{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T06:56:03Z","timestamp":1764053763766,"version":"3.44.0"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030863364"},{"type":"electronic","value":"9783030863371"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-86337-1_2","type":"book-chapter","created":{"date-parts":[[2021,9,3]],"date-time":"2021-09-03T20:48:12Z","timestamp":1630702092000},"page":"18-32","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Fast Text vs. Non-text Classification of Images"],"prefix":"10.1007","author":[{"given":"Jiri","family":"Kralicek","sequence":"first","affiliation":[]},{"given":"Jiri","family":"Matas","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","unstructured":"Alessi, N.G., Battiato, S., Gallo, G., Mancuso, M., Stanco, F.: Automatic discrimination of text images. In: Sampat, N., Motta, R.J., Blouke, M.M., Sampat, N., Motta, R.J. (eds.) Sensors and Camera Systems for Scientific, Industrial, and Digital Photography Applications IV, vol. 5017, pp. 351\u2013359. International Society for Optics and Photonics, SPIE (2003). https:\/\/doi.org\/10.1117\/12.476747","DOI":"10.1117\/12.476747"},{"key":"2_CR2","doi-asserted-by":"publisher","unstructured":"Baek, Y., Lee, B., Han, D., Yun, S., Lee, H.: Character region awareness for text detection. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9357\u20139366, June 2019. https:\/\/doi.org\/10.1109\/CVPR.2019.00959","DOI":"10.1109\/CVPR.2019.00959"},{"key":"2_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv 1409, September 2014"},{"key":"2_CR4","doi-asserted-by":"publisher","unstructured":"Bai, X., Shi, B., Chengquan, Z., Cai, X., Qi, L.: Text\/non-text image classification in the wild with convolutional neural networks. Pattern Recogn. (2016). https:\/\/doi.org\/10.1016\/j.patcog.2016.12.005","DOI":"10.1016\/j.patcog.2016.12.005"},{"key":"2_CR5","doi-asserted-by":"publisher","unstructured":"Bodla, N., Singh, B., Chellappa, R., Davis, L.S.: Soft-NMS - improving object detection with one line of code. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 5562\u20135570 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.593","DOI":"10.1109\/ICCV.2017.593"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"2_CR7","doi-asserted-by":"publisher","unstructured":"Gupta, N., Jalal, A.S.: Text or non-text image classification using fully convolution network (FCN). In: 2020 International Conference on Contemporary Computing and Applications (IC3A), pp. 150\u2013153 (2020). https:\/\/doi.org\/10.1109\/IC3A48958.2020.233287","DOI":"10.1109\/IC3A48958.2020.233287"},{"issue":"9","key":"2_CR8","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015). https:\/\/doi.org\/10.1109\/TPAMI.2015.2389824","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.B.: Mask R-CNN. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"He, P., Huang, W., He, T., Zhu, Q., Qiao, Y., Li, X.: Single shot text detector with regional attention. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 3066\u20133074 (2017)","DOI":"10.1109\/ICCV.2017.331"},{"key":"2_CR11","doi-asserted-by":"publisher","unstructured":"He, W., Zhang, X., Yin, F., Liu, C.: Deep direct regression for multi-oriented scene text detection. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 745\u2013753 (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.87","DOI":"10.1109\/ICCV.2017.87"},{"key":"2_CR12","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations, December 2014"},{"key":"2_CR13","doi-asserted-by":"publisher","unstructured":"Liao, M., Lyu, P., He, M., Yao, C., Wu, W., Bai, X.: Mask textspotter: an end-to-end trainable neural network for spotting text with arbitrary shapes. IEEE Trans. Pattern Anal. Mach. Intell. PP, 1 (2019). https:\/\/doi.org\/10.1109\/TPAMI.2019.2937086","DOI":"10.1109\/TPAMI.2019.2937086"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: Textboxes: a fast text detector with a single deep neural network. In: AAAI (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"2_CR15","doi-asserted-by":"publisher","unstructured":"Lin, T., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 936\u2013944 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"2_CR16","unstructured":"Liu, J., Liu, X., Sheng, J., Liang, D., Li, X., Liu, Q.: Pyramid mask text detector. arXiv abs\/1903.11800 (2019)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Long, S., Ruan, J., Zhang, W., He, X., Wu, W., Yao, C.: TextSnake: a flexible representation for detecting text of arbitrary shapes. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01216-8_2"},{"issue":"11","key":"2_CR19","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1109\/TMM.2018.2818020","volume":"20","author":"J Ma","year":"2018","unstructured":"Ma, J., et al.: Arbitrary-oriented scene text detection via rotation proposals. IEEE Trans. Multimed. 