{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T03:24:59Z","timestamp":1779333899777,"version":"3.51.4"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T00:00:00Z","timestamp":1692835200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T00:00:00Z","timestamp":1692835200000},"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":["Int J Multimed Info Retr"],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1007\/s13735-023-00293-6","type":"journal-article","created":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T14:06:33Z","timestamp":1692885993000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["DELIGHT-Net: DEep and LIGHTweight network to segment Indian text at word level from wild scenic images"],"prefix":"10.1007","volume":"12","author":[{"given":"Shilpa","family":"Mahajan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajneesh","family":"Rani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karan","family":"Trehan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,24]]},"reference":[{"key":"293_CR1","doi-asserted-by":"publisher","unstructured":"Alghamdi A, Alluhaybi D, Almehmadi D, Alameer K, Siddeq SB, Alsubait T (2021) Text segmentation of historical Arabic handwritten manuscripts using projection profile. In: 2021 national computing colleges conference (NCCC), pp 1\u20136. https:\/\/doi.org\/10.1109\/NCCC49330.2021.9428836","DOI":"10.1109\/NCCC49330.2021.9428836"},{"key":"293_CR2","doi-asserted-by":"crossref","unstructured":"Amara M, Zidi K, Ghedira K, Zidi S (2016) New rules to enhance the performances of histogram projection for segmenting small-sized Arabic words. In: International conference on hybrid intelligent systems. Springer, pp 167\u2013176","DOI":"10.1007\/978-3-319-27221-4_14"},{"key":"293_CR3","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1016\/S0031-3203(01)00081-4","volume":"35","author":"V Bansal","year":"2002","unstructured":"Bansal V, Sinha RMK (2002) Segmentation of touching and fused Devanagari characters. Pattern Recogn 35:875\u2013893. https:\/\/doi.org\/10.1016\/S0031-3203(01)00081-4","journal-title":"Pattern Recogn"},{"key":"293_CR4","doi-asserted-by":"publisher","first-page":"881","DOI":"10.1007\/s12065-020-00472-y","volume":"14","author":"HT Basavaraju","year":"2021","unstructured":"Basavaraju HT, Aradhya VN, Pavithra MS, Guru DS, Bhateja V (2021) Arbitrary oriented multilingual text detection and segmentation using level set and Gaussian mixture model. Evol Intell 14:881\u2013894. https:\/\/doi.org\/10.1007\/s12065-020-00472-y","journal-title":"Evol Intell"},{"key":"293_CR5","doi-asserted-by":"publisher","unstructured":"Bhattacharya U, Parui SK, Mondal S (2009) Devanagari and Bangla text extraction from natural scene images. In: 2009 10th international conference on document analysis and recognition, pp 171\u2013175. https:\/\/doi.org\/10.1109\/ICDAR.2009.178","DOI":"10.1109\/ICDAR.2009.178"},{"key":"293_CR6","doi-asserted-by":"crossref","unstructured":"Chaitra Y, Dinesh R (2022) An impact of radon transforms and filtering techniques for text localization in natural scene text images. In: ICT with intelligent applications: proceedings of ICTIS 2021, vol 1. Springer, pp 563\u2013573","DOI":"10.1007\/978-981-16-4177-0_55"},{"key":"293_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-021-06309-9","author":"Y Chaitra","year":"2021","unstructured":"Chaitra Y, Dinesh R, Gopalakrishna M, Prakash BA (2021) Deep-cnntl: text localization from natural scene images using deep convolution neural network with transfer learning. Arab J Sci Eng. https:\/\/doi.org\/10.1007\/s13369-021-06309-9","journal-title":"Arab J Sci Eng"},{"key":"293_CR8","doi-asserted-by":"crossref","unstructured":"Chaitra Y, Dinesh