{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:52:09Z","timestamp":1771955529471,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609161","type":"print"},{"value":"9789819609178","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-0917-8_22","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:59:17Z","timestamp":1733558357000},"page":"383-399","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["KhmerST: A Low-Resource Khmer Scene Text Detection and\u00a0Recognition Benchmark"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4684-0416","authenticated-orcid":false,"given":"Vannkinh","family":"Nom","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9383-3842","authenticated-orcid":false,"given":"Souhail","family":"Bakkali","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9658-0833","authenticated-orcid":false,"given":"Muhammad Muzzamil","family":"Luqman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0123-439X","authenticated-orcid":false,"given":"Micka\u00ebl","family":"Coustaty","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5666-475X","authenticated-orcid":false,"given":"Jean-Marc","family":"Ogier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"22_CR1","doi-asserted-by":"publisher","first-page":"128044","DOI":"10.1109\/ACCESS.2023.3332361","volume":"11","author":"R Buoy","year":"2023","unstructured":"Buoy, R., Iwamura, M., Srun, S., Kise, K.: Toward a low-resource non-latin-complete baseline: an exploration of khmer optical character recognition. IEEE Access 11, 128044\u2013128060 (2023)","journal-title":"IEEE Access"},{"issue":"1","key":"22_CR2","doi-asserted-by":"publisher","first-page":"3","DOI":"10.46223\/HCMCOUJS.tech.en.12.1.2217.2022","volume":"12","author":"R Buoy","year":"2022","unstructured":"Buoy, R., Taing, N., Chenda, S., Kor, S.: Khmer printed character recognition using attention-based seq2seq network. Ho Chi Minh City Open University Journal Of Science-Engineering And Technology 12(1), 3\u201316 (2022)","journal-title":"Ho Chi Minh City Open University Journal Of Science-Engineering And Technology"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Te\u00f3filo\u00a0E de\u00a0Campos, Bodla\u00a0Rakesh Babu, and Manik Varma. Character recognition in natural images. In International conference on computer vision theory and applications, volume\u00a01, pages 273\u2013280. SCITEPRESS, 2009","DOI":"10.5220\/0001770102730280"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Yasuhisa Fujii, Karel Driesen, Jonathan Baccash, Ash Hurst, and Ashok\u00a0C Popat. Sequence-to-label script identification for multilingual ocr. In 2017 14th IAPR international conference on document analysis and recognition (ICDAR), volume\u00a01, pages 161\u2013168. IEEE, 2017","DOI":"10.1109\/ICDAR.2017.35"},{"key":"22_CR5","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.patcog.2017.04.027","volume":"70","author":"L G\u00f3mez","year":"2017","unstructured":"G\u00f3mez, L., Karatzas, D.: Textproposals: a text-specific selective search algorithm for word spotting in the wild. Pattern Recogn. 70, 60\u201374 (2017)","journal-title":"Pattern Recogn."},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Tong He, Weilin Huang, Yu\u00a0Qiao, and Jian Yao.Text-attentional convolutional neural network for scene text detection.IEEE transactions on image processing, 25(6):2529\u20132541, 2016","DOI":"10.1109\/TIP.2016.2547588"},{"key":"22_CR7","unstructured":"Joshua Horton, Makara Sok, Marc Durdin, and Rasmey Ty.Spoof-vulnerable rendering in khmer unicode implementations.In Proceedings of the Sixth Asian Conference on Information Systems, pages 177\u2013180, 2017"},{"key":"22_CR8","unstructured":"Muhammad Hussain. Yolov5, yolov8 and yolov10: The go-to detectors for real-time vision. arXiv preprint arXiv:2407.02988, 2024"},{"key":"22_CR9","unstructured":"Max Jaderberg, Karen Simonyan, Andrea Vedaldi, and Andrew Zisserman. Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227, 2014"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Jehyun Jung, SeongHun Lee, Min\u00a0Su Cho, and Jin\u00a0Hyung Kim. Touch tt: Scene text extractor using touchscreen interface. ETRI Journal, 33(1):78\u201388, 2011","DOI":"10.4218\/etrij.11.1510.0029"},{"key":"22_CR11","unstructured":"Chen-Yu Lee and Simon Osindero. Recursive recurrent nets with attention modeling for ocr in the wild. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2231\u20132239, 2016"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Li, M., Lv, T., Chen, J., Cui, L., Yijuan, L., Florencio, D., Zhang, C., Li, Z., Wei, F.: Trocr: Transformer-based optical character recognition with pre-trained models. In Proceedings of the AAAI Conference on Artificial Intelligence 37, 13094\u201313102 (2023)","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Lucas, S.M., Panaretos, A., Sosa, L., Tang, A., Wong, S., Young, R., Ashida, K., Nagai, H., Okamoto, M., Yamamoto, H., Icdar, et al.: robust reading competitions: entries, results, and future directions. IJDAR 7(105\u2013122), 2005 (2003)","DOI":"10.1007\/s10032-004-0134-3"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Ashee Mahajan, Anand Nayyar, Rachna Jain, and Preeti Nagrath. Natural scenes\u2019 text detection and