{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T22:25:45Z","timestamp":1765232745764},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,6,15]],"date-time":"2019-06-15T00:00:00Z","timestamp":1560556800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,6,15]],"date-time":"2019-06-15T00:00:00Z","timestamp":1560556800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"OAC\/DMR","award":["1640867"],"award-info":[{"award-number":["1640867"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1007\/s10032-019-00327-y","type":"journal-article","created":{"date-parts":[[2019,6,15]],"date-time":"2019-06-15T15:02:37Z","timestamp":1560610957000},"page":"221-233","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Generalized framework for summarization of fixed-camera lecture videos by detecting and binarizing handwritten content"],"prefix":"10.1007","volume":"22","author":[{"given":"Bhargava","family":"Urala\u00a0Kota","sequence":"first","affiliation":[]},{"given":"Kenny","family":"Davila","sequence":"additional","affiliation":[]},{"given":"Alexander","family":"Stone","sequence":"additional","affiliation":[]},{"given":"Srirangaraj","family":"Setlur","sequence":"additional","affiliation":[]},{"given":"Venu","family":"Govindaraju","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,15]]},"reference":[{"key":"327_CR1","doi-asserted-by":"crossref","unstructured":"Banerjee, P., Bhattacharya, U., Chaudhuri, B.B.: Automatic detection of handwritten texts from video frames of lectures. In: 2014 14th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 627\u2013632. IEEE (2014)","DOI":"10.1109\/ICFHR.2014.110"},{"key":"327_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2008\/246309","volume":"2008","author":"K Bernardin","year":"2008","unstructured":"Bernardin, K., Stiefelhagen, R.: Evaluating multiple object tracking performance: the clear mot metrics. J. Image Video Process. 2008, 1 (2008)","journal-title":"J. Image Video Process."},{"key":"327_CR3","volume-title":"Symbolic and Visual Retrieval of Mathematical Notation Using Formula Graph Symbol Pair Matching and Structural Alignment","author":"KD Castellanos","year":"2017","unstructured":"Castellanos, K.D.: Symbolic and Visual Retrieval of Mathematical Notation Using Formula Graph Symbol Pair Matching and Structural Alignment. Rochester Institute of Technology, Rochester (2017)"},{"issue":"7","key":"327_CR4","doi-asserted-by":"publisher","first-page":"1443","DOI":"10.1109\/TMM.2007.906602","volume":"9","author":"C Choudary","year":"2007","unstructured":"Choudary, C., Liu, T.: Summarization of visual content in instructional videos. IEEE Trans. Multimed. 9(7), 1443\u20131455 (2007)","journal-title":"IEEE Trans. Multimed."},{"issue":"5","key":"327_CR5","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1109\/34.1000236","volume":"24","author":"D Comaniciu","year":"2002","unstructured":"Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell. 24(5), 603\u2013619 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"327_CR6","unstructured":"Davila, K., Agarwal, A., Gaborski, R., Zanibbi, R., Ludi, S.: Accessmath: indexing and retrieving video segments containing math expressions based on visual similarity. In: Image processing workshop (WNYIPW), 2013 IEEE Western New York, pp. 14\u201317. IEEE (2013)"},{"key":"327_CR7","doi-asserted-by":"crossref","unstructured":"Davila, K., Zanibbi, R.: Whiteboard video summarization via spatio-temporal conflict minimization. In: International Conference on Document Analysis and Recognition (ICDAR) (2017)","DOI":"10.1109\/ICDAR.2017.66"},{"key":"327_CR8","doi-asserted-by":"crossref","unstructured":"Davila, K., Zanibbi, R.: Visual search engine for handwritten and typeset math in lecture videos and latex notes. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR). IEEE (2018)","DOI":"10.1109\/ICFHR-2018.2018.00018"},{"key":"327_CR9","unstructured":"Dickson, P.E., Adrion, W.R., Hanson, A.R.: Whiteboard content extraction and analysis for the classroom environment. In: 10th IEEE International Symposium on Multimedia, 2008. ISM 2008, pp. 702\u2013707. IEEE (2008)"},{"key":"327_CR10","doi-asserted-by":"crossref","unstructured":"Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2963\u20132970. