{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T05:39:02Z","timestamp":1757309942876,"version":"3.37.3"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T00:00:00Z","timestamp":1658793600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T00:00:00Z","timestamp":1658793600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076117"],"award-info":[{"award-number":["62076117"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61762061"],"award-info":[{"award-number":["61762061"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004479","name":"Natural Science Foundation of Jiangxi Province","doi-asserted-by":"publisher","award":["20161ACB20004"],"award-info":[{"award-number":["20161ACB20004"]}],"id":[{"id":"10.13039\/501100004479","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangxi Key Laboratory of Smart City","award":["20192BCD40002"],"award-info":[{"award-number":["20192BCD40002"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1007\/s11042-022-12497-9","type":"journal-article","created":{"date-parts":[[2022,7,26]],"date-time":"2022-07-26T07:02:48Z","timestamp":1658818968000},"page":"4371-4386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Memory-efficient document layout analysis method using LD-net"],"prefix":"10.1007","volume":"82","author":[{"given":"Haoyu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2526-2181","authenticated-orcid":false,"given":"Weidong","family":"Min","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zitai","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,26]]},"reference":[{"key":"12497_CR1","doi-asserted-by":"crossref","unstructured":"Bhowmik S, Kundu S, Sarkar R (2020) BINYAS: A complex document layout analysis system. Multimedia Tools Appl, pp 1\u201334","DOI":"10.1007\/s11042-020-09832-3"},{"issue":"6","key":"12497_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355610","volume":"52","author":"GM Binmakhashen","year":"2019","unstructured":"Binmakhashen GM, Mahmoud SA (2019) Document layout analysis: A comprehensive survey. ACM Comput Surv 52(6):1\u201336","journal-title":"ACM Comput Surv"},{"key":"12497_CR3","doi-asserted-by":"crossref","unstructured":"Breuel T (2002) Two geometric algorithms for layout analysis. In: Proc ACM Int Workshop Doc Anal Syst, Princeton, USA, pp 188\u2013199","DOI":"10.1007\/3-540-45869-7_23"},{"key":"12497_CR4","unstructured":"Breuel T (2008) The OCRopus open source OCR system. In: Proc IS&T\/SPIE 20th Annu Symp, San Jose, California, USA, pp 0F1\u20130F15"},{"key":"12497_CR5","doi-asserted-by":"crossref","unstructured":"Bukhari SS, Shafait F, Breuel T (2011) Improved document image segmentation algorithm using multiresolution morphology. In: SPIE document recognition and retrieval XVIII, DRR\u201911, San Francisco, USA, pp 78740D\u201378740D","DOI":"10.1117\/12.873461"},{"key":"12497_CR6","doi-asserted-by":"crossref","unstructured":"Bukhari S, Shafait F, Breuel T (2013) Towards generic text-line extraction. In: Proc Int Conf Document Anal Recognit (ICDAR), Washington, pp 748\u2013752","DOI":"10.1109\/ICDAR.2013.153"},{"issue":"1","key":"12497_CR7","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s10032-011-0176-2","volume":"16","author":"S Bukhari","year":"2013","unstructured":"Bukhari S, Shafait F, Breuel T (2013) Coupled snakelets for curled text-line segmentation from warped document images. Int J Doc Anal Recognit. (IJDAR) 16(1):33\u201353","journal-title":"Int J Doc Anal Recognit. (IJDAR)"},{"key":"12497_CR8","unstructured":"Campos VB, Calvo-Zaragoza J, Toselli AH, Ruiz EV (2016) Sheet Music Statistical Layout Analysis. In: Proc 14th Int Conf Frontiers Handwriting Recognit (ICFHR), Shenzhen, China, pp 313\u2013318"},{"key":"12497_CR9","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/S0031-3203(04)00239-0","volume":"38","author":"F Chang","year":"2005","unstructured":"Chang F, Chu S-Y, Chen C-Y (2005) Chinese document layout analysis using adaptive regrouping strategy. Pattern Recognit 38:261\u2013271","journal-title":"Pattern Recognit"},{"key":"12497_CR10","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/j.patrec.2016.06.011","volume":"80","author":"H Dai-Ton","year":"2016","unstructured":"Dai-Ton H, Duc-Dung N, Duc-Hieu L (2016) An, adaptive over-split and merge algorithm for page segmentation. Pattern Recogn Lett 80:137\u2013143","journal-title":"Pattern Recogn Lett"},{"key":"12497_CR11","doi-asserted-by":"publisher","first-page":"1090","DOI":"10.1109\/LSP.2020.3003828","volume":"27","author":"R