R, Jeevan M, Arpitha M, Aishwarya V, Akshitha K (2022) An impact of yolov5 on text detection and recognition system using tesseractocr in images\/video frames. In: 2022 IEEE international conference on data science and information system (ICDSIS). IEEE, pp 1\u20136","DOI":"10.1109\/ICDSIS55133.2022.9915927"},{"key":"293_CR9","doi-asserted-by":"publisher","unstructured":"Dai Y, Huang Z, Gao Y, Xu Y, Chen K, Guo J, Qiu W (2018) Fused text segmentation networks for multi-oriented scene text detection. In: Proceedings: international conference on pattern recognition. IEEE, pp 3604\u20133609. https:\/\/doi.org\/10.1109\/ICPR.2018.8546066","DOI":"10.1109\/ICPR.2018.8546066"},{"key":"293_CR10","doi-asserted-by":"publisher","first-page":"10603","DOI":"10.1109\/ACCESS.2018.2795104","volume":"6","author":"SB Dhok","year":"2018","unstructured":"Dhok SB (2018) Multilingual character segmentation and recognition schemes for Indian document images. IEEE Access 6:10603\u201310617. https:\/\/doi.org\/10.1109\/ACCESS.2018.2795104","journal-title":"IEEE Access"},{"key":"293_CR11","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.isprsjprs.2020.01.013","volume":"162","author":"FI Diakogiannis","year":"2020","unstructured":"Diakogiannis FI, Waldner F, Caccetta P, Wu C (2020) Resunet-a: a deep learning framework for semantic segmentation of remotely sensed data. ISPRS J Photogramm Remote Sens 162:94\u2013114","journal-title":"ISPRS J Photogramm Remote Sens"},{"key":"293_CR12","doi-asserted-by":"crossref","unstructured":"Firdaus FI, Khumaini A, Utaminingrum F (2017) Arabic letter segmentation using modified connected component labeling. In: 2017 international conference on sustainable information engineering and technology (SIET). IEEE, pp 392\u2013397","DOI":"10.1109\/SIET.2017.8304170"},{"key":"293_CR13","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1016\/j.future.2018.04.074","volume":"87","author":"G Jillani","year":"2018","unstructured":"Jillani G, Hussain J, Yasmin M, Sharif M, Lawrence S (2018) A novel machine learning approach for scene text extraction. FuturE Gener Comput Syst 87:328\u2013340. https:\/\/doi.org\/10.1016\/j.future.2018.04.074","journal-title":"FuturE Gener Comput Syst"},{"key":"293_CR14","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1109\/TMM.2016.2638622","volume":"19","author":"S Karaoglu","year":"2017","unstructured":"Karaoglu S, Tao R, Gevers T, Smeulders AWM (2017) Words matter: scene text for image classification and retrieval. IEEE Trans Multimed 19:1063\u20131076. https:\/\/doi.org\/10.1109\/TMM.2016.2638622","journal-title":"IEEE Trans Multimed"},{"key":"293_CR15","doi-asserted-by":"publisher","first-page":"1637","DOI":"10.1007\/s00371-020-01927-0","volume":"37","author":"RP Kaur","year":"2021","unstructured":"Kaur RP, Jindal MK, Kumar M (2021) Text and graphics segmentation of newspapers printed in Gurmukhi script: a hybrid approach. Vis Comput 37:1637\u20131659. https:\/\/doi.org\/10.1007\/s00371-020-01927-0","journal-title":"Vis Comput"},{"key":"293_CR16","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/j.eswa.2019.04.030","volume":"131","author":"V Khare","year":"2019","unstructured":"Khare V, Shivakumara P, Chan CS, Lu T, Meng LK, Woon HH, Blumenstein M (2019) A novel character segmentation-reconstruction approach for license plate recognition. Expert Syst Appl 131:219\u2013239","journal-title":"Expert Syst Appl"},{"key":"293_CR17","doi-asserted-by":"publisher","first-page":"2117","DOI":"10.1109\/TIP.2007.900098","volume":"16","author":"S Kumar","year":"2007","unstructured":"Kumar S, Gupta R, Khanna N, Chaudhury S, Joshi SD (2007) Text extraction and document image segmentation using matched wavelets and MRF model. IEEE Trans Image Process 