{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:02:05Z","timestamp":1775066525804,"version":"3.50.1"},"publisher-location":"Cham","reference-count":52,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031416842","type":"print"},{"value":"9783031416859","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-41685-9_2","type":"book-chapter","created":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T14:04:59Z","timestamp":1692367499000},"page":"20-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Improving Handwritten OCR with\u00a0Training Samples Generated by\u00a0Glyph Conditional Denoising Diffusion Probabilistic Model"],"prefix":"10.1007","author":[{"given":"Haisong","family":"Ding","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bozhi","family":"Luan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongnan","family":"Gui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Huo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,19]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Alonso, E., Moysset, B., Messina, R.O.: Adversarial generation of handwritten text images conditioned on sequences. In: Proceedings of ICDAR, pp. 481\u2013486 (2019)","DOI":"10.1109\/ICDAR.2019.00083"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Barrere, K., Soullard, Y., Lemaitre, A., Co\u00fcasnon, B.: A light Transformer-based architecture for handwritten text recognition. In: Proceedings of DAS, pp. 275\u2013290 (2022)","DOI":"10.1007\/978-3-031-06555-2_19"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Bhunia, A.K., Khan, S.H., Cholakkal, H., Anwer, R.M., Khan, F.S., Shah, M.: Handwriting transformers. In: Proceedings of ICCV, pp. 1066\u20131074 (2021)","DOI":"10.1109\/ICCV48922.2021.00112"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Bhunia, A.K., Das, A., Bhunia, A.K., Kishore, P.S.R., Roy, P.P.: Handwriting recognition in low-resource scripts using adversarial learning. In: Proceedings of CVPR, pp. 4767\u20134776 (2020)","DOI":"10.1109\/CVPR.2019.00490"},{"key":"2_CR5","unstructured":"Davis, B.L., Morse, B.S., Price, B.L., Tensmeyer, C., Wigington, C., Jain, R.: Text and style conditioned GAN for the generation of offline-handwriting lines. In: Proceedings of BMVC (2020)"},{"key":"2_CR6","unstructured":"Dhariwal, P., Nichol, A.Q.: Diffusion models beat GANs on image synthesis. In: Proceedings of NeurIPS, vol. 34, pp. 8780\u20138794 (2021)"},{"key":"2_CR7","unstructured":"Diaz, D.H., Qin, S., Ingle, R.R., Fujii, Y., Bissacco, A.: Rethinking text line recognition models. CoRR abs\/2104.07787 (2021)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Dutta, K., Krishnan, P., Mathew, M., Jawahar, C.V.: Improving CNN-RNN hybrid networks for handwriting recognition. In: Proceedings of ICFHR, pp. 80\u201385 (2018)","DOI":"10.1109\/ICFHR-2018.2018.00023"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"d\u2019Arce, R., Norton, T., Hannuna, S., Cristianini, N.: Self-attention networks for non-recurrent handwritten text recognition. In: Proceedings of ICFHR, pp. 389\u2013403 (2022)","DOI":"10.1007\/978-3-031-21648-0_27"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Etter, D., Rawls, S., Carpenter, C., Sell, G.: A synthetic recipe for OCR. In: Proceedings of ICDAR, pp. 864\u2013869 (2019)","DOI":"10.1109\/ICDAR.2019.00143"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Fogel, S., Averbuch-Elor, H., Cohen, S., Shai Mazor, R.L.: ScrabbleGAN: semi-supervised varying length handwritten text generation. In: Proceedings of CVPR, pp. 4323\u20134332 (2020)","DOI":"10.1109\/CVPR42600.2020.00438"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Gan, J., Wang, W.: HiGAN: handwriting imitation conditioned on arbitrary-length texts and disentangled styles. In: Proceedings of AAAI, pp. 7484\u20137492 (2021)","DOI":"10.1609\/aaai.v35i9.16917"},{"key":"2_CR13","unstructured":"Goodfellow, I.J., et al.: Generative adversarial nets. In: Proceedings of NIPS, pp. 2672\u20132680 (2014)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F.J., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of ICML, pp. 369\u2013376 (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Guan, M., Ding, H., Chen, K., Huo, Q.: Improving handwritten OCR with augmented text line images synthesized from online handwriting samples by style-conditioned GAN. In: Proceedings of ICFHR, pp. 151\u2013156 (2020)","DOI":"10.1109\/ICFHR2020.2020.00037"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Gui, D., Chen, K., Ding, H., Huo, Q.: Zero-shot generation of training data with denoising diffusion probabilistic model for handwritten Chinese character recognition. In: Proceedings of ICDAR (2023)","DOI":"10.1007\/978-3-031-41679-8_20"},{"key":"2_CR17","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Proceedings of NIPS, vol. 30, pp. 6626\u20136637 (2017)"},{"key":"2_CR18","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Proceedings of NeurIPS, vol. 33, pp. 6840\u20136851 (2020)"},{"key":"2_CR19","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: Proceedings of NeurIPS, Workshop on Deep Generative Models and Downstream Applications (2021)"},{"key":"2_CR20","unstructured":"Song, J., Chenlin Meng, S.E.: Denoising diffusion implicit models. In: Proceedings of ICLR (2021)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Kahn, J., Lee, A., Hannun, A.Y.: Self-training for end-to-end speech recognition. In: Proceedings of ICASSP, pp. 7084\u20137088 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054295"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Kang, L., Riba, P., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: Distilling content from style for handwritten word recognition. In: Proceedings of ICFHR, pp. 139\u2013144 (2020)","DOI":"10.1109\/ICFHR2020.2020.00035"},{"key":"2_CR23","doi-asserted-by":"publisher","first-page":"8846","DOI":"10.1109\/TPAMI.2021.3122572","volume":"44","author":"L Kang","year":"2022","unstructured":"Kang, L., Riba, P., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: Content and style aware generation of text-line images for handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intell. 44, 8846\u20138860 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108766","volume":"129","author":"L Kang","year":"2022","unstructured":"Kang, L., Riba, P., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: Pay attention to what you read: non-recurrent handwritten text-line recognition. Pattern Recogn. 129, 108799 (2022)","journal-title":"Pattern Recogn."},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Kang, L., Riba, P., Wang, Y., Rusi\u00f1ol, M., Forn\u00e9s, A., Villegas, M.: GANwriting: content-conditioned generation of styled handwritten word images. In: Proceedings of ECCV, vol. 23, pp. 273\u2013289 (2020)","DOI":"10.1007\/978-3-030-58592-1_17"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Kang, L., Rusi\u00f1ol, M., Forn\u00e9s, A., Riba, P., Villegas, M.: Unsupervised adaptation for synthetic-to-real handwritten word recognition. In: Proceedings of WACV, pp. 3491\u20133500 (2020)","DOI":"10.1109\/WACV45572.2020.9093392"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of CVPR, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"2_CR28","unstructured":"Li, M., e al.: TrOCR: transformer-based optical character recognition with pre-trained models. CoRR abs\/2109.10282 (2022)"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Gool, L.V.: Repaint: inpainting using denoising diffusion probabilistic models. In: Proceedings of CVPR, pp. 11451\u201311461 (2022)","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"2_CR30","unstructured":"Luhman, T., Luhman, E.: Diffusion models for handwriting generation. CoRR abs\/2011.06704 (2020)"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Luo, C., Zhu, Y., Jin, L., Li, Z., Peng, D.: SLOGAN: handwriting style synthesis for arbitrary-length and out-of-vocabulary text. IEEE Trans. Neural Netw. Learn. Syst., 1\u201313 (2022)","DOI":"10.1109\/TNNLS.2022.3151477"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Luo, C., Zhu, Y., Jin, L., Wang, Y.: Learn to augment: joint data augmentation and network optimization for text recognition. In: Proceedings of CVPR, pp. 13743\u201313752 (2020)","DOI":"10.1109\/CVPR42600.2020.01376"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Ly, N.T., Nguyen, H.T., Nakagawa, M.: 2D self-attention convolutional recurrent network for offline handwritten text recognition. In: Proceedings of ICDAR, pp. 191\u2013204 (2021)","DOI":"10.1007\/978-3-030-86549-8_13"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Marti, U., Bunke, H.: The IAM-database: an English sentence database for offline handwriting recognition. Int. J. Doc. Anal. Recogn., pp. 39\u201346 (2002)","DOI":"10.1007\/s100320200071"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Michael, J., Labahn, R., Gr\u00fcning, T., Z\u00f6llner, J.: Evaluating sequence-to-sequence models for