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540041"},{"issue":"1","key":"327_CR11","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.M.A., Van Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The Pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111(1), 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"327_CR12","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"327_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"327_CR14","unstructured":"Huang, L., Yang, Y., Deng, Y., Yu, Y.: Densebox: unifying landmark localization with end to end object detection (2015). arXiv preprint arXiv:1509.04874"},{"key":"327_CR15","doi-asserted-by":"crossref","unstructured":"Jia, W., Sun, L., Zhong, Z., Huo, Q.: A CNN-based approach to detecting text from images of whiteboards and handwritten notes. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR). IEEE (2018)","DOI":"10.1109\/ICFHR-2018.2018.00010"},{"key":"327_CR16","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., Matas, J., Neumann, L., Chandrasekhar, V.R., Lu, S., et\u00a0al.: 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":"327_CR17","doi-asserted-by":"crossref","unstructured":"Khosla, A., Hamid, R., Lin, C.J., Sundaresan, N.: Large-scale video summarization using web-image priors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2698\u20132705 (2013)","DOI":"10.1109\/CVPR.2013.348"},{"key":"327_CR18","doi-asserted-by":"crossref","unstructured":"Kim, G., Sigal, L., Xing, E.P.: Joint summarization of large-scale collections of web images and videos for storyline reconstruction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4225\u20134232 (2014)","DOI":"10.1109\/CVPR.2014.538"},{"key":"327_CR19","unstructured":"Kim, K.H., Hong, S., Roh, B., Cheon, Y., Park, M.: PVANet: deep but lightweight neural networks for real-time object detection (2016). arXiv preprint arXiv:1608.08021"},{"key":"327_CR20","unstructured":"Kota, B.U., Davila, K., Stone, A., Setlur, S., Govindaraju, V.: Automated detection of handwritten whiteboard content in lecture videos for summarization. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 19\u201324. IEEE (2018)"},{"issue":"5","key":"327_CR21","doi-asserted-by":"publisher","first-page":"7067","DOI":"10.1007\/s11042-016-3353-y","volume":"76","author":"GC Lee","year":"2017","unstructured":"Lee, G.C., Yeh, F.H., Chen, Y.J., Chang, T.K.: Robust handwriting extraction and lecture video summarization. Multimed. Tools Appl. 76(5), 7067\u20137085 (2017)","journal-title":"Multimed. Tools Appl."},{"key":"327_CR22","unstructured":"Lee, Y.J., Ghosh, J., Grauman, K.: Discovering important people and objects for egocentric video summarization. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1346\u20131353. IEEE (2012)"},{"key":"327_CR23","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, pp. 4161\u20134167 (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"327_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R.B., He, K., Hariharan, B., Belongie, S.J.: Feature pyramid networks for object detection. In: CVPR, vol. 1, p. 4 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"327_CR25","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., Berg, A.C.: Ssd: Single shot multibox detector. In: European Conference on Computer Vision, pp. 21\u201337. Springer (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"327_CR26","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"327_CR27","doi-asserted-by":"crossref","unstructured":"Meng, G., Yuan, K., Wu, Y., Xiang, S., Pan, C.: Deep networks for degraded document image binarization through pyramid reconstruction. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 727\u2013732. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.124"},{"key":"327_CR28","doi-asserted-by":"crossref","unstructured":"Meng, J., Wang, H., Yuan, J., Tan, Y.P.: From keyframes to key objects: video summarization by representative object proposal selection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1039\u20131048 (2016)","DOI":"10.1109\/CVPR.2016.118"},{"key":"327_CR29","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: A method for text localization and recognition in real-world images. In: Asian Conference on Computer Vision, pp. 770\u2013783. Springer (2010)","DOI":"10.1007\/978-3-642-19318-7_60"},{"issue":"2","key":"327_CR30","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1109\/TIP.2012.2219550","volume":"22","author":"K Ntirogiannis","year":"2013","unstructured":"Ntirogiannis, K., Gatos, B., Pratikakis, I.: Performance evaluation methodology for historical document image binarization. IEEE Trans. Image Process. 