3390\/app132212503, https:\/\/www.mdpi.com\/2076-3417\/13\/22\/12503","DOI":"10.3390\/app132212503"},{"key":"21145_CR21","doi-asserted-by":"publisher","unstructured":"Pfitzmann B, Auer C, Dolfi M et al (2022) Doclaynet: A large human-annotated dataset for document-layout segmentation. In: Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining. Association for computing machinery, New York, NY, USA, KDD \u201922, pp 3743\u20133751. https:\/\/doi.org\/10.1145\/3534678.3539043, https:\/\/doi.org\/10.1145\/3534678.3539043","DOI":"10.1145\/3534678.3539043"},{"key":"21145_CR22","doi-asserted-by":"crossref","unstructured":"Popovi\u0107 M (2017) chrf++: words helping character n-grams. In: Proceedings of the second conference on machine translation, pp 612\u2013618","DOI":"10.18653\/v1\/W17-4770"},{"key":"21145_CR23","doi-asserted-by":"publisher","unstructured":"Prakash A, Umesh S, Murthy HA (2023) Towards developing state-of-the-art tts synthesisers for 13 indian languages with signal processing aided alignments. In: 2023 IEEE automatic speech recognition and understanding workshop (ASRU), pp 1\u20138. https:\/\/doi.org\/10.1109\/ASRU57964.2023.10389630","DOI":"10.1109\/ASRU57964.2023.10389630"},{"key":"21145_CR24","unstructured":"Radford A, Kim JW, Hallacy C et al (2021) Learning transferable visual models from natural language supervision. In: Meila M, Zhang T (eds) Proceedings of the 38th international conference on machine learning, proceedings of machine learning research, vol 139. PMLR, pp 8748\u20138763. https:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"issue":"12","key":"21145_CR25","first-page":"634","volume":"20","author":"R Rajan","year":"2022","unstructured":"Rajan R, Devasena MG (2022) A novel reading technique for visually impaired person using enhanced optical character recognition method. NeuroQuantology 20(12):634\u2013650","journal-title":"NeuroQuantology"},{"key":"21145_CR26","unstructured":"Ricardo R (2022) The Benefits of CBD drinks. Ricardo R, 1st edn"},{"key":"21145_CR27","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/978-3-030-86549-8_9","volume-title":"Document Analysis and Recognition - ICDAR 2021","author":"Z Shen","year":"2021","unstructured":"Shen Z, Zhang R, Dell M et al (2021) Layoutparser: A unified toolkit for deep learning based document image analysis. In: Llad\u00f3s J, Lopresti D, Uchida S (eds) Document Analysis and Recognition - ICDAR 2021. Springer International Publishing, Cham, pp 131\u2013146"},{"key":"21145_CR28","doi-asserted-by":"publisher","unstructured":"Sundara\u00a0Pandiyan S, Kelvin C (2021) A translator for indian sign boards to english using tesseract and seq2seq model. In: 2021 international conference on simulation, automation & smart manufacturing (SASM), pp 1\u20134. https:\/\/doi.org\/10.1109\/SASM51857.2021.9841215","DOI":"10.1109\/SASM51857.2021.9841215"},{"key":"21145_CR29","first-page":"393","volume":"25","author":"D Tsonos","year":"2009","unstructured":"Tsonos D, Kaccori H, Kouroupetroglou G (2009) A design-for-all approach towards multimodal accessibility of mathematics. Assist Technol Res Ser 25:393\u2013397","journal-title":"Assist Technol Res Ser"},{"key":"21145_CR30","unstructured":"Van Den\u00a0Oord A, Dieleman S, Zen H et al (2016) Wavenet: A generative model for raw audio. 12. arXiv preprint arXiv:1609.03499"},{"key":"21145_CR31","doi-asserted-by":"crossref","unstructured":"Vinyals O, Toshev A, Bengio S et al (2015) Show and tell: A neural image caption generator. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2015.7298935"},{"issue":"4","key":"21145_CR32","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/TPAMI.2016.2587640","volume":"39","author":"O Vinyals","year":"2017","unstructured":"Vinyals O, Toshev A, Bengio S et al (2017) Show and tell: Lessons learned from the 2015 mscoco image captioning challenge. IEEE Trans Pattern Anal Mach Intell 39(4):652\u2013663. https:\/\/doi.org\/10.1109\/TPAMI.2016.2587640","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"21145_CR33","unstructured":"Vu HN, Nguyen HD, Tran MT (2022) Re-matching images and news using clip pretrained model. In: Proceedings of the MediaEval\u201922: Multimedia evaluation workshop, CEUR Workshop Proceedings"},{"key":"21145_CR34","doi-asserted-by":"crossref","unstructured":"You Q, Jin H, Wang Z et al (2016) Image captioning with semantic attention. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2016.503"},{"key":"21145_CR35","doi-asserted-by":"publisher","unstructured":"Young P, Lai A, Hodosh M et al (2014) From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptions. Trans Assoc Comput Linguist 2:67\u201378. https:\/\/doi.org\/10.1162\/tacl_a_00166, https:\/\/aclanthology.org\/Q14-1006\/","DOI":"10.1162\/tacl_a_00166"},{"key":"21145_CR36","unstructured":"Yue X, Song Y, Asai A et al (2025) Pangea: A fully open multilingual multimodal llm for 39 languages. https:\/\/arxiv.org\/abs\/2410.16153"},{"key":"21145_CR37","doi-asserted-by":"crossref","unstructured":"Zhong X, Tang J, Yepes AJ (2019) Publaynet: Largest dataset ever for document layout analysis. https:\/\/arxiv.org\/abs\/1908.07836","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"21145_CR38","doi-asserted-by":"crossref","unstructured":"Zhou Y, Wang M, Liu D et al (2020a) More grounded image captioning by distilling image-text matching model. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.00483"},{"key":"21145_CR39","doi-asserted-by":"crossref","unstructured":"Zhou Y, Wang M, Liu D et al (2020b) More grounded image captioning by distilling image-text matching model. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR42600.2020.00483"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21145-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-026-21145-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-026-21145-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T21:09:25Z","timestamp":1769980165000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-026-21145-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,1]]},"references-count":39,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["21145"],"URL":"https:\/\/doi.org\/10.1007\/s11042-026-21145-5","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,1]]},"assertion":[{"value":"1 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 October 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 December 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 February 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"All the authors involved in this manuscript give full consent for publication of this submitted article.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"75"}}