16:2117\u20132128. https:\/\/doi.org\/10.1109\/TIP.2007.900098","journal-title":"IEEE Trans Image Process"},{"key":"293_CR18","doi-asserted-by":"crossref","unstructured":"Liao M, Pang G, Huang J, Hassner T, Bai X (2020) Mask textspotter v3: segmentation proposal network for robust scene text spotting. In: Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, 23\u201328 Aug 2020, Proceedings, Part XI 16. Springer, pp 706\u2013722","DOI":"10.1007\/978-3-030-58621-8_41"},{"key":"293_CR19","doi-asserted-by":"publisher","unstructured":"Liu X (2005) An edge-based text region extraction algorithm for indoor mobile robot navigation. In: IEEE international conference mechatronics and automation, 2005, vol 2, pp 701\u2013706. https:\/\/doi.org\/10.1109\/ICMA.2005.1626635","DOI":"10.1109\/ICMA.2005.1626635"},{"key":"293_CR20","doi-asserted-by":"crossref","unstructured":"Liu X (2006) Multiscale edge-based text extraction from complex images. Xiaoqing Liu and Jagath Samarabandu The University of Western Ontario Department of Electrical & Computer Engineering. Neural Computing and Applications, pp 1721\u20131724","DOI":"10.1109\/ICME.2006.262882"},{"key":"293_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107591","author":"T Lu","year":"2021","unstructured":"Lu T, Dooms A (2021) Probabilistic homogeneity for document image segmentation. Pattern Recognit. https:\/\/doi.org\/10.1016\/j.patcog.2020.107591","journal-title":"Pattern Recognit"},{"key":"293_CR22","unstructured":"Ma J, Zhang H, Shan Y, Qie X, Xu X, Qi Z (2022) BTS: a bi-lingual benchmark for text segmentation in the wild. In: CVPR, pp 19152\u201319162"},{"key":"293_CR23","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s10032-022-00408-5","volume":"25","author":"B Madi","year":"2022","unstructured":"Madi B, Droby A, El-Sana J (2022) Textline alignment on the image domain. Int J Doc Anal Recognit 25:415\u2013427","journal-title":"Int J Doc Anal Recognit"},{"key":"293_CR24","doi-asserted-by":"publisher","unstructured":"Mahajan S, Rani R (2018) Text extraction from Indian and non-Indian natural scene images: a review. In: 2018 first international conference on secure cyber computing and communication (ICSCCC). IEEE, pp 584\u2013588. https:\/\/doi.org\/10.1109\/ICSCCC.2018.8703369","DOI":"10.1109\/ICSCCC.2018.8703369"},{"key":"293_CR25","doi-asserted-by":"publisher","unstructured":"Mahajan S, Rani R (2019) A decade on script identification from natural images\/videos: a review. In: 2019 international conference on issues and challenges in intelligent computing techniques (ICICT), pp 1\u20135. https:\/\/app.dimensions.ai\/details\/publication\/pub.1124551290. https:\/\/doi.org\/10.1109\/icict46931.2019.8977630","DOI":"10.1109\/icict46931.2019.8977630"},{"key":"293_CR26","doi-asserted-by":"publisher","first-page":"4317","DOI":"10.1007\/s10462-021-10000-8","volume":"54","author":"S Mahajan","year":"2021","unstructured":"Mahajan S, Rani R (2021) Text detection and localization in scene images: a broad review. Artif Intell Rev 54:4317\u20134377","journal-title":"Artif Intell Rev"},{"key":"293_CR27","doi-asserted-by":"publisher","unstructured":"Mancas-Thillou C, Gosselin B (2005) Color text extraction from camera-based images: the impact of the choice of the clustering distance. In: Proceedings of the international conference on document analysis and recognition, ICDAR, pp 312\u2013316. https:\/\/doi.org\/10.1109\/ICDAR.2005.76","DOI":"10.1109\/ICDAR.2005.76"},{"key":"293_CR28","doi-asserted-by":"publisher","unstructured":"Mechi O, Mehri M, Ingold R, Amara NEB (2019) Text line segmentation in historical document images using an adaptive U-net architecture. In: Proceedings of the international conference on document analysis and