De","year":"2020","unstructured":"De R, Chakraborty A, Sarkar R (2020) Document image binarization using dual discriminator generative adversarial networks. IEEE Signal Process Lett 27:1090\u20131094","journal-title":"IEEE Signal Process Lett"},{"key":"12497_CR12","doi-asserted-by":"crossref","unstructured":"Gao L, Yi X, Jiang Z, Hao L, Tang Z (2017) ICDAR 2017 competition on page object detection. In: Proc 14th IAPR Int Conf Document Anal Recognit (ICDAR), Kyoto, Japan, pp 141\u20131422","DOI":"10.1109\/ICDAR.2017.231"},{"key":"12497_CR13","doi-asserted-by":"publisher","first-page":"1275","DOI":"10.1007\/s10044-017-0595-x","volume":"20","author":"AM Hesham","year":"2017","unstructured":"Hesham AM, Rashwan MA, Al-Barhamtoshy HM, Abdou SM, Badr AA, Farag I (2017) Arabic document layout analysis. Pattern Anal Appl 20:1275\u20131287","journal-title":"Pattern Anal Appl"},{"key":"12497_CR14","unstructured":"Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H (2017) Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861"},{"key":"12497_CR15","doi-asserted-by":"crossref","unstructured":"Kasar T, Barlas P, Adam S, Chatelain C, Paquet T (2013) Learning to detect tables in scanned document images using line information. In: Proc Int Conf Document Anal Recognit (ICDAR), pp 1185\u20131189","DOI":"10.1109\/ICDAR.2013.240"},{"key":"12497_CR16","doi-asserted-by":"crossref","unstructured":"Koci E, Thiele M, Lehner W, Romero O (2018) Table recognition in spreadsheets via a graph representation. In: IAPR international workshop on document analysis systems (DAS). IEEE, Vienna, Austria, pp 139\u2013144","DOI":"10.1109\/DAS.2018.48"},{"key":"12497_CR17","doi-asserted-by":"crossref","unstructured":"Le VP, Nayef N, Visani M, Ogier J, Tran CD (2015) Text and non-text segmentation based on connected component features. In: Proc Int Conf Document Anal Recognit (ICDAR), Tunis, pp 1096\u20131100","DOI":"10.1109\/ICDAR.2015.7333930"},{"key":"12497_CR18","doi-asserted-by":"crossref","unstructured":"Li Y, Zou Y, Ma J (2018) DeepLayout: A semantic segmentation approach to page layout analysis. In: Proc Int Conf Intell Comput, Bengaluru, India, pp 266\u2013277","DOI":"10.1007\/978-3-319-95957-3_30"},{"key":"12497_CR19","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1109\/TITS.2017.2756989","volume":"19","author":"W Min","year":"2018","unstructured":"Min W, Fan M, Guo X, Han Q (2018) A new approach to track multiple vehicles with the combination of robust detection and two classifiers. IEEE Trans Intell Trans Syst 19:174\u2013186","journal-title":"IEEE Trans Intell Trans Syst"},{"key":"12497_CR20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10032-018-0314-1","volume":"22","author":"B Moysset","year":"2019","unstructured":"Moysset B, Messina R (2019) Are 2d-lstm really dead for offline text recognition. Int J Document Anal Recognit (IJDAR) 22:1\u201316","journal-title":"Int J Document Anal Recognit (IJDAR)"},{"key":"12497_CR21","doi-asserted-by":"crossref","unstructured":"Nayef N, Ogier J (2015) Text zone classification using unsupervised feature learning. In: Proc Int Conf Document Anal Recognit (ICDAR), Tunis, pp 776\u2013780","DOI":"10.1109\/ICDAR.2015.7333867"},{"key":"12497_CR22","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/s10032-019-00330-3","volume":"22","author":"NV Nguyen","year":"2019","unstructured":"Nguyen NV, Rigaud C, Burie JC (2019) Comic MTL: optimized multi-task learning for comic book image analysis. Int J Document Anal Recognit (IJDAR) 22:265\u2013284","journal-title":"Int J Document Anal Recognit (IJDAR)"},{"issue":"12","key":"12497_CR23","doi-asserted-by":"publisher","first-page":"1907","DOI":"10.1109\/LSP.2019.2953953","volume":"26","author":"Y Niu","year":"2019","unstructured":"Niu Y, Wen J, Zhong P, Xue Y (2019) A Hybrid, R-BILSTM-C neural network based text steganalysis. IEEE Signal Process Lett 26(12):1907\u20131911","journal-title":"IEEE Signal Process Lett"},{"key":"12497_CR24","unstructured":"Oliveira DAB, Viana PM (2017) Fast CNN-based document layout analysis. In: Proc IEEE Conf Comput Vis Pattern Recog, Waikiki, USA, pp 1173\u20131180"},{"issue":"1","key":"12497_CR25","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"SMC-9","author":"N Otsu","year":"1979","unstructured":"Otsu N (1979) Threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern SMC-9(1):62\u201366","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"12497_CR26","unstructured":"Phillips