{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:11:36Z","timestamp":1767337896935,"version":"3.44.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032046291","type":"print"},{"value":"9783032046307","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T00:00:00Z","timestamp":1757980800000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-04630-7_20","type":"book-chapter","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T23:48:08Z","timestamp":1757980088000},"page":"351-368","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["WildKhmerST: A Comprehensive Dataset and\u00a0Benchmark for\u00a0Khmer Scene Text Detection and\u00a0Recognition in\u00a0the\u00a0Wild"],"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\/0009-0000-9878-4015","authenticated-orcid":false,"given":"Saly","family":"Keo","sequence":"additional","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\/0000-0002-1734-2205","authenticated-orcid":false,"given":"Mar\u00e7al","family":"Rossinyol","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":[[2025,9,16]]},"reference":[{"key":"20_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-030-86549-8_21","volume-title":"Document Analysis and Recognition \u2013 ICDAR 2021","author":"R Atienza","year":"2021","unstructured":"Atienza, R.: Vision transformer for fast and efficient scene text recognition. In: Llad\u00f3s, J., Lopresti, D., Uchida, S. (eds.) ICDAR 2021. LNCS, vol. 12821, pp. 319\u2013334. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-86549-8_21"},{"key":"20_CR2","doi-asserted-by":"crossref","unstructured":"Baek, J., et al.: What is wrong with scene text recognition model comparisons? Dataset and model analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4715\u20134723 (2019)","DOI":"10.1109\/ICCV.2019.00481"},{"key":"20_CR3","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1007\/978-3-031-19815-1_11","volume-title":"ECCV 2022","author":"D Bautista","year":"2022","unstructured":"Bautista, D., Atienza, R.: Scene text recognition with permuted autoregressive sequence models. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13688, pp. 178\u2013196. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_11"},{"key":"20_CR4","unstructured":"Buoy, R., Taing, N., Chenda, S.: Khmer word search: challenges, solutions, and semantic-aware search. arXiv preprint arXiv:2112.08918 (2021)"},{"key":"20_CR5","doi-asserted-by":"crossref","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":"20_CR6","doi-asserted-by":"crossref","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 Univ. J. Sci.-Eng. Technol. 12(1), 3\u201316 (2022)","journal-title":"Ho Chi Minh City Open Univ. J. Sci.-Eng. Technol."},{"key":"20_CR7","unstructured":"Buoy, R., Kor, S., Taing, N.: An end-to-end Khmer optical character recognition using sequence-to-sequence with attention. arXiv:abs\/2106.10875 (2021)"},{"issue":"1","key":"20_CR8","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1109\/TITS.2004.825086","volume":"5","author":"SL Chang","year":"2004","unstructured":"Chang, S.L., Chen, L.S., Chung, Y.C., Chen, S.W.: Automatic license plate recognition. IEEE Trans. Intell. Transp. Syst. 5(1), 42\u201353 (2004)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"20_CR9","doi-asserted-by":"crossref","unstructured":"Cho, W., Choi, S., Park, D.K., Shin, I., Choo, J.: Image-to-image translation via group-wise deep whitening-and-coloring transformation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10639\u201310647 (2019)","DOI":"10.1109\/CVPR.2019.01089"},{"issue":"4","key":"20_CR10","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/0262-8856(86)90048-X","volume":"4","author":"RH Davis","year":"1986","unstructured":"Davis, R.H., Lyall, J.: Recognition of handwritten characters\u2013a review. Image Vis. Comput. 4(4), 208\u2013218 (1986)","journal-title":"Image Vis. Comput."},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"de Campos, T.E., Babu, B.R., Varma, M.: Character recognition in natural images. In: International Conference on Computer Vision Theory and Applications, vol. 1, pp. 273\u2013280. SCITEPRESS (2009)","DOI":"10.5220\/0001770102730280"},{"key":"20_CR12","doi-asserted-by":"crossref","unstructured":"Dutta, A., Zisserman, A.: The VIA annotation software for images, audio and video. In: Proceedings of the 27th ACM International Conference on Multimedia, pp. 2276\u20132279 (2019)","DOI":"10.1145\/3343031.3350535"},{"key":"20_CR13","doi-asserted-by":"crossref","unstructured":"Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2963\u20132970. