{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:21:23Z","timestamp":1779294083439,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819703753","type":"print"},{"value":"9789819703760","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-0376-0_34","type":"book-chapter","created":{"date-parts":[[2024,2,11]],"date-time":"2024-02-11T09:02:09Z","timestamp":1707642129000},"page":"451-464","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Using an Optimal then Enhanced YOLO Model for Multi-Lingual Scene Text Detection Containing the Arabic Scripts"],"prefix":"10.1007","author":[{"given":"Houssem","family":"Turki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed","family":"Elleuch","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Monji","family":"Kherallah","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,12]]},"reference":[{"key":"34_CR1","doi-asserted-by":"publisher","first-page":"66322","DOI":"10.1109\/ACCESS.2018.2878899","volume":"6","author":"X Bai","year":"2018","unstructured":"Bai, X., Yang, M., Lyu, P., Xu, Y., Luo, J.: Integrating scene text and visual appearance for fine-grained image classification. IEEE Access 6, 66322\u201366335 (2018)","journal-title":"IEEE Access"},{"key":"34_CR2","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1007\/s10044-015-0526-7","volume":"19","author":"I Abdelaziz","year":"2016","unstructured":"Abdelaziz, I., Abdou, S., Al-Barhamtoshy, H.: A large vocabulary system for Arabic online handwriting recognition. Pattern Anal. Appl. 19, 1129\u20131141 (2016)","journal-title":"Pattern Anal. Appl."},{"key":"34_CR3","doi-asserted-by":"publisher","unstructured":"Turki, H., Elleuch, M., Kherallah, M.: SYPHAX Dataset. IEEE Dataport (2023). https:\/\/doi.org\/10.21227\/ydqd-2443","DOI":"10.21227\/ydqd-2443"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Nayef, N., et al.: ICDAR2019 robust reading challenge on multi-lingual scene text detection and recognition\u2014RRC-MLT-2019. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1582\u20131587. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Sultana, F., Sufian, A., Dutta, P.: A review of object detection models based on convolutional neural network. Intell. Comput.: Image Proc. Based Appl., 1\u201316 (2020)","DOI":"10.1007\/978-981-15-4288-6_1"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Turki, H., Halima, M.B., Alimi, A.M.: Text detection based on MSER and CNN features. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 949\u2013954. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.159"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Amrouche, A., Bentrcia, Y., Hezil, N., Abed, A., Boubakeur, K.N., Ghribi, K.: Detection and localization of Arabic text in natural scene images. In: 2022 First International Conference on Computer Communications and Intelligent Systems (I3CIS), pp. 72\u201376. IEEE (2022)","DOI":"10.1109\/I3CIS56626.2022.10075747"},{"key":"34_CR8","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"},{"issue":"2","key":"34_CR9","doi-asserted-by":"publisher","first-page":"21","DOI":"10.3390\/jlpea12020021","volume":"12","author":"N Ravi","year":"2022","unstructured":"Ravi, N., El-Sharkawy, M.: Real-time embedded implementation of improved object detector for resource-constrained devices. J. Low Power Electron. Appl. 12(2), 21 (2022)","journal-title":"J. Low Power Electron. Appl."},{"issue":"6","key":"34_CR10","doi-asserted-by":"publisher","first-page":"9243","DOI":"10.1007\/s11042-022-13644-y","volume":"82","author":"T Diwan","year":"2023","unstructured":"Diwan, T., Anirudh, G., Tembhurne, J.V.: Object detection using YOLO: challenges, architectural successors, datasets and applications. Multimedia Tools Appl. 82(6), 9243\u20139275 (2023)","journal-title":"Multimedia Tools Appl."},{"key":"34_CR11","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint: arXiv:2004.10934 (2020)"},{"key":"34_CR12","unstructured":"Jocher, G., Nishimura, K., Mineeva, T., Vilarino, R.: Yolov5 by ultralytics. Dispon\u0131vel em: https:\/\/github.com\/ultralytics\/yolov5 (2020)"},{"key":"34_CR13","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint: arXiv:1804.02767 (2018)"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"Latha, R.S., et al.: Text detection and language identification in natural scene images using YOLOv5. In:\u00a02023 International Conference on Computer Communication and Informatics (ICCCI), pp. 1\u20137. IEEE (2023)","DOI":"10.1109\/ICCCI56745.2023.10128400"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Xu, Q., Zheng, G., Ren, W., Li, X., Yang, Z., Huang, Z.: An efficient and effective text spotter for characters in natural scene images based on an improved YOLOv5 model. In: International Conference on Artificial Intelligence, Virtual Reality, and Visualization (AIVRV 2022), vol. 12588, pp. 64\u201368. SPIE (2023)","DOI":"10.1117\/12.2667388"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Luo, Y., Zhao, C., Zhang, F.: Research on scene text detection algorithm based on modified YOLOv5. In: International Conference on Mechatronics Engineering and Artificial Intelligence (MEAI 2022), vol. 12596, pp. 620\u2013626. SPIE (2023)","DOI":"10.1117\/12.2672998"},{"key":"34_CR17","unstructured":"Li, C., et al.: YOLOv6: a single-stage object detection framework for industrial applications. arXiv preprint: arXiv:2209.02976 (2022)"},{"key":"34_CR18","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding YOLO series in 2021. arXiv preprint: arXiv:2107.08430 (2021)"},{"issue":"6","key":"34_CR19","doi-asserted-by":"publisher","first-page":"3161","DOI":"10.3390\/s23063161","volume":"23","author":"S Norkobil Saydirasulovich","year":"2023","unstructured":"Norkobil Saydirasulovich, S., Abdusalomov, A., Jamil, M.K., Nasimov, R., Kozhamzharova, D., Cho, Y.I.: A YOLOv6-based improved fire detection approach for smart city environments. Sensors 23(6), 3161 (2023)","journal-title":"Sensors"},{"issue":"3","key":"34_CR20","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1007\/s11554-023-01299-3","volume":"20","author":"C Gupta","year":"2023","unstructured":"Gupta, C., Gill, N.S., Gulia, P., Chatterjee, J.M.: A novel finetuned YOLOv6 transfer learning model for real-time object detection. J. Real-Time Image Proc. 20(3), 42 (2023)","journal-title":"J. Real-Time Image Proc."