{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T11:12:09Z","timestamp":1783768329774,"version":"3.55.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T00:00:00Z","timestamp":1778025600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476088"],"award-info":[{"award-number":["62476088"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["20DZ2254400"],"award-info":[{"award-number":["20DZ2254400"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s00530-026-02355-1","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:16:09Z","timestamp":1778048169000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scene text image super-resolution algorithm based on directional feature modeling"],"prefix":"10.1007","volume":"32","author":[{"given":"Qin","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yubo","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanbin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,6]]},"reference":[{"issue":"1","key":"2355_CR1","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2021","unstructured":"Long, S., He, X., Yao, C.: Scene text detection and recognition: The deep learning era. Int. J. Comput. Vision 129(1), 161\u2013184 (2021)","journal-title":"Int. J. Comput. Vision"},{"issue":"6","key":"2355_CR2","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1109\/TASSP.1981.1163711","volume":"29","author":"R Keys","year":"2003","unstructured":"Keys, R.: Cubic convolution interpolation for digital image processing. IEEE Trans. Acoust. Speech Signal Process. 29(6), 1153\u20131160 (2003)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"1","key":"2355_CR3","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/TMI.1983.4307610","volume":"2","author":"JA Parker","year":"2007","unstructured":"Parker, J.A., Kenyon, R.V., Troxel, D.E.: Comparison of interpolating methods for image resampling. IEEE Trans. Med. Imaging 2(1), 31\u201339 (2007)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"2","key":"2355_CR4","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","volume":"38","author":"C Dong","year":"2015","unstructured":"Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295\u2013307 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2355_CR5","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Liu, X., Wang, W., Liang, D., Shen, C., Bai, X.: Scene text image super-resolution in the wild. In: European conference on computer vision, pp. 650\u2013666 (2020). Springer","DOI":"10.1007\/978-3-030-58607-2_38"},{"key":"2355_CR6","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TIP.2023.3237002","volume":"32","author":"J Ma","year":"2023","unstructured":"Ma, J., Guo, S., Zhang, L.: Text prior guided scene text image super-resolution. IEEE Trans. Image Process. 32, 1341\u20131353 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"2355_CR7","doi-asserted-by":"crossref","unstructured":"Ma, J., Liang, Z., Zhang, L.: A text attention network for spatial deformation robust scene text image super-resolution. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 5911\u20135920 (2022)","DOI":"10.1109\/CVPR52688.2022.00582"},{"key":"2355_CR8","doi-asserted-by":"crossref","unstructured":"Guo, H., Dai, T., Meng, G., Xia, S.-T.: Towards robust scene text image super-resolution via explicit location enhancement. arXiv preprint arXiv:2307.09749 (2023)","DOI":"10.24963\/ijcai.2023\/87"},{"key":"2355_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L., Wu, J., Liu, Y.: Leveraging text semantics for enhanced scene text image super-resolution. Intell. Converged Netw. (2025)","DOI":"10.23919\/ICN.2025.0009"},{"key":"2355_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111513","volume":"164","author":"B Liu","year":"2025","unstructured":"Liu, B., Yang, Z., Chiu, C., Xiong, Y.: Textdiff: enhancing scene text image super-resolution with mask-guided residual diffusion models. Pattern Recogn. 164, 111513 (2025)","journal-title":"Pattern Recogn."},{"key":"2355_CR11","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhang, J., Li, H., Wang, Z., Hou, L., Zou, D., Bian, L.: Diffusion-based blind text image super-resolution. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 25827\u201325836 (2024)","DOI":"10.1109\/CVPR52733.2024.02440"},{"issue":"11","key":"2355_CR12","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2016","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2355_CR13","doi-asserted-by":"crossref","unstructured":"Ranjan, P., Hans, S., Ismail, S.: Next-gen imaging: the power of hyperspectral data and autoencoders. In: International conference on artificial intelligence and speech technology, pp. 29\u201341 (2024). Springer","DOI":"10.1007\/978-3-031-91340-2_3"},{"issue":"4","key":"2355_CR14","doi-asserted-by":"publisher","first-page":"63","DOI":"10.3390\/fintech4040063","volume":"4","author":"P Ranjan","year":"2025","unstructured":"Ranjan, P., Itani, R., Faccia, A.: An interpretable 1d-cnn framework for stock price forecasting: a comparative study with lstm and arima. FinTech 4(4), 63 (2025)","journal-title":"FinTech"},{"key":"2355_CR15","doi-asserted-by":"crossref","unstructured":"Hans, S., Ranjan, P., Ismail, S.: Redefining vision tasks: the power of transformers in classification, detection, and segmentation. In: International conference on artificial intelligence and speech technology, pp. 42\u201353 (2025). Springer","DOI":"10.1007\/978-3-031-91340-2_4"},{"key":"2355_CR16","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. arXiv preprint arXiv:2111.00396 (2021)"},{"key":"2355_CR17","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. In: First conference on language modeling (2024)"},{"key":"2355_CR18","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: efficient visual representation learning with bidirectional state space model. arXiv preprint arXiv:2401.09417 (2024)"},{"key":"2355_CR19","doi-asserted-by":"publisher","first-page":"103031","DOI":"10.52202\/079017-3273","volume":"37","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Jiao, J., Liu, Y.: Vmamba: visual state space model. Adv. Neural. Inf. Process. Syst. 37, 103031\u2013103063 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2355_CR20","doi-asserted-by":"crossref","unstructured":"Guo, H., Guo, Y., Zha, Y., Zhang, Y., Li, W., Dai, T., Xia, S.-T., Li, Y.: Mambairv2: Attentive state space restoration. In: Proceedings of the computer vision and pattern recognition conference, pp. 28124\u201328133 (2025)","DOI":"10.1109\/CVPR52734.2025.02619"},{"key":"2355_CR21","doi-asserted-by":"crossref","unstructured":"Park, J., Kwon, Y., Kim, J.H.: An example-based prior model for text image super-resolution. In: Eighth international conference on document analysis and recognition (ICDAR\u201905), pp. 374\u2013378 (2005). IEEE","DOI":"10.1109\/ICDAR.2005.49"},{"key":"2355_CR22","doi-asserted-by":"crossref","unstructured":"Walha, R., Drira, F., Lebourgeois, F., Alimi, A.M.: Super-resolution of single text image by sparse representation. In: Proceeding of the workshop on document analysis and recognition, pp. 22\u201329 (2012)","DOI":"10.1145\/2432553.2432558"},{"key":"2355_CR23","unstructured":"Dong, C., Zhu, X., Deng, Y., Loy, C.C., Qiao, Y.: Boosting optical character recognition: a super-resolution approach. arXiv preprint arXiv:1506.02211 (2015)"},{"key":"2355_CR24","unstructured":"Wang, W., Xie, E., Sun, P., Wang, W., Tian, L., Shen, C., Luo, P.: Textsr: content-aware text super-resolution guided by recognition. arXiv preprint arXiv:1909.07113 (2019)"},{"key":"2355_CR25","doi-asserted-by":"crossref","unstructured":"Zhao, M., Wang, M., Bai, F., Li, B., Wang, J., Zhou, S.: C3-stisr: Scene text image super-resolution with triple clues. arXiv preprint arXiv:2204.14044 (2022)","DOI":"10.24963\/ijcai.2022\/238"},{"key":"2355_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.129309","volume":"623","author":"M Zhao","year":"2025","unstructured":"Zhao, M., Xu, Y., Li, B., Wang, J., Guan, J., Zhou, S.: Hiren: towards higher supervision quality for better scene text image super-resolution. Neurocomputing 623, 129309 (2025)","journal-title":"Neurocomputing"},{"key":"2355_CR27","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Gao, L., Tang, Z., Wei, B.: Recognition-guided diffusion model for scene text image super-resolution. In: ICASSP 2024-2024 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 2940\u20132944 (2024). IEEE","DOI":"10.1109\/ICASSP48485.2024.10447585"},{"key":"2355_CR28","first-page":"1474","volume":"33","author":"A Gu","year":"2020","unstructured":"Gu, A., Dao, T., Ermon, S., Rudra, A., R\u00e9, C.: Hippo: recurrent memory with optimal polynomial projections. Adv. Neural. Inf. Process. Syst. 33, 1474\u20131487 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2355_CR29","doi-asserted-by":"crossref","unstructured":"Wang, Z., Li, C., Xu, H., Zhu, X., Li, H.: Mamba yolo: a simple baseline for object detection with state space model. In: Proceedings of the AAAI conference on artificial intelligence, vol. 39, pp. 8205\u20138213 (2025)","DOI":"10.1609\/aaai.v39i8.32885"},{"issue":"11","key":"2355_CR30","doi-asserted-by":"publisher","first-page":"8427","DOI":"10.1007\/s11760-024-03484-8","volume":"18","author":"H Tang","year":"2024","unstructured":"Tang, H., Huang, G., Cheng, L., Yuan, X., Tao, Q., Chen, X., Zhong, G., Yang, X.: Rm-unet: Unet-like mamba with rotational ssm module for medical image segmentation. SIViP 18(11), 8427\u20138443 (2024)","journal-title":"SIViP"},{"issue":"1","key":"2355_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/07474939108800194","volume":"10","author":"M Aoki","year":"1991","unstructured":"Aoki, M., Havenner, A.: State space modeling of multiple time series. Economet. Rev. 10(1), 1\u201359 (1991)","journal-title":"Economet. Rev."