{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:46:16Z","timestamp":1743104776391,"version":"3.40.3"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031314162"},{"type":"electronic","value":"9783031314179"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-31417-9_27","type":"book-chapter","created":{"date-parts":[[2023,5,6]],"date-time":"2023-05-06T12:02:31Z","timestamp":1683374551000},"page":"350-361","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Scene Text Detection with Gradient Auto Encoders"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0231-3014","authenticated-orcid":false,"given":"S.","family":"Raveeshwara","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4379-2960","authenticated-orcid":false,"given":"B. H.","family":"Shekar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,5,7]]},"reference":[{"key":"27_CR1","series-title":"Studies in Computational Intelligence","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1007\/978-981-10-8797-4_68","volume-title":"Integrated Intelligent Computing, Communication and Security","author":"BN Ajay","year":"2019","unstructured":"Ajay, B.N., Naveena, C.: A mechanism for detection of text in images using DWT and MSER. In: Krishna, A.N., Srikantaiah, K.C., Naveena, C. (eds.) Integrated Intelligent Computing, Communication and Security. SCI, vol. 771, pp. 669\u2013676. Springer, Singapore (2019). https:\/\/doi.org\/10.1007\/978-981-10-8797-4_68"},{"key":"27_CR2","doi-asserted-by":"crossref","unstructured":"Basavaraju, H., et al.: Neighborhood structure-based model for multilingual arbitrarily-oriented text localization in images\/videos (2021)","DOI":"10.9781\/ijimai.2021.05.003"},{"key":"27_CR3","series-title":"Advances in Intelligent Systems and Computing","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1007\/978-981-10-7563-6_54","volume-title":"Information and decision sciences","author":"HT Basavaraju","year":"2018","unstructured":"Basavaraju, H.T., Manjunath Aradhya, V.N., Guru, D.S.: A novel arbitrary-oriented multilingual text detection in images\/video. In: Satapathy, S.C., Joao Manuel, R.S., Tavares, V.B., Mohanty, J.R. (eds.) Information and decision sciences. AISC, vol. 701, pp. 519\u2013529. Springer, Singapore (2018). https:\/\/doi.org\/10.1007\/978-981-10-7563-6_54"},{"issue":"3","key":"27_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/IJNCR.2018070101","volume":"7","author":"HT Basavaraju","year":"2018","unstructured":"Basavaraju, H.T., et al.: LoG and structural based arbitrary oriented multilingual text detection in images\/video. Int. J. Nat. Comput. Res. (IJNCR). 7(3), 1\u201316 (2018)","journal-title":"Int. J. Nat. Comput. Res. (IJNCR)."},{"issue":"3","key":"27_CR5","doi-asserted-by":"publisher","first-page":"31","DOI":"10.4018\/IJCVIP.2020070103","volume":"10","author":"S Basu","year":"2020","unstructured":"Basu, S., et al.: Multilingual scene text detection using gradient morphology. Int. J. Comput. Vis. Image Process. 10(3), 31\u201343 (2020). https:\/\/doi.org\/10.4018\/IJCVIP.2020070103","journal-title":"Int. J. Comput. Vis. Image Process."},{"key":"27_CR6","unstructured":"Buitinck, L., et al.: API design for machine learning software: experiences from the scikit-learn project. In: ECML PKDD Workshop: Languages for Data Mining and Machine Learning, pp. 108\u2013122 (2013)"},{"key":"27_CR7","unstructured":"Chen, D., Luettin, J.: A survey of text detection and recognition in images and videos (2000)"},{"key":"27_CR8","doi-asserted-by":"publisher","unstructured":"Chen, H., et al.: Robust text detection in natural images with edge-enhanced maximally stable extremal regions. In: 2011 18th IEEE International Conference on Image Processing, pp. 2609\u20132612 (2011). https:\/\/doi.org\/10.1109\/ICIP.2011.6116200","DOI":"10.1109\/ICIP.2011.6116200"},{"key":"27_CR9","unstructured":"Chollet, F.: Others: Keras (2015)"},{"key":"27_CR10","doi-asserted-by":"publisher","unstructured":"Coates, A., et al.: Text detection and character recognition in scene images with unsupervised feature learning. In: 2011 International Conference on Document Analysis and Recognition, pp. 440\u2013445 (2011). https:\/\/doi.org\/10.1109\/ICDAR.2011.95","DOI":"10.1109\/ICDAR.2011.95"},{"key":"27_CR11","doi-asserted-by":"publisher","unstructured":"Epshtein, B., et al.: Detecting text in natural scenes with stroke width transform. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2963\u20132970 (2010). https:\/\/doi.org\/10.1109\/CVPR.2010.5540041","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"27_CR12","doi-asserted-by":"publisher","unstructured":"Fu, K., et al.: Text detection for natural scene based on MobileNet V2 and U-Net. In: 2019 IEEE International Conference on Mechatronics and Automation (ICMA), pp. 1560\u20131564 (2019). https:\/\/doi.org\/10.1109\/ICMA.2019.8816384","DOI":"10.1109\/ICMA.2019.8816384"},{"issue":"6","key":"27_CR13","doi-asserted-by":"publisher","first-page":"2529","DOI":"10.1109\/TIP.2016.2547588","volume":"25","author":"T He","year":"2016","unstructured":"He, T., et al.: Text-attentional convolutional neural network for scene text detection. IEEE Trans. Image Process. 25(6), 2529\u20132541 (2016). https:\/\/doi.org\/10.1109\/TIP.2016.2547588","journal-title":"IEEE Trans. Image Process."},{"issue":"5","key":"27_CR14","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1016\/j.patcog.2003.10.012","volume":"37","author":"K Jung","year":"2004","unstructured":"Jung, K., et al.: Text information extraction in images and video: a survey. Pattern Recogn. 37(5), 977\u2013997 (2004). https:\/\/doi.org\/10.1016\/j.patcog.2003.10.012","journal-title":"Pattern Recogn."},{"key":"27_CR15","doi-asserted-by":"publisher","unstructured":"Kumar, D., et al.: Multi-script robust reading competition in ICDAR 2013. In: Proceedings of the 4th International Workshop on Multilingual OCR. Association for Computing Machinery, New York, NY, USA (2013). https:\/\/doi.org\/10.1145\/2505377.2505390","DOI":"10.1145\/2505377.2505390"},{"issue":"11","key":"27_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/fi12110200","volume":"12","author":"H Li","year":"2020","unstructured":"Li, H., Lu, H.: AT-Text: assembling text components for efficient dense scene text detection. Future Internet. 12(11), 1\u201314 (2020). https:\/\/doi.org\/10.3390\/fi12110200","journal-title":"Future Internet."},{"key":"27_CR17","doi-asserted-by":"publisher","unstructured":"Liao, M., et al.: Rotation-sensitive regression for oriented scene text detection. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 5909\u20135918 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00619","DOI":"10.1109\/CVPR.2018.00619"},{"key":"27_CR18","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.patcog.2019.02.002","volume":"90","author":"Y Liu","year":"2019","unstructured":"Liu, Y., et al.: Curved scene text detection via transverse and longitudinal sequence connection. Pattern Recogn. 90, 337\u2013345 (2019). https:\/\/doi.org\/10.1016\/j.patcog.2019.02.002","journal-title":"Pattern Recogn."},{"issue":"1","key":"27_CR19","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2020","unstructured":"Long, S., He, X., Yao, C.: Scene text detection and recognition: the deep learning era. Int. J. Comput. Vision 129(1), 161\u2013184 (2020). https:\/\/doi.org\/10.1007\/s11263-020-01369-0","journal-title":"Int. J. Comput. Vision"},{"issue":"2","key":"27_CR20","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/s12065-019-00248-z","volume":"14","author":"VN Manjunath Aradhya","year":"2019","unstructured":"Manjunath Aradhya, V.N., Basavaraju, H.T., Guru, D.S.: Decade research on text detection in images\/videos: a review. Evol. Intel. 14(2), 405\u2013431 (2019). https:\/\/doi.org\/10.1007\/s12065-019-00248-z","journal-title":"Evol. Intel."