I (1995) User\u2019s reference manual, cd-rom, uw-iii document image database-iii"},{"key":"12497_CR27","doi-asserted-by":"crossref","unstructured":"Qin X, Zhou Y, He Z, Wang Y, Tang Z (2017) A Faster R-CNN based method for comic characters face detection. In: Proc Int Conf Document Anal Recognit (ICDAR), Kyoto, Japan, pp 1074\u20131080","DOI":"10.1109\/ICDAR.2017.178"},{"key":"12497_CR28","doi-asserted-by":"crossref","unstructured":"Royer E, Bouchara F (2017) Guiding text image keypoints extraction through layout analysis. In: Proc Int Conf Document Anal Recognit (ICDAR), Kyoto, Japan, pp 9\u201314","DOI":"10.1109\/ICDAR.2017.342"},{"key":"12497_CR29","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-CAM: Visual explanations from deep networks via gradient-based localization. In: Proc IEEE Int Conf Comput Vis, pp 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"issue":"3","key":"12497_CR30","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1007\/s10032-016-0265-3","volume":"19","author":"TA Tran","year":"2016","unstructured":"Tran TA, Na IS, Kim SH (2016) Page segmentation using minimum homogeneity algorithm and adaptive mathematical morphology. Int J Doc Anal Recognit (IJDAR) 19(3):191\u2013209","journal-title":"Int J Doc Anal Recognit (IJDAR)"},{"key":"12497_CR31","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.eswa.2017.05.030","volume":"85","author":"TA Tran","year":"2017","unstructured":"Tran TA, Na IS, Kim SH (2017) A robust system for document layout analysis using multilevel homogeneity structure. Expert Syst Appl 85:99\u2013113","journal-title":"Expert Syst Appl"},{"issue":"4","key":"12497_CR32","doi-asserted-by":"publisher","first-page":"77","DOI":"10.5392\/IJoC.2015.11.4.077","volume":"11","author":"DN Tran","year":"2005","unstructured":"Tran DN, Tran TA, Oh A, Kim SH, Na IS (2005) Table detection from document image using vertical arrangement of text blocks. Int J Contents 11(4):77\u201385","journal-title":"Int J Contents"},{"key":"12497_CR33","doi-asserted-by":"publisher","unstructured":"Wang Q, Min W, He D, Zou S, Huang T, Zhang Y, Liu R (2020) Discriminative fine-grained network for vehicle re-identification using two-stage re-ranking. Sci China Inf Sci. https:\/\/doi.org\/10.1007\/385s11432-019-2811-8","DOI":"10.1007\/385s11432-019-2811-8"},{"issue":"6","key":"12497_CR34","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1147\/rd.266.0647","volume":"26","author":"K Wong","year":"1982","unstructured":"Wong K, Casey R, Wahl F (1982) Document analysis systems. IBM J Res Dev 26(6):647\u2013656","journal-title":"IBM J Res Dev"},{"key":"12497_CR35","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/s10032-019-00337-w","volume":"22","author":"J Yang","year":"2019","unstructured":"Yang J, Kim H, Kwak H, Kim I (2019) HanFont: large-scale adaptive Hangul font recognizer using CNN and font clustering. Int J Document Anal Recognit (IJDAR) 22:407\u2013416","journal-title":"Int J Document Anal Recognit (IJDAR)"},{"key":"12497_CR36","doi-asserted-by":"crossref","unstructured":"Yi X, Gao L, Liao Y, Zhang X, Liu R, Jiang Z (2017) CNN based page object detection in document images. In: Proc Int Conf Document Anal Recognit (ICDAR), Kyoto, Japan, pp 230\u2013235","DOI":"10.1109\/ICDAR.2017.46"},{"key":"12497_CR37","unstructured":"Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions. In: Proc Int Conf Learn Representations"},{"key":"12497_CR38","doi-asserted-by":"crossref","unstructured":"Zhang X, Zhou X, Lin M, Sun J (2018) ShuffleNet: An extremely efficient convolutional neural network for mobile devices. In: Proc Conf Computer Vision and Pattern Recognition (CVPR), Salt Lake, pp 6848\u20136856","DOI":"10.1109\/CVPR.2018.00716"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12497-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-12497-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12497-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T09:47:52Z","timestamp":1672825672000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-12497-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,26]]},"references-count":38,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["12497"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-12497-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2022,7,26]]},"assertion":[{"value":"15 January 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 January 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}