recognition, ICDAR, vol 1, pp 369\u2013374. https:\/\/doi.org\/10.1109\/ICDAR.2019.00066","DOI":"10.1109\/ICDAR.2019.00066"},{"key":"293_CR29","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/s10032-019-00317-0","volume":"22","author":"N Milosevic","year":"2019","unstructured":"Milosevic N, Gregson C, Hernandez R, Nenadic G (2019) A framework for information extraction from tables in biomedical literature. Int J Doc Anal Recognit 22:55\u201378","journal-title":"Int J Doc Anal Recognit"},{"key":"293_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10032-021-00390-4","volume":"25","author":"DD Nguyen","year":"2022","unstructured":"Nguyen DD (2022) Tablesegnet: a fully convolutional network for table detection and segmentation in document images. Int J Doc Anal Recognit 25:1\u201314","journal-title":"Int J Doc Anal Recognit"},{"key":"293_CR31","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1016\/j.patcog.2009.05.007","volume":"43","author":"V Papavassiliou","year":"2010","unstructured":"Papavassiliou V, Stafylakis T, Katsouros V, Carayannis G (2010) Handwritten document image segmentation into text lines and words. Pattern Recogn 43:369\u2013377. https:\/\/doi.org\/10.1016\/j.patcog.2009.05.007","journal-title":"Pattern Recogn"},{"key":"293_CR32","doi-asserted-by":"publisher","unstructured":"Peng D, Jin L, Wu Y, Wang Z, Cai M (2019) A fast and accurate fully convolutional network for end-to-end handwritten Chinese text segmentation and recognition. In: Proceedings of the international conference on document analysis and recognition, ICDAR, pp 25\u201330. https:\/\/doi.org\/10.1109\/ICDAR.2019.00014","DOI":"10.1109\/ICDAR.2019.00014"},{"key":"293_CR33","first-page":"19","volume":"9","author":"F Qomariyah","year":"2017","unstructured":"Qomariyah F, Utaminingrum F, Mahmudy WF (2017) The segmentation of printed Arabic characters based on interest point. J Telecommun Electron Comput Eng 9:19\u201324","journal-title":"J Telecommun Electron Comput Eng"},{"key":"293_CR34","doi-asserted-by":"crossref","unstructured":"Raj H, Ghosh R (2014) Devanagari text extraction from natural scene images. In: International conference on advances in computing,communications and informatics (ICACCI), pp 513\u2013517","DOI":"10.1109\/ICACCI.2014.6968472"},{"key":"293_CR35","doi-asserted-by":"crossref","unstructured":"Rajan V, Raj S (2017) Text detection and character extraction in natural scene images using fractional Poisson model. In: Proceedings of the IEEE 2017 international conference on computing methodologies and communication, pp 1136\u20131141","DOI":"10.1109\/ICCMC.2017.8282651"},{"key":"293_CR36","doi-asserted-by":"publisher","first-page":"618","DOI":"10.17485\/ijst\/v14i7.2146","volume":"14","author":"B Rajyagor","year":"2021","unstructured":"Rajyagor B, Rakholia R (2021) Tri-level handwritten text segmentation techniques for Gujarati language. Indian J Sci Technol 14:618\u2013627. https:\/\/doi.org\/10.17485\/ijst\/v14i7.2146","journal-title":"Indian J Sci Technol"},{"key":"293_CR37","doi-asserted-by":"publisher","first-page":"618","DOI":"10.17485\/IJST\/v14i7.2146","volume":"14","author":"B Rajyagor","year":"2021","unstructured":"Rajyagor B, Rakholia R (2021) Tri-level handwritten text segmentation techniques for Gujarati language. Indian J Sci Technol 14:618\u2013627","journal-title":"Indian J Sci Technol"},{"key":"293_CR38","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1109\/TIP.2019.2930176","volume":"29","author":"X Rong","year":"2020","unstructured":"Rong X, Yi C, Tian Y (2020) Unambiguous scene text segmentation with referring expression comprehension. IEEE Trans Image Process 29:591\u2013601. https:\/\/doi.org\/10.1109\/TIP.2019.2930176","journal-title":"IEEE