},{"key":"27_CR21","unstructured":"Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems. https:\/\/www.tensorflow.org\/ (2015)"},{"key":"27_CR22","doi-asserted-by":"publisher","unstructured":"Matas, J., et al.: Robust wide-baseline stereo from maximally stable extremal regions. In: Image and Vision Computing (2004). https:\/\/doi.org\/10.1016\/j.imavis.2004.02.006","DOI":"10.1016\/j.imavis.2004.02.006"},{"issue":"4","key":"27_CR23","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1117\/12.159642","volume":"2","author":"J-F Rivest","year":"1993","unstructured":"Rivest, J.-F., et al.: Morphological gradients. J. Electron. Imaging 2(4), 326\u2013336 (1993). https:\/\/doi.org\/10.1117\/12.159642","journal-title":"J. Electron. Imaging"},{"key":"27_CR24","doi-asserted-by":"publisher","unstructured":"Shekar, B.H., et al.: Discrete wavelet transform and gradient difference based approach for text localization in videos. In: Proceedings - 2014 5th International Conference on Signal and Image Processing, ICSIP 2014, pp. 280\u2013284 (2014). https:\/\/doi.org\/10.1109\/ICSIP.2014.50","DOI":"10.1109\/ICSIP.2014.50"},{"key":"27_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41870-021-00851-3","volume":"14","author":"BH Shekar","year":"2022","unstructured":"Shekar, B.H., Raveeshwara, S.: Contour feature learning for locating text in natural scene images. Int. J. Inf. Technol. 14, 1\u20136 (2022). https:\/\/doi.org\/10.1007\/s41870-021-00851-3","journal-title":"Int. J. Inf. Technol."},{"key":"27_CR26","doi-asserted-by":"crossref","unstructured":"Shekar, B.H., Raveeshwara, S.: Morphological gradient analysis and contour feature learning for locating text in natural scene images. In: International Conference on Computer Vision and Image Processing, pp. 254\u2013261 (2022)","DOI":"10.1007\/978-3-031-11349-9_22"},{"key":"27_CR27","doi-asserted-by":"publisher","unstructured":"Shekar, B.H., Smitha M., L.: Morphological gradient based approach for text localization in video\/scene images. In: 2014 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pp. 2426\u20132431 (2014). https:\/\/doi.org\/10.1109\/ICACCI.2014.6968426","DOI":"10.1109\/ICACCI.2014.6968426"},{"key":"27_CR28","doi-asserted-by":"publisher","unstructured":"Wan, Z., et al.: TextScanner: reading characters in order for robust scene text recognition. arXiv (2019). https:\/\/doi.org\/10.1609\/aaai.v34i07.6891","DOI":"10.1609\/aaai.v34i07.6891"},{"key":"27_CR29","doi-asserted-by":"publisher","unstructured":"Wang, X., et al.: Arbitrary shape scene text detection with adaptive text region representation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2019-June, pp. 6442\u20136451 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00661","DOI":"10.1109\/CVPR.2019.00661"},{"issue":"11","key":"27_CR30","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1109\/34.809116","volume":"21","author":"V Wu","year":"1999","unstructured":"Wu, V., et al.: Textfinder: an automatic system to detect and recognize text in images. IEEE Trans. Pattern Anal. Mach. Intell. 21(11), 1224\u20131229 (1999). https:\/\/doi.org\/10.1109\/34.809116","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"27_CR31","doi-asserted-by":"publisher","unstructured":"Yang, Q., et al.: Inceptext: a new inception-text module with deformable PSROI pooling for multi-oriented scene text detection. In: IJCAI International Joint Conference on Artificial Intelligence, pp. 1071\u20131077 (2018). https:\/\/doi.org\/10.24963\/ijcai.2018\/149","DOI":"10.24963\/ijcai.2018\/149"},{"key":"27_CR32","doi-asserted-by":"publisher","unstructured":"Yao, C., et al.: Detecting texts of arbitrary orientations in natural images. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 8, pp. 1083\u20131090 (2012). https:\/\/doi.org\/10.1109\/CVPR.2012.6247787","DOI":"10.1109\/CVPR.2012.6247787"},{"key":"27_CR33","unstructured":"Yao, C., et al.: Scene text detection via holistic, multi-channel prediction, pp. 1\u201310 (2016)"},{"issue":"7","key":"27_CR34","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2014","unstructured":"Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 37(7), 1480\u20131500 (2014)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"27_CR35","doi-asserted-by":"publisher","first-page":"2752","DOI":"10.1109\/TIP.2016.2554321","volume":"25","author":"XC Yin","year":"2016","unstructured":"Yin, X.C., et al.: Text detection, tracking and recognition in video: a comprehensive survey. IEEE Trans. Image Process. 25(6), 2752\u20132773 (2016). https:\/\/doi.org\/10.1109\/TIP.2016.2554321","journal-title":"IEEE Trans. Image Process."},{"issue":"19","key":"27_CR36","doi-asserted-by":"publisher","first-page":"29005","DOI":"10.1007\/s11042-021-11101-w","volume":"80","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Huang, Y., Zhao, D., Wu, C.H., Ip, W.H., Yung, K.L.: A scene text detector based on deep feature merging. Multimedia Tools Appl. 80(19), 29005\u201329016 (2021). https:\/\/doi.org\/10.1007\/s11042-021-11101-w","journal-title":"Multimedia Tools Appl."},{"key":"27_CR37","doi-asserted-by":"publisher","unstructured":"Zhang, Z., et al.: Multi-oriented text detection with fully convolutional networks. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4159\u20134167 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.451","DOI":"10.1109\/CVPR.2016.451"},{"issue":"10","key":"27_CR38","doi-asserted-by":"publisher","first-page":"1523","DOI":"10.1016\/0031-3203(95)00030-4","volume":"28","author":"Y Zhong","year":"1995","unstructured":"Zhong, Y., et al.: Locating text in complex color images. Pattern Recogn. 28(10), 1523\u20131535 (1995). https:\/\/doi.org\/10.1016\/0031-3203(95)00030-4","journal-title":"Pattern Recogn."},{"key":"27_CR39","doi-asserted-by":"publisher","unstructured":"Zhou, X., et al.: EAST: an efficient and accurate scene text detector. In: Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, pp. 2642\u20132651 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.283","DOI":"10.1109\/CVPR.2017.283"},{"issue":"1","key":"27_CR40","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","volume":"10","author":"A Zhu","year":"2017","unstructured":"Zhu, A.: Scene text detection and recognition. Front. Comp. Sci. 10(1), 19\u201336 (2017)","journal-title":"Front. Comp. Sci."},{"issue":"1","key":"27_CR41","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(1), 19\u201336 (2016). https:\/\/doi.org\/10.1007\/s11704-015-4488-0","journal-title":"Front. Comp. Sci."}],"container-title":["Communications in Computer and Information Science","Computer Vision and Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-31417-9_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,6]],"date-time":"2023-05-06T12:13:12Z","timestamp":1683375192000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-31417-9_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031314162","9783031314179"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-31417-9_27","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"7 May 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CVIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Vision and Image Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nagpur","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 November 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cvip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/vnit.ac.in\/cvip2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"307","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":"110","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":"11","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":"36% - 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":"4","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)"}}]}}