{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T07:45:08Z","timestamp":1775807108923,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T00:00:00Z","timestamp":1747872000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100002553","name":"Seoul National University of Science and Technology","doi-asserted-by":"publisher","award":["2023-1087"],"award-info":[{"award-number":["2023-1087"]}],"id":[{"id":"10.13039\/501100002553","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002553","name":"Seoul National University of Science and Technology","doi-asserted-by":"publisher","award":["2023-1087"],"award-info":[{"award-number":["2023-1087"]}],"id":[{"id":"10.13039\/501100002553","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1007\/s10032-025-00525-x","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T03:47:10Z","timestamp":1747885630000},"page":"77-90","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring the effectiveness of data-centric AI approaches to developing a prescription recognition system"],"prefix":"10.1007","volume":"29","author":[{"given":"Jihyo","family":"Kim","sequence":"first","affiliation":[]},{"given":"Daejeong","family":"Mun","sequence":"additional","affiliation":[]},{"given":"Jaemoon","family":"Hwang","sequence":"additional","affiliation":[]},{"given":"Sangheum","family":"Hwang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,22]]},"reference":[{"key":"525_CR1","doi-asserted-by":"publisher","unstructured":"Ciuntu, V., Ferdowsi, H.: Real-time traffic sign detection and classification using machine learning and optical character recognition. In: IEEE International conference on electro information technology, pp. 480\u2013486 (2020). https:\/\/doi.org\/10.1109\/EIT48999.2020.9208309","DOI":"10.1109\/EIT48999.2020.9208309"},{"issue":"1\u20133","key":"525_CR2","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1504\/IJIE.2020.104646","volume":"7","author":"R Anand","year":"2020","unstructured":"Anand, R., Shanthi, T., Sabeenian, R.S., Veni, S.: Real time noisy dataset implementation of optical character identification using cnn. Int. J. Intell. Enterprise 7(1\u20133), 67\u201380 (2020). https:\/\/doi.org\/10.1504\/IJIE.2020.104646","journal-title":"Int. J. Intell. Enterprise"},{"key":"525_CR3","doi-asserted-by":"publisher","unstructured":"Nguyen, T.-T., Nguyen, D.-V.V., Le, T.: Developing a prescription recognition system based on craft and tesseract. In: Computational Collective Intelligence, pp. 443\u2013455 (2021). https:\/\/doi.org\/10.1007\/978-3-030-88081-1_33","DOI":"10.1007\/978-3-030-88081-1_33"},{"issue":"01","key":"525_CR4","doi-asserted-by":"publisher","first-page":"8610","DOI":"10.1609\/aaai.v33i01.33018610","volume":"33","author":"H Li","year":"2019","unstructured":"Li, H., Wang, P., Shen, C., Zhang, G.: Show, attend and read: a simple and strong baseline for irregular text recognition. Proc. AAAI Conf. Artif. Intell. 33(01), 8610\u20138617 (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33018610","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"525_CR5","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"525_CR6","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. In: International conference on learning representations (2021). https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"525_CR7","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., Berg, A.C., Fei-Fei, L.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115, 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vision"},{"key":"525_CR8","doi-asserted-by":"publisher","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014) https:\/\/doi.org\/10.48550\/arXiv.1409.1556","DOI":"10.48550\/arXiv.1409.1556"},{"key":"525_CR9","doi-asserted-by":"publisher","unstructured":"Huang, G., Liu, Z., Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR) (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"525_CR10","doi-asserted-by":"publisher","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K.: Spatial transformer networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015). https:\/\/doi.org\/10.48550\/arXiv.1506.02025","DOI":"10.48550\/arXiv.1506.02025"},{"key":"525_CR11","doi-asserted-by":"publisher","unstructured":"Shi, B., Wang, X., Lyu, P., Yao, C., Bai, X.: Robust scene text recognition with automatic rectification. In: Proceedings of the IEEE conference on computer vision and pattern recognition (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.452","DOI":"10.1109\/CVPR.2016.452"},{"key":"525_CR12","doi-asserted-by":"publisher","first-page":"10062","DOI":"10.1109\/ACCESS.2022.3144844","volume":"10","author":"AA Chandio","year":"2022","unstructured":"Chandio, A.A., Asikuzzaman, M., Pickering, M.R., Leghari, M.: Cursive text recognition in natural scene images using deep convolutional recurrent neural network. IEEE Access 10, 10062\u201310078 (2022). https:\/\/doi.org\/10.1109\/ACCESS.2022.3144844","journal-title":"IEEE Access"},{"key":"525_CR13","doi-asserted-by":"publisher","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014) https:\/\/doi.org\/10.48550\/arXiv.1406.2227","DOI":"10.48550\/arXiv.1406.2227"},{"key":"525_CR14","doi-asserted-by":"publisher","unstructured":"Yim, M., Kim, Y., Cho, H.-C., Park, S.: Synthtiger: Synthetic text image generator towards better text recognition models. In: International conference on document analysis and recognition, pp. 109\u2013124 (2021). https:\/\/doi.org\/10.1007\/978-3-030-86337-1_8","DOI":"10.1007\/978-3-030-86337-1_8"},{"key":"525_CR15","doi-asserted-by":"publisher","unstructured":"Chen, X., Jin, L., Zhu, Y., Luo, C., Wang, T.: Text recognition in the wild: A survey. ACM Comput. Surv. 54(2) (2021) https:\/\/doi.org\/10.1145\/3440756","DOI":"10.1145\/3440756"},{"key":"525_CR16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3152990","author":"Z Shao","year":"2022","unstructured":"Shao, Z., Han, J., Marnerides, D., Debattista, K.: Region-object relation-aware dense captioning via transformer. IEEE Trans. Neural Netw. Learn. Syst. (2022). https:\/\/doi.org\/10.1109\/TNNLS.2022.3152990","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"525_CR17","doi-asserted-by":"publisher","first-page":"8753","DOI":"10.1109\/TMM.2023.3241517","volume":"25","author":"Z Shao","year":"2023","unstructured":"Shao, Z., Han, J., Debattista, K., Pang, Y.: Textual context-aware dense captioning with diverse words. IEEE Trans. Multimedia 25, 8753\u20138766 (2023). https:\/\/doi.org\/10.1109\/TMM.2023.3241517","journal-title":"IEEE Trans. Multimedia"},{"key":"525_CR18","doi-asserted-by":"publisher","first-page":"7581","DOI":"10.1109\/TMM.2024.3369863","volume":"26","author":"Z Shao","year":"2024","unstructured":"Shao, Z., Han, J., Debattista, K., Pang, Y.: DCMSTRD: End-to-end dense captioning via multi-scale transformer decoding. IEEE Trans. Multimedia 26, 7581\u20137593 (2024). https:\/\/doi.org\/10.1109\/TMM.2024.3369863","journal-title":"IEEE Trans. Multimedia"},{"issue":"6","key":"525_CR19","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1109\/34.24792","volume":"11","author":"FL Bookstein","year":"1989","unstructured":"Bookstein, F.L.: Principal warps: Thin-plate splines and the decomposition of deformations. IEEE Trans. Pattern Anal. Mach. Intell. 11(6), 567\u2013585 (1989). https:\/\/doi.org\/10.1109\/34.24792","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"01","key":"525_CR20","doi-asserted-by":"publisher","first-page":"8714","DOI":"10.1609\/aaai.v33i01.33018714","volume":"33","author":"M Liao","year":"2019","unstructured":"Liao, M., Zhang, J., Wan, Z., Xie, F., Liang, J., Lyu, P., Yao, C., Bai, X.: Scene text recognition from two-dimensional perspective. Proc. AAAI Conf. Artif. Intell. 33(01), 8714\u20138721 (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33018714","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"1","key":"525_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103544","volume":"61","author":"T Nasir","year":"2024","unstructured":"Nasir, T., Malik, M.K.: Efficient crnn: Towards end-to-end low resource urdu text recognition using depthwise separable convolutions and gated recurrent units. Inf. Process. Manag. 61(1), 103544 (2024). https:\/\/doi.org\/10.1016\/j.ipm.2023.103544","journal-title":"Inf. Process. Manag."