Trans Image Process"},{"key":"293_CR39","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"293_CR40","doi-asserted-by":"publisher","first-page":"2727","DOI":"10.32604\/cmc.2021.016447","volume":"68","author":"SI Saleem","year":"2021","unstructured":"Saleem SI, Abdulazeez AM, Orman Z (2021) A new segmentation framework for Arabic handwritten text using machine learning techniques. Comput Mater Contin 68:2727\u20132754. https:\/\/doi.org\/10.32604\/cmc.2021.016447","journal-title":"Comput Mater Contin"},{"key":"293_CR41","doi-asserted-by":"publisher","first-page":"8212","DOI":"10.1109\/TIP.2021.3113157","volume":"30","author":"C Wang","year":"2021","unstructured":"Wang C, Zhao S, Zhu L, Luo K, Guo Y, Wang J, Liu S (2021) Semi-supervised pixel-level scene text segmentation by mutually guided network. IEEE Trans Image Process 30:8212\u20138221. https:\/\/doi.org\/10.1109\/TIP.2021.3113157","journal-title":"IEEE Trans Image Process"},{"key":"293_CR42","doi-asserted-by":"crossref","unstructured":"Xu X, Qi Z, Ma J, Zhang H, Shan Y, Qie X (2022) Bts: a bi-lingual benchmark for text segmentation in the wild. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 19152\u201319162","DOI":"10.1109\/CVPR52688.2022.01856"},{"key":"293_CR43","doi-asserted-by":"crossref","unstructured":"Xu X, Zhang Z, Wang Z, Price B, Wang Z, Shi H (2021) Rethinking text segmentation: a novel dataset and a text-specific refinement approach. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12045\u201312055","DOI":"10.1109\/CVPR46437.2021.01187"},{"key":"293_CR44","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1109\/TCYB.2014.2330657","volume":"45","author":"H Yang","year":"2015","unstructured":"Yang H, Wu S, Member S, Deng C, Lin W, Member S (2015) Scale and orientation invariant text segmentation for born-digital compound images. IEEE Trans Cybern 45:519\u2013533. https:\/\/doi.org\/10.1109\/TCYB.2014.2330657","journal-title":"IEEE Trans Cybern"},{"key":"293_CR45","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1109\/tai.2021.3116216","volume":"3","author":"C Zhang","year":"2021","unstructured":"Zhang C, Tao Y, Du K, Ding W, Wang B, Liu J, Wang W (2021) Character-level street view text spotting based on deep multisegmentation network for smarter autonomous driving. IEEE Trans Artif Intell 3:297\u2013308. https:\/\/doi.org\/10.1109\/tai.2021.3116216","journal-title":"IEEE Trans Artif Intell"},{"key":"293_CR46","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1109\/LGRS.2018.2802944","volume":"15","author":"Z Zhang","year":"2018","unstructured":"Zhang Z, Liu Q, Wang Y (2018) Road extraction by deep residual u-net. IEEE Geosci Remote Sens Lett 15:749\u2013753","journal-title":"IEEE Geosci Remote Sens Lett"}],"container-title":["International Journal of Multimedia Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-023-00293-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13735-023-00293-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13735-023-00293-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,2]],"date-time":"2023-12-02T14:14:29Z","timestamp":1701526469000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13735-023-00293-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,24]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["293"],"URL":"https:\/\/doi.org\/10.1007\/s13735-023-00293-6","relation":{},"ISSN":["2192-6611","2192-662X"],"issn-type":[{"value":"2192-6611","type":"print"},{"value":"2192-662X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,24]]},"assertion":[{"value":"22 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 August 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflicts of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"29"}}