22(2), 595\u2013609 (2013)","journal-title":"IEEE Trans. Image Process."},{"key":"327_CR31","unstructured":"Onishi, M., Izumi, M., Fukunaga, K.: Blackboard segmentation using video image of lecture and its applications. In: Proceedings of 15th International Conference on Pattern Recognition, 2000, vol. 4, pp. 615\u2013618. IEEE (2000)"},{"issue":"1","key":"327_CR32","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62\u201366 (1979)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"327_CR33","doi-asserted-by":"crossref","unstructured":"Pratikakis, I., Zagoris, K., Barlas, G., Gatos, B.: ICFHR2016 handwritten document image binarization contest (H-DIBCO 2016). In: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 619\u2013623. IEEE (2016)","DOI":"10.1109\/ICFHR.2016.0118"},{"key":"327_CR34","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":"327_CR35","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"327_CR36","doi-asserted-by":"crossref","unstructured":"Shah, R.R., Yu, Y., Shaikh, A.D., Tang, S., Zimmermann, R.: Atlas: automatic temporal segmentation and annotation of lecture videos based on modelling transition time. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 209\u2013212. ACM (2014)","DOI":"10.1145\/2647868.2656407"},{"key":"327_CR37","doi-asserted-by":"crossref","unstructured":"Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., Cardoso, M.J.: Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, pp. 240\u2013248. Springer (2017)","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"327_CR38","unstructured":"Tang, L., Kender, J.R.: A unified text extraction method for instructional videos. In: IEEE International Conference on Image Processing, 2005. ICIP 2005, vol. 3, pp. III\u20131216. IEEE (2005)"},{"key":"327_CR39","doi-asserted-by":"crossref","unstructured":"Tian, Z., Huang, W., He, T., He, P., Qiao, Y.: Detecting text in natural image with connectionist text proposal network. In: European Conference on Computer Vision, pp. 56\u201372. Springer (2016)","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"327_CR40","doi-asserted-by":"crossref","unstructured":"Vajda, S., Rothacker, L., Fink, G.A.: A method for camera-based interactive whiteboard reading. In: International Workshop on Camera-Based Document Analysis and Recognition, pp. 112\u2013125. Springer (2011)","DOI":"10.1007\/978-3-642-29364-1_9"},{"key":"327_CR41","unstructured":"Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: Coco-text: dataset and benchmark for text detection and recognition in natural images (2016). arXiv preprint arXiv:1601.07140"},{"issue":"7","key":"327_CR42","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2015","unstructured":"Ye, Q., Doermann, D.: Text detection and recognition in imagery: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 37(7), 1480\u20131500 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"327_CR43","doi-asserted-by":"publisher","first-page":"2752","DOI":"10.1109\/TIP.2016.2554321","volume":"25","author":"XC Yin","year":"2016","unstructured":"Yin, X.C., Zuo, Z.Y., Tian, S., Liu, C.L.: Text detection, tracking and recognition in video: a comprehensive survey. IEEE Trans. Image Process. 25(6), 2752\u20132773 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"327_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yao, C., Wen, H., Wang, Y., Zhou, S., He, W., Liang, J.: East: an efficient and accurate scene text detector. In: Proceedings of CVPR, pp. 2642\u20132651 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"issue":"1","key":"327_CR45","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. Comput. Sci. 10(1), 19\u201336 (2016)","journal-title":"Front. Comput. Sci."}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-019-00327-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-019-00327-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-019-00327-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T21:44:38Z","timestamp":1663710278000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-019-00327-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,15]]},"references-count":45,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["327"],"URL":"https:\/\/doi.org\/10.1007\/s10032-019-00327-y","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,15]]},"assertion":[{"value":"16 November 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 May 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 June 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}