{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T20:34:39Z","timestamp":1773002079983,"version":"3.50.1"},"reference-count":34,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T00:00:00Z","timestamp":1764374400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T00:00:00Z","timestamp":1764374400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0116100"],"award-info":[{"award-number":["2022ZD0116100"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["CAAI Trans on Intel Tech"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Increased awareness of Tibetan cultural preservation, along with technological advancements, has led to significant efforts in academic research on Tibetan. However, the structural complexity of the Tibetan language and limited labeled handwriting data impede advancements in Optical Character Recognition (OCR) and other applications. To address these challenges, this paper proposes an innovative Tibetan data augmentation technique, using Generative Adversarial Networks (GANs) to synthesise arbitrary handwriting images in variable calligraphic styles based on inputs. Moreover, our method leverages a Real\u2010Fake Cross Inputs Strategy during training to enhance generation diversity and improve model generalisability in generating handwritten text beyond the training set and pre\u2010defined corpus. The model was trained on three Tibetan handwriting datasets, including Um\u00ea style numerals, Uchen style consonants, and Khyug\u2010yig style words. Experimental results demonstrate that the model successfully generates realistic and recognisable Tibetan numeral and consonant handwriting, achieving Fr\u00e9chet Inception Distance (FID) scores of 14.45 and 27.63, respectively. The proposed method's effectiveness in augmenting OCR models was validated as evidenced by a reduced OCR Word Error Rate (WER) on the augmented datasets.<\/jats:p>","DOI":"10.1049\/cit2.70078","type":"journal-article","created":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T17:04:36Z","timestamp":1764435876000},"page":"55-65","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Tibetan Data Augmentation via GAN\u2010Based Handwritten Text Generation"],"prefix":"10.1049","volume":"11","author":[{"given":"Dorje","family":"Tashi","sequence":"first","affiliation":[{"name":"School of Information Science and Technology Tibet University  Lhasa China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1459-1888","authenticated-orcid":false,"given":"Bingtian","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering University of Electronic Science and Technology of China  Chengdu China"}]},{"given":"Tianying","family":"Sheng","sequence":"additional","affiliation":[{"name":"School of Computer Science University of Sydney  Sydney New South Wales Australia"}]},{"given":"Yongbin","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering University of Electronic Science and Technology of China  Chengdu China"}]},{"given":"Xiangxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering University of Electronic Science and Technology of China  Chengdu China"}]},{"given":"Jin","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology Tibet University  Lhasa China"}]},{"given":"Lobsang","family":"Yeshi","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology Tibet University  Lhasa China"}]},{"given":"Rinchen","family":"Dongrub","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology Tibet University  Lhasa China"}]},{"given":"Thupten","family":"Tsering","sequence":"additional","affiliation":[{"name":"School of Computer Qinghai Normal University  Xining China"}]},{"given":"Nyima","family":"Tashi","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology Tibet University  Lhasa China"}]}],"member":"265","published-online":{"date-parts":[[2025,11,29]]},"reference":[{"key":"e_1_2_9_2_1","article-title":"Algorithm Study on Feature Extracting of Tibetan Character Recognition","author":"Wang W.","year":"1999","journal-title":"Journal of Northwest Minorities University (Natural Science)"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR.2014.60"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.16249\/j.cnki.2096\u20104617.2019.04.013"},{"key":"e_1_2_9_5_1","article-title":"Multi\u2010Font\u00a0Tibetan Printed Character Recognition Based on Neural Network","volume":"10","author":"San Z. J.","year":"2022","journal-title":"Computer Simulation"},{"issue":"2","key":"e_1_2_9_6_1","article-title":"Research on Property of Tibetan Characters as Information Processing","volume":"9","author":"Jiang D.","year":"1995","journal-title":"Journal of Chinese Information Processing"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/IALP57159.2022.9961323"},{"key":"e_1_2_9_8_1","article-title":"Overview of the First National Forum on Collation and Research of Tibetan Ancient Texts","volume":"2","author":"Dorjee S.","year":"2018","journal-title":"China Tibetology"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.3724\/2096\u20107004.di.2024.0048"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.3969\/j.issn.1003\u20100077.2017.05.009"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/PRML59573.2023.10348273"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.3156\/JSOFT.29.5_177_2"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01418-6_10"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.37421\/2157\u20107145.2023.14.553"},{"key":"e_1_2_9_15_1","unstructured":"A.Brock J.Donahue K.Simonyan \u201cLarge Scale GAN Training for High Fidelity Natural Image Synthesis \u201d arXiv:1809.11096 (2018)."},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.11239"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00083"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00438"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_17"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00112"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16917"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550070"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00579"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02151"},{"key":"e_1_2_9_25_1","first-page":"410","volume-title":"European Conference on Computer Vision","author":"Dai G.","year":"2024"},{"key":"e_1_2_9_26_1","unstructured":"M.MirzaandS.Osindero \u201cConditional Generative Adversarial Nets \u201d arXiv:1411.1784 (2014)."},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1707.00683"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143891"},{"key":"e_1_2_9_29_1","unstructured":"J. C. F.Gauss.Tibetanmnist(2018) https:\/\/www.heywhale.com\/mw\/dataset\/5bfe734a954d6e0010683839."},{"key":"e_1_2_9_30_1","unstructured":"Crxm.Tibetan Handwriting Consonants Dataset(2020) https:\/\/www.heywhale.com\/mw\/dataset\/5eb0d52f366f4d002d756691."},{"key":"e_1_2_9_31_1","unstructured":"D. P.Kingma J.Ba \u201cAdam: A Method for Stochastic Optimization \u201d arXiv:1412.6980 (2014)."},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.08500"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2003.819861"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1606.03498"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/tfuzz.2024.3397697"}],"container-title":["CAAI Transactions on Intelligence Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70078","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/cit2.70078","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/cit2.70078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T18:10:36Z","timestamp":1772993436000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/cit2.70078"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,29]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1049\/cit2.70078"],"URL":"https:\/\/doi.org\/10.1049\/cit2.70078","archive":["Portico"],"relation":{},"ISSN":["2468-6557","2468-2322"],"issn-type":[{"value":"2468-6557","type":"print"},{"value":"2468-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,29]]},"assertion":[{"value":"2024-08-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}