20(11), 3111\u20133122 (2018)","journal-title":"IEEE Trans. Multimed."},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"McDonnell, M.D., Vladusich, T.: Enhanced image classification with a fast-learning shallow convolutional neural network. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20137 (2015)","DOI":"10.1109\/IJCNN.2015.7280796"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Lyu, P., Shi, B., Zhang, C., Bai, X.: Distinguishing text\/non-text natural images with multi-dimensional recurrent neural networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 3981\u20133986 (2016)","DOI":"10.1109\/ICPR.2016.7900256"},{"key":"2_CR22","doi-asserted-by":"publisher","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779\u2013788 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"issue":"6","key":"2_CR23","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.: MobileNetV2: inverted residuals and linear bottlenecks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"2_CR26","doi-asserted-by":"publisher","unstructured":"Shi, B., Bai, X., Belongie, S.: Detecting oriented text in natural images by linking segments. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3482\u20133490 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.371","DOI":"10.1109\/CVPR.2017.371"},{"key":"2_CR27","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556, September 2014"},{"key":"2_CR28","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":"2_CR29","doi-asserted-by":"publisher","unstructured":"Wang, J., Yang, J., Yu, K., Lv, F., Huang, T., Gong, Y.: Locality-constrained linear coding for image classification. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3360\u20133367 (2010). https:\/\/doi.org\/10.1109\/CVPR.2010.5540018","DOI":"10.1109\/CVPR.2010.5540018"},{"key":"2_CR30","doi-asserted-by":"publisher","unstructured":"Wojna, Z., et al.: Attention-based extraction of structured information from street view imagery. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 844\u2013850 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.143","DOI":"10.1109\/ICDAR.2017.143"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Xie, E., Zang, Y., Shao, S., Yu, G., Yao, C., Li, G.: Scene text detection with supervised pyramid context network. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 9038\u20139045, July 2019","DOI":"10.1609\/aaai.v33i01.33019038"},{"key":"2_CR32","unstructured":"Yao, C., Bai, X., Sang, N., Zhou, X., Zhou, S., Cao, Z.: Scene text detection via holistic, multi-channel prediction. arXiv, June 2016"},{"key":"2_CR33","doi-asserted-by":"publisher","unstructured":"Zhang, C., Yao, C., Shi, B., Bai, X.: Automatic discrimination of text and non-text natural images. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 886\u2013890 (2015). https:\/\/doi.org\/10.1109\/ICDAR.2015.7333889","DOI":"10.1109\/ICDAR.2015.7333889"},{"key":"2_CR34","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Chengquan, Z., Shen, W., Yao, C., Liu, W., Bai, X.: Multi-oriented text detection with fully convolutional networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4159\u20134167, June 2016. https:\/\/doi.org\/10.1109\/CVPR.2016.451","DOI":"10.1109\/CVPR.2016.451"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Zhao, M., Wang, R., Yin, F., Zhang, X., Huang, L., Ogier, J.: Fast text\/non-text image classification with knowledge distillation. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1458\u20131463 (2019)","DOI":"10.1109\/ICDAR.2019.00234"},{"key":"2_CR36","doi-asserted-by":"publisher","unstructured":"Zhou, X., et al.: East: an efficient and accurate scene text detector. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2642\u20132651 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.283","DOI":"10.1109\/CVPR.2017.283"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-86337-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T22:04:52Z","timestamp":1756850692000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-86337-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030863364","9783030863371"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-86337-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"2 September 2021","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":"Lausanne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iapr.org\/icdar2021","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":"340","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":"182","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":"54% - 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":"2.9","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":"4.9","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":"Additionally, 13 competition reports are included.","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)"}}]}}