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"20_CR14","doi-asserted-by":"crossref","unstructured":"Gilani, A., Qasim, S.R., Malik, I., Shafait, F.: Table detection using deep learning. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), Vol. 1, pp. 771\u2013776. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.131"},{"key":"20_CR15","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)"},{"issue":"3","key":"20_CR16","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/BF02626996","volume":"5","author":"AK Jain","year":"1992","unstructured":"Jain, A.K., Bhattacharjee, S.: Text segmentation using Gabor filters for automatic document processing. Mach. Vis. Appl. 5(3), 169\u2013184 (1992)","journal-title":"Mach. Vis. Appl."},{"key":"20_CR17","doi-asserted-by":"crossref","unstructured":"Jang, Y.K., Cho, N.I.: Self-supervised product quantization for deep unsupervised image retrieval. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12085\u201312094 (2021)","DOI":"10.1109\/ICCV48922.2021.01187"},{"issue":"3","key":"20_CR18","doi-asserted-by":"crossref","first-page":"508","DOI":"10.3390\/electronics9030508","volume":"9","author":"J Jo","year":"2020","unstructured":"Jo, J., Lee, S., Lee, C., Lee, D., Lim, H.: Development of fashion product retrieval and recommendations model based on deep learning. Electronics 9(3), 508 (2020)","journal-title":"Electronics"},{"key":"20_CR19","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484\u20131493). IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"20_CR20","doi-asserted-by":"crossref","unstructured":"Karatzas, D., et al.: ICDAR 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"20_CR21","unstructured":"Levenshtein, V.I.: Binary codes capable of correcting deletions, insertions, and reversals. In: Proceedings of the Soviet Physics Doklady (1966)"},{"key":"20_CR22","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: TROCR: transformer-based optical character recognition with pre-trained models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 11, pp. 13094\u201313102 (2023)","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"20_CR23","doi-asserted-by":"crossref","unstructured":"Lucas, S.M., et al.: ICDAR 2003 robust reading competitions: entries, results, and future directions. In: International Journal of Document Analysis and Recognition (IJDAR), vol. 7, pp. 105\u2013122 (2005)","DOI":"10.1007\/s10032-004-0134-3"},{"key":"20_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1007\/978-3-030-01258-8_35","volume-title":"Computer Vision \u2013 ECCV 2018","author":"E M\u00fcller-Budack","year":"2018","unstructured":"M\u00fcller-Budack, E., Pustu-Iren, K., Ewerth, R.: Geolocation estimation of photos using a hierarchical model and scene classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 575\u2013592. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01258-8_35"},{"key":"20_CR25","doi-asserted-by":"crossref","first-page":"124945","DOI":"10.1109\/ACCESS.2021.3110787","volume":"9","author":"T Nasir","year":"2021","unstructured":"Nasir, T., Malik, M.K., Shahzad, K.: MMU-OCR-21: towards end-to-end Urdu text recognition using deep learning. IEEE Access 9, 124945\u2013124962 (2021)","journal-title":"IEEE Access"},{"key":"20_CR26","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, vol. 2011, no. 2, p. 4 (2011)"},{"key":"20_CR27","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3538\u20133545. IEEE (2012)","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"20_CR28","doi-asserted-by":"crossref","unstructured":"Nom, V., Bakkali, S., Luqman, M.M., Coustaty, M., Ogier, J.M.: KhmerST: a low-resource khmer scene text detection and recognition benchmark. In: Proceedings of the Asian Conference on Computer Vision pp. 1777\u20131792 (2024)","DOI":"10.1007\/978-981-96-0917-8_22"},{"key":"20_CR29","unstructured":"Paul, D., Chaudhuri, B.B.: A BLSTM network for printed Bengali OCR system with high accuracy. arXiv preprint arXiv:1908.08674 (2019)"},{"key":"20_CR30","doi-asserted-by":"crossref","unstructured":"Rawls, S., Cao, H., Sabir, E., Natarajan, P.: Combining deep learning and language modeling for segmentation-free OCR from raw pixels. In: 2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR), pp. 119\u2013123. IEEE (2017)","DOI":"10.1109\/ASAR.2017.8067772"},{"key":"20_CR31","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"20_CR32","doi-asserted-by":"crossref","unstructured":"Schreiber, S., Agne, S., Wolf, I., Dengel, A., Ahmed, S.: Deepdesrt: deep learning for detection and structure recognition of tables in document images. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 1162\u20131167. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.192"},{"key":"20_CR33","doi-asserted-by":"crossref","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, pp. 4168\u20134176 (2016)","DOI":"10.1109\/CVPR.2016.452"},{"issue":"11","key":"20_CR34","doi-asserted-by":"crossref","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":"20_CR35","doi-asserted-by":"crossref","unstructured":"Sok, P., Taing, N.: 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, pp. 1\u20139. IEEE (2014)","DOI":"10.1109\/APSIPA.2014.7041823"},{"key":"20_CR36","doi-asserted-by":"crossref","unstructured":"Sun, Y., Liu, J., Liu, W., Han, J., Ding, E., Liu, J.: Chinese street view text: Large-scale Chinese text reading with partially supervised learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9086\u20139095 (2019)","DOI":"10.1109\/ICCV.2019.00918"},{"key":"20_CR37","doi-asserted-by":"crossref","unstructured":"Tian, Y., Chen, C., Shah, M.: Cross-view image matching for geo-localization in urban environments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3608\u20133616 (2017)","DOI":"10.1109\/CVPR.2017.216"},{"key":"20_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/978-3-319-46484-8_4","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Z Tian","year":"2016","unstructured":"Tian, Z., Huang, W., He, T., He, P., Qiao, Yu.: Detecting text in natural image with connectionist text proposal network. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9912, pp. 56\u201372. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_4"},{"key":"20_CR39","doi-asserted-by":"crossref","unstructured":"Valy, D., Verleysen, M., Chhun, S.: Data augmentation and text recognition on Khmer historical manuscripts. In: 2020 17th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 73\u201378. IEEE (2020)","DOI":"10.1109\/ICFHR2020.2020.00024"},{"key":"20_CR40","unstructured":"Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: Coco-text: dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140 (2016)"},{"key":"20_CR41","doi-asserted-by":"crossref","unstructured":"Wei, T.C., Sheikh, U.U., Ab Rahman, A.A.H.: Improved optical character recognition with deep neural network. In: 2018 IEEE 14th International Colloquium on Signal Processing its Applications (CSPA), pp. 245\u2013249. IEEE (2018)","DOI":"10.1109\/CSPA.2018.8368720"},{"key":"20_CR42","doi-asserted-by":"crossref","first-page":"91661","DOI":"10.1109\/ACCESS.2020.2994287","volume":"8","author":"W Weihong","year":"2020","unstructured":"Weihong, W., Jiaoyang, T.: Research on license plate recognition algorithms based on deep learning in complex environment. IEEE Access 8, 91661\u201391675 (2020)","journal-title":"IEEE Access"},{"key":"20_CR43","doi-asserted-by":"crossref","unstructured":"Wu, L., Tian, S., Wang, Y., Xiong, P.: CPN: complementary proposal network for unconstrained text detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 6, pp. 6057\u20136065 (2024)","DOI":"10.1609\/aaai.v38i6.28421"},{"key":"20_CR44","doi-asserted-by":"crossref","unstructured":"Yi, Z., Zhang, H., Tan, P., Gong, M.: DualGAN: unsupervised dual learning for image-to-image translation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2849\u20132857 (2017)","DOI":"10.1109\/ICCV.2017.310"},{"key":"20_CR45","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1007\/s11390-019-1923-y","volume":"34","author":"TL Yuan","year":"2019","unstructured":"Yuan, T.L., Zhu, Z., Xu, K., Li, C.J., Mu, T.J., Hu, S.M.: A large chinese text dataset in the wild. J. Comput. Sci. Technol. 34, 509\u2013521 (2019)","journal-title":"J. Comput. Sci. Technol."},{"key":"20_CR46","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"20_CR47","unstructured":"Zhou, Z., Du, X., Zheng, Y., Jin, C.: Aggregated text transformer for scene text detection. arXiv preprint arXiv:2211.13984 (2022)"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04630-7_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T23:48:24Z","timestamp":1757980104000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04630-7_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,16]]},"ISBN":["9783032046291","9783032046307"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04630-7_20","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,16]]},"assertion":[{"value":"16 September 2025","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":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}