},{"key":"525_CR22","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1007\/s00138-018-0942-y","volume":"29","author":"Z Lei","year":"2018","unstructured":"Lei, Z., Zhao, S., Song, H., Shen, J.: Scene text recognition using residual convolutional recurrent neural network. Mach. Vis. Appl. 29, 861\u2013871 (2018). https:\/\/doi.org\/10.1007\/s00138-018-0942-y","journal-title":"Mach. Vis. Appl."},{"key":"525_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2022.103732","volume":"142","author":"Z XinSheng","year":"2022","unstructured":"XinSheng, Z., Yu, W.: Industrial character recognition based on improved crnn in complex environments. Comput. Ind. 142, 103732 (2022). https:\/\/doi.org\/10.1016\/j.compind.2022.103732","journal-title":"Comput. Ind."},{"key":"525_CR24","doi-asserted-by":"publisher","unstructured":"Borisyuk, F., Gordo, A., Sivakumar, V.: Rosetta: Large scale system for text detection and recognition in images. In: Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery data mining, pp. 71\u201379 (2018). https:\/\/doi.org\/10.1145\/3219819.3219861","DOI":"10.1145\/3219819.3219861"},{"key":"525_CR25","doi-asserted-by":"publisher","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the 23rd international conference on machine learning, pp. 369\u2013376 (2006). https:\/\/doi.org\/10.1145\/1143844.1143891","DOI":"10.1145\/1143844.1143891"},{"issue":"07","key":"525_CR26","doi-asserted-by":"publisher","first-page":"11005","DOI":"10.1609\/aaai.v34i07.6735","volume":"34","author":"W Hu","year":"2020","unstructured":"Hu, W., Cai, X., Hou, J., Yi, S., Lin, Z.: Gtc: Guided training of ctc towards efficient and accurate scene text recognition. Proc. AAAI Conf. Artif. Intell. 34(07), 11005\u201311012 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i07.6735","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"525_CR27","doi-asserted-by":"publisher","unstructured":"Cheng, Z., Bai, F., Xu, Y., Zheng, G., Pu, S., Zhou, S.: Focusing attention: Towards accurate text recognition in natural images. In: Proceedings of the IEEE international conference on computer vision (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.543","DOI":"10.1109\/ICCV.2017.543"},{"key":"525_CR28","doi-asserted-by":"publisher","unstructured":"Feng, X., Yao, H., Qi, Y., Zhang, J., Zhang, S.: Scene text recognition via transformer. arXiv preprint arXiv:2003.08077 (2020) https:\/\/doi.org\/10.48550\/arXiv.2003.08077","DOI":"10.48550\/arXiv.2003.08077"},{"key":"525_CR29","unstructured":"Du, Y., Chen, Z., Jia, C., Yin, X., Li, C., Du, Y., Jiang, Y.-G.: Context perception parallel decoder for scene text recognition. arXiv:arXiv preprint arXiv:2307.12270 (2023)"},{"key":"525_CR30","doi-asserted-by":"publisher","unstructured":"Atienza, R.: Vision transformer for fast and efficient scene text recognition. In: International conference on document analysis and recognition, pp. 319\u2013334 (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_21","DOI":"10.1007\/978-3-030-86549-8_21"},{"key":"525_CR31","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning transferable visual models from natural language supervision. In: proceedings of the 38th international conference on machine learning, vol. 139, pp. 8748\u20138763 (2021)"},{"key":"525_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, S., Quan, R., Zhu, L., Yang, Y.: Clip4str: A simple baseline for scene text recognition with pre-trained vision-language model. arXiv preprint arXiv:2305.14014 (2023)","DOI":"10.1109\/TIP.2024.3512354"},{"key":"525_CR33","doi-asserted-by":"publisher","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE conference on computer vision and pattern recognition (2016). https:\/\/doi.org\/10.48550\/arXiv.1604.06646","DOI":"10.48550\/arXiv.1604.06646"},{"key":"525_CR34","doi-asserted-by":"publisher","unstructured":"Zhan, F., Lu, S., Xue, C.: Verisimilar image synthesis for accurate detection and recognition of texts in scenes. In: Proceedings of the European conference on computer vision (2018). https:\/\/doi.org\/10.48550\/arXiv.1807.03021","DOI":"10.48550\/arXiv.1807.03021"},{"issue":"02","key":"525_CR35","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2737-0","volume":"63","author":"M Liao","year":"2020","unstructured":"Liao, M., Song, B., Long, S., He, M., Yao, C., Bai, X.: Synthtext3d: Synthesizing scene text images from 3d virtual worlds. Sci. China Inf. Sci. 63(02), 120105 (2020). https:\/\/doi.org\/10.1007\/s11432-019-2737-0","journal-title":"Sci. China Inf. Sci."