},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"34_CR22","doi-asserted-by":"publisher","unstructured":"Negi, A., Kesarwani, Y., Saranya, P.: Text Based Traffic Signboard Detection Using YOLO v7 Architecture. In: Singh, M., Tyagi, V., Gupta, P., Flusser, J., \u00d6ren, T. (eds.) Advances in Computing and Data Sciences. Communications in Computer and Information Science, vol. 1848, pp. 1\u201311. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-37940-6_1","DOI":"10.1007\/978-3-031-37940-6_1"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Moussaoui, H., El Akkad, N., Benslimane, M.: Arabic and Latin license plate detection and recognition based on YOLOv7 and image processing methods (2023)","DOI":"10.21203\/rs.3.rs-3195386\/v1"},{"key":"34_CR24","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":"34_CR25","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":"34_CR26","doi-asserted-by":"crossref","unstructured":"Tounsi, M., Moalla, I., Alimi, A.M.: ARASTI: a database for Arabic scene text recognition. In: 2017 1st International Workshop on Arabic Script Analysis and Recognition (ASAR), pp. 140\u2013144. IEEE (2017)","DOI":"10.1109\/ASAR.2017.8067776"},{"key":"34_CR27","first-page":"2761","volume":"70","author":"AH Ashraf","year":"2022","unstructured":"Ashraf, A.H., et al.: Weapons detection for security and video surveillance using CNN and YOLO-v5s. CMC-Comput. Mater. Contin 70, 2761\u20132775 (2022)","journal-title":"CMC-Comput. Mater. Contin"},{"key":"34_CR28","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.imavis.2019.04.007","volume":"87","author":"RC Chen","year":"2019","unstructured":"Chen, R.C.: Automatic License Plate Recognition via sliding-window darknet-YOLO deep learning. Image Vis. Comput. 87, 47\u201356 (2019)","journal-title":"Image Vis. Comput."},{"issue":"26","key":"34_CR29","doi-asserted-by":"publisher","first-page":"37821","DOI":"10.1007\/s11042-022-12962-5","volume":"81","author":"C Dewi","year":"2022","unstructured":"Dewi, C., Chen, R.C., Jiang, X., Yu, H.: Deep convolutional neural network for enhancing traffic sign recognition developed on YOLO v4. Multimedia Tools Appl. 81(26), 37821\u201337845 (2022)","journal-title":"Multimedia Tools Appl."},{"issue":"7\u20138","key":"34_CR30","first-page":"3385","volume":"125","author":"L Zhang","year":"2023","unstructured":"Zhang, L., Xu, F., Liu, Y., Zhang, D., Gui, L., Zuo, D.: A posture detection method for augmented reality\u2013aided assembly based on YOLO-6D. Int. J. Adv. Manufact. Technol. 125(7\u20138), 3385\u20133399 (2023)","journal-title":"Int. J. Adv. Manufact. Technol."},{"issue":"1","key":"34_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10032-022-00400-z","volume":"26","author":"D Zhang","year":"2023","unstructured":"Zhang, D., Mao, R., Guo, R., Jiang, Y., Zhu, J.: YOLO-table: disclosure document table detection with involution. Int. J. Doc. Anal. Recogn. (IJDAR) 26(1), 1\u201314 (2023)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"issue":"1","key":"34_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1\u201348 (2019)","journal-title":"J. Big Data"},{"key":"34_CR33","doi-asserted-by":"crossref","unstructured":"Schaefer, S., McPhail, T., Warren, J.: Image deformation using moving least squares. In: ACM SIGGRAPH 2006 Papers, pp. 533\u2013540 (2006)","DOI":"10.1145\/1141911.1141920"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Zeiler, M.D., Taylor, G.W., Fergus, R.: Adaptive deconvolutional networks for mid and high level feature learning. In: Proceedings of the 2011 International Conference on Computer Vision, Barcelona, Spain, 6\u201313 November 2011, pp. 2018\u20132025 (2011)","DOI":"10.1109\/ICCV.2011.6126474"},{"key":"34_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: ECA-Net: efficient channel attention for deep convolutional neural networks. In: Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 14 June 2020 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"}],"container-title":["Lecture Notes in Computer Science","Image and Video Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-0376-0_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,11]],"date-time":"2024-02-11T09:07:10Z","timestamp":1707642430000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-0376-0_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819703753","9789819703760"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-0376-0_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"12 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PSIVT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific-Rim Symposium on Image and Video Technology","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"22 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"psivt2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/psivt2023.aut.ac.nz\/","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":"Easy Chair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"75","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":"34","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":"45% - 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":"3","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":"3","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}