recognition using cnn and pytesseract. In The Fifth International Conference on Safety and Security with IoT: SaSeIoT 2021, pages 159\u2013171. Springer, 2022","DOI":"10.1007\/978-3-030-94285-4_10"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Anand Mishra, Karteek Alahari, and CV\u00a0Jawahar.Scene text recognition using higher order language priors.In BMVC-British machine vision conference. BMVA, 2012","DOI":"10.5244\/C.26.127"},{"key":"22_CR16","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Baolin, W., Ng, A.Y., Reading digits in natural images with unsupervised feature learning. In NIPS workshop on deep learning and unsupervised feature learning, volume, et al.: page 7, p. 2011. Granada, Spain (2011)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Siyang Qin and Roberto Manduchi. Cascaded segmentation-detection networks for word-level text spotting. In 2017 14th IAPR international conference on document analysis and recognition (ICDAR), volume\u00a01, pages 1275\u20131282. IEEE, 2017","DOI":"10.1109\/ICDAR.2017.210"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 779\u2013788, 2016","DOI":"10.1109\/CVPR.2016.91"},{"key":"22_CR19","unstructured":"Saurabh Saoji, A\u00a0Eqbal, and B\u00a0Vidyapeeth. Text recognition and detection from images using pytesseract. J Interdiscip Cycle Res, 13:1674\u20131679, 2021"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Kumar Shwait, Preetpal\u00a0Kaur Buttar, and Rahul Gautam. Detection and recognition of hindi text from natural scenes and its transliteration to english. International Journal of Advanced Research in Computer Science, 13(2), 2022","DOI":"10.26483\/ijarcs.v13i2.6808"},{"key":"22_CR21","doi-asserted-by":"publisher","unstructured":"Smith, R., Gu, C., Lee, D.-S., Hu, H., Unnikrishnan, R., Ibarz, J., Arnoud, S., Lin, S.: End-to-End Interpretation of the French Street Name Signs Dataset. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9913, pp. 411\u2013426. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46604-0_30","DOI":"10.1007\/978-3-319-46604-0_30"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Pongsametrey Sok and Nguonly Taing. Support vector machine (svm) based classifier for khmer printed character-set recognition. In Signal and information processing association annual summit and conference (APSIPA), 2014 Asia-Pacific, pages 1\u20139. IEEE, 2014","DOI":"10.1109\/APSIPA.2014.7041823"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Dona Valy, Michel Verleysen, and Sophea Chhun. Text recognition on khmer historical documents using glyph class map generation with encoder-decoder model. In ICPRAM, pages 749\u2013756, 2019","DOI":"10.5220\/0007555507490756"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Dona Valy, Michel Verleysen, and Sophea Chhun. Data augmentation and text recognition on khmer historical manuscripts. In 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pages 73\u201378. IEEE, 2020","DOI":"10.1109\/ICFHR2020.2020.00024"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Dona Valy, Michel Verleysen, Sophea Chhun, and Jean-Christophe Burie. A new khmer palm leaf manuscript dataset for document analysis and recognition: Sleukrith set. In Proceedings of the 4th International Workshop on Historical Document Imaging and Processing, pages 1\u20136, 2017","DOI":"10.1145\/3151509.3151510"},{"key":"22_CR26","unstructured":"Andreas Veit, Tomas Matera, Lukas Neumann, Jiri Matas, and Serge Belongie. Coco-text: Dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140, 2016"},{"key":"22_CR27","unstructured":"Tao Wang, David\u00a0J Wu, Adam Coates, and Andrew\u00a0Y Ng. End-to-end text recognition with convolutional neural networks. In Proceedings of the 21st international conference on pattern recognition (ICPR2012), pages 3304\u20133308. IEEE, 2012"},{"key":"22_CR28","doi-asserted-by":"crossref","unstructured":"Yuan, T.-L., Zhu, Z., Kun, X., Li, C.-J., Tai-Jiang, M., Shi-Min, H.: A large chinese text dataset in the wild. J. Comput. Sci. Technol. 34, 509\u2013521 (2019)","DOI":"10.1007\/s11390-019-1923-y"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Zhang Yun-An, Pan Ziheng, Dui Hongyan, and Bai Guanghan. Yolov3-tesseract model for improved intelligent form recognition. Recent Advances in Computer Science and Communications (Formerly: Recent Patents on Computer Science), 14(6):1833\u20131842, 2021","DOI":"10.2174\/2666255813666191204141610"},{"key":"22_CR30","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","volume":"10","author":"Y Zhu","year":"2016","unstructured":"Zhu, Y., Yao, C., Bai, X.: Scene text detection and recognition: Recent advances and future trends. Front. Comp. Sci. 10, 19\u201336 (2016)","journal-title":"Front. Comp. Sci."}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0917-8_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:29:26Z","timestamp":1733560166000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0917-8_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609161","9789819609178"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0917-8_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","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":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}