},{"key":"2355_CR32","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. Adv Neural Inform Process Syst 28 (2015)"},{"key":"2355_CR33","unstructured":"Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)"},{"key":"2355_CR34","doi-asserted-by":"crossref","unstructured":"Chen, J., Li, B., Xue, X.: Scene text telescope: Text-focused scene image super-resolution. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 12026\u201312035 (2021)","DOI":"10.1109\/CVPR46437.2021.01185"},{"key":"2355_CR35","doi-asserted-by":"crossref","unstructured":"Cai, J., Zeng, H., Yong, H., Cao, Z., Zhang, L.: Toward real-world single image super-resolution: a new benchmark and a new model. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 3086\u20133095 (2019)","DOI":"10.1109\/ICCV.2019.00318"},{"key":"2355_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, X., Chen, Q., Ng, R., Koltun, V.: Zoom to learn, learn to zoom. In: Proceedings of the IEEE\/CVF Conference on computer vision and pattern recognition, pp. 3762\u20133770 (2019)","DOI":"10.1109\/CVPR.2019.00388"},{"key":"2355_CR37","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., Matas, J., Neumann, L., Chandrasekhar, V.R., Lu, S., et al.: Icdar 2015 competition on robust reading. In: 2015 13th International conference on document analysis and recognition (ICDAR), pp. 1156\u20131160 (2015). IEEE","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"2355_CR38","doi-asserted-by":"crossref","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: 2011 international conference on computer vision, pp. 1457\u20131464 (2011). IEEE","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"2355_CR39","doi-asserted-by":"crossref","unstructured":"Phan, T.Q., Shivakumara, P., Tian, S., Tan, C.L.: Recognizing text with perspective distortion in natural scenes. In: Proceedings of the IEEE international conference on computer vision, pp. 569\u2013576 (2013)","DOI":"10.1109\/ICCV.2013.76"},{"key":"2355_CR40","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.patcog.2019.01.020","volume":"90","author":"C Luo","year":"2019","unstructured":"Luo, C., Jin, L., Sun, Z.: Moran: a multi-object rectified attention network for scene text recognition. Pattern Recogn. 90, 109\u2013118 (2019)","journal-title":"Pattern Recogn."},{"issue":"9","key":"2355_CR41","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1109\/TPAMI.2018.2848939","volume":"41","author":"B Shi","year":"2018","unstructured":"Shi, B., Yang, M., Wang, X., Lyu, P., Yao, C., Bai, X.: Aster: an attentional scene text recognizer with flexible rectification. IEEE Trans. Pattern Anal. Mach. Intell. 41(9), 2035\u20132048 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2355_CR42","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"2355_CR43","doi-asserted-by":"crossref","unstructured":"Ledig, C., Theis, L., Husz\u00e1r, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4681\u20134690 (2017)","DOI":"10.1109\/CVPR.2017.19"},{"key":"2355_CR44","doi-asserted-by":"crossref","unstructured":"Noguchi, C., Fukuda, S., Yamanaka, M.: Scene text image super-resolution based on text-conditional diffusion models. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp. 1485\u20131495 (2024)","DOI":"10.1109\/WACV57701.2024.00151"},{"key":"2355_CR45","doi-asserted-by":"crossref","unstructured":"TomyEnrique, L., Du, X., Liu, K., Yuan, H., Zhou, Z., Jin, C.: Efficient scene text image super-resolution with semantic guidance. In: ICASSP 2024-2024 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 3160\u20133164 (2024). IEEE","DOI":"10.1109\/ICASSP48485.2024.10446964"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02355-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02355-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02355-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T10:19:49Z","timestamp":1783765189000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02355-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,6]]},"references-count":45,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["2355"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02355-1","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,6]]},"assertion":[{"value":"17 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"280"}}