handwritten text recognition. In: Proceedings of ICDAR, pp. 1286\u20131293 (2019)","DOI":"10.1109\/ICDAR.2019.00208"},{"key":"2_CR36","unstructured":"Mirza, M., Osindero, S.: Conditional generative adversarial nets. Comput. Sci., pp. 2672\u20132680 (2014)"},{"key":"2_CR37","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: Proceedings of ICML, pp. 8162\u20138171 (2021)"},{"key":"2_CR38","unstructured":"Nichol, A.Q., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: Proceedings of ICML, pp. 16784\u201316804 (2022)"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Park, D.S., et al.: Improved noisy student training for automatic speech recognition. In: Proceedings of Interspeech, pp. 2817\u20132821 (2020)","DOI":"10.21437\/Interspeech.2020-1470"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Perez, E., Strub, F., de Vries, H., Dumoulin, V., Courville, A.C.: FiLM: visual reasoning with a general conditioning layer. In: Proceedings of AAAI, pp. 3942\u20133951 (2018)","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Puigcerver, J.: Are multidimensional recurrent layers really necessary for handwritten text recognition? In: Proceedings of ICDAR, pp. 67\u201372 (2017)","DOI":"10.1109\/ICDAR.2017.20"},{"key":"2_CR42","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. CoRR abs\/2204.06125 (2022)"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. CoRR abs\/2205.11487 (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"2_CR44","unstructured":"Sohl-Dickstein, J., Weiss, E.A., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: Proceedings of ICML, pp. 2256\u20132265 (2015)"},{"key":"2_CR45","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: Proceedings of ICLR (2021)"},{"key":"2_CR46","unstructured":"Wang, T., et al.: Pretraining is all you need for image-to-image translation. CoRR abs\/2205.12952 (2022)"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, H., Sun, S., Wei, H.: An approach based on Transformer and deformable convolution for realistic handwriting samples generation. In: Proceedings of ICPR, pp. 1457\u20131463 (2022)","DOI":"10.1109\/ICPR56361.2022.9956551"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Wick, C., Z\u00f6llner, J., Gr\u00fcning, T.: Transformer for handwritten text recognition using bidirectional post-decoding. In: Proceedings of ICDAR, pp. 112\u2013126 (2021)","DOI":"10.1007\/978-3-030-86334-0_8"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Wick, C., Z\u00f6llner, J., Gr\u00fcning, T.: Rescoring sequence-to-sequence models for text line recognition with CTC-prefixes. In: Proceedings of DAS, pp. 260\u2013274 (2022)","DOI":"10.1007\/978-3-031-06555-2_18"},{"key":"2_CR50","doi-asserted-by":"crossref","unstructured":"Wolf, F., Fink, G.A.: Combining self-training and minimal annotations for handwritten word recognition. In: Proceedings of ICFHR, pp. 300\u2013315 (2022)","DOI":"10.1007\/978-3-031-21648-0_21"},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Wolf, F., Fink, G.A.: Self-training of handwritten word recognition for synthetic-to-real adaptation. In: Proceedings of ICPR, pp. 3885\u20133892 (2022)","DOI":"10.1109\/ICPR56361.2022.9956168"},{"key":"2_CR52","doi-asserted-by":"crossref","unstructured":"Zdenek, J., Nakayama, H.: JokerGAN: memory-efficient model for handwritten text generation with text line awareness. In: Proceedings of ACM Multimedia, pp. 5655\u20135663 (2021)","DOI":"10.1145\/3474085.3475713"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition - ICDAR 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-41685-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T08:14:55Z","timestamp":1702973695000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-41685-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031416842","9783031416859"],"references-count":52,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-41685-9_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"19 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"San Jos\u00e9, CA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icdar2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"316","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"154","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.89","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.50","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Number and type of other papers accepted : IJDAR track papers","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}