},{"key":"525_CR36","doi-asserted-by":"publisher","unstructured":"Rang, M., Bi, Z., Liu, C., Wang, Y., Han, K.: An empirical study of scaling law for scene text recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp. 15619\u201315629 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01479","DOI":"10.1109\/CVPR52733.2024.01479"},{"key":"525_CR37","doi-asserted-by":"publisher","unstructured":"Bautista, D., Atienza, R.: Scene text recognition with permuted autoregressive sequence models. In: Proceedings of the European conference on computer vision, pp. 178\u2013196 (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_11","DOI":"10.1007\/978-3-031-19815-1_11"},{"key":"525_CR38","doi-asserted-by":"publisher","unstructured":"Baek, J., Kim, G., Lee, J., Park, S., Han, D., Yun, S., Oh, S.J., Lee, H.: What is wrong with scene text recognition model comparisons? dataset and model analysis. In: Proceedings of the IEEE\/CVF international conference on computer vision (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00481","DOI":"10.1109\/ICCV.2019.00481"},{"key":"525_CR39","doi-asserted-by":"publisher","unstructured":"Lee, H.-S., Yoon, Y., Jang, P.H., Choi, C.: Popeval: A character-level approach to end-to-end evaluation compatible with word-level benchmark dataset. In: International conference on document analysis and recognition, pp. 1207\u20131213 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00195","DOI":"10.1109\/ICDAR.2019.00195"},{"key":"525_CR40","doi-asserted-by":"publisher","unstructured":"Du, Y., Chen, Z., Jia, C., Yin, X., Zheng, T., Li, C., Du, Y., Jiang, Y.-G.: Svtr: Scene text recognition with a single visual model. In: Proceedings of the thirty-first international joint conference on artificial intelligence, IJCAI-22, pp. 884\u2013890 (2022). https:\/\/doi.org\/10.24963\/ijcai.2022\/124","DOI":"10.24963\/ijcai.2022\/124"},{"key":"525_CR41","doi-asserted-by":"publisher","unstructured":"Ilharco, G., Wortsman, M., Wightman, R., Gordon, C., Carlini, N., Taori, R., Dave, A., Shankar, V., Namkoong, H., Miller, J., Hajishirzi, H., Farhadi, A., Schmidt, L.: Openclip (2021). https:\/\/doi.org\/10.5281\/zenodo.5143773","DOI":"10.5281\/zenodo.5143773"},{"key":"525_CR42","doi-asserted-by":"publisher","unstructured":"Srinivasan, K., Raman, K., Chen, J., Bendersky, M., Najork, M.: Wit: Wikipedia-based image text dataset for multimodal multilingual machine learning. In: Proceedings of the 44th International ACM SIGIR conference on research and development in information retrieval, pp. 2443\u20132449 (2021). https:\/\/doi.org\/10.1145\/3404835.3463257","DOI":"10.1145\/3404835.3463257"}],"updated-by":[{"DOI":"10.1007\/s10032-025-00550-w","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T00:00:00Z","timestamp":1757289600000}}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-025-00525-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-025-00525-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-025-00525-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T06:50:08Z","timestamp":1775803808000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-025-00525-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,22]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["525"],"URL":"https:\/\/doi.org\/10.1007\/s10032-025-00525-x","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,22]]},"assertion":[{"value":"23 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 March 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2025","order":6,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":7,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1007\/s10032-025-00550-w","URL":"https:\/\/doi.org\/10.1007\/s10032-025-00550-w","order":9,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}