{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T11:29:02Z","timestamp":1762342142565,"version":"3.37.3"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T00:00:00Z","timestamp":1695859200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T00:00:00Z","timestamp":1695859200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000103","name":"National Endowment for the Humanities","doi-asserted-by":"publisher","award":["LG-71-16-0152-16","LG-71-16-0152-16","LG-71-16-0152-16"],"award-info":[{"award-number":["LG-71-16-0152-16","LG-71-16-0152-16","LG-71-16-0152-16"]}],"id":[{"id":"10.13039\/100000103","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000208","name":"Institute of Museum and Library Services","doi-asserted-by":"publisher","award":["HJ-253589","HJ-253589","HJ-253589"],"award-info":[{"award-number":["HJ-253589","HJ-253589","HJ-253589"]}],"id":[{"id":"10.13039\/100000208","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2024,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Image downscaling is an essential operation to reduce spatial complexity for various applications and is becoming increasingly important due to the growing number of solutions that rely on memory-intensive approaches, such as applying deep convolutional neural networks to semantic segmentation tasks on large images. Although conventional content-independent image downscaling can efficiently reduce complexity, it is vulnerable to losing perceptual details, which are important to preserve. Alternatively, existing content-aware downscaling severely distorts spatial structure and is not effectively applicable for segmentation tasks involving document images. In this paper, we propose a novel image downscaling approach that combines the strengths of both content-independent and content-aware strategies. The approach limits the sampling space per the content-independent strategy, adaptively relocating such sampled pixel points, and amplifying their intensities based on the local gradient and texture via the content-aware strategy. To demonstrate its effectiveness, we plug our adaptive downscaling method into a deep learning-based document image segmentation pipeline and evaluate the performance improvement. We perform the evaluation on three publicly available historical newspaper digital collections with differences in quality and quantity, comparing our method with one widely used downscaling method, Lanczos. We further demonstrate the robustness of the proposed method by using three different training scenarios: stand-alone, image-pyramid, and augmentation. The results show that training a deep convolutional neural network using images generated by the proposed method outperforms Lanczos, which relies on only content-independent strategies.<\/jats:p>","DOI":"10.1007\/s10032-023-00454-7","type":"journal-article","created":{"date-parts":[[2023,9,28]],"date-time":"2023-09-28T02:01:30Z","timestamp":1695866490000},"page":"159-175","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Perceptual cue-guided adaptive image downscaling for enhanced semantic segmentation on large document images"],"prefix":"10.1007","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9876-4388","authenticated-orcid":false,"given":"Chulwoo","family":"Pack","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leen-Kiat","family":"Soh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0003-6789","authenticated-orcid":false,"given":"Elizabeth","family":"Lorang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,28]]},"reference":[{"issue":"6","key":"454_CR1","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1109\/TASSP.1981.1163711","volume":"29","author":"R Keys","year":"1981","unstructured":"Keys, R.: Cubic convolution interpolation for digital image processing. IEEE Trans. Acoust. Speech Signal Process. 29(6), 1153\u20131160 (1981)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"8","key":"454_CR2","doi-asserted-by":"publisher","first-page":"1016","DOI":"10.1175\/1520-0450(1979)018<1016:LFIOAT>2.0.CO;2","volume":"18","author":"CE Duchon","year":"1979","unstructured":"Duchon, C.E.: Lanczos filtering in one and two dimensions. J. Appl. Meteorol. Climatol. 18(8), 1016\u20131022 (1979)","journal-title":"J. Appl. Meteorol. Climatol."},{"key":"454_CR3","unstructured":"Oliveira, S.A., Seguin, B., Kaplan, F.: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR) (IEEE, 2018), pp. 7\u201312"},{"key":"454_CR4","unstructured":"Lee, J., Hayashi, H., Ohyama, W., Uchida, S.: 2019 International Conference on Document Analysis and Recognition (ICDAR) (IEEE, 2019), pp. 1023\u20131028"},{"key":"454_CR5","unstructured":"Wick, C., Puppe, F.: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS) (IEEE, 2018), pp. 287\u2013292"},{"key":"454_CR6","unstructured":"Yang, X., Yumer, E., Asente, P., Kraley, M., Kifer, D., Lee\u00a0Giles, C.: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017), pp. 5315\u20135324"},{"key":"454_CR7","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18 (Springer, 2015), pp. 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"454_CR8","doi-asserted-by":"publisher","unstructured":"Avidan, S., Shamir, A.: ACM SIGGRAPH 2007 Papers (Association for Computing Machinery, New York, NY, USA, 2007), SIGGRAPH \u201907, p. 10-es. https:\/\/doi.org\/10.1145\/1275808.1276390","DOI":"10.1145\/1275808.1276390"},{"issue":"4","key":"454_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2766891","volume":"34","author":"AC Oeztireli","year":"2015","unstructured":"Oeztireli, A.C., Gross, M.: Perceptually based downscaling of images. ACM Trans. Gr. 34(4), 1\u201310 (2015)","journal-title":"ACM Trans. Gr."},{"issue":"6","key":"454_CR10","first-page":"1","volume":"32","author":"J Kopf","year":"2013","unstructured":"Kopf, J., Shamir, A., Peers, P.: Content-adaptive image downscaling. ACM Trans. Gr. 32(6), 1\u20138 (2013)","journal-title":"ACM Trans. Gr."},{"issue":"4","key":"454_CR11","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1109\/83.370671","volume":"4","author":"X Ran","year":"1995","unstructured":"Ran, X., Farvardin, N.: A perceptually motivated three-component image model-part i: description of the model. IEEE Trans. Image Process. 4(4), 401\u2013415 (1995)","journal-title":"IEEE Trans. Image Process."},{"issue":"4","key":"454_CR12","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1109\/TCSVT.2004.825574","volume":"14","author":"E Ong","year":"2004","unstructured":"Ong, E., Lin, W., Lu, Z., Yao, S., Etoh, M.: Visual distortion assessment with emphasis on spatially transitional regions. IEEE Trans. Circuits Syst. Video Technol. 14(4), 559\u2013566 (2004)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"454_CR13","doi-asserted-by":"crossref","unstructured":"Rouse, D.M., Hemami, S.S.: Human Vision and Electronic Imaging XII, vol. 6492 (SPIE, 2007), pp. 602\u2013611","DOI":"10.1117\/12.707539"},{"issue":"3","key":"454_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1360612.1360615","volume":"27","author":"M Rubinstein","year":"2008","unstructured":"Rubinstein, M., Shamir, A., Avidan, S.: Improved seam carving for video retargeting. ACM Trans. Gr. 27(3), 1\u20139 (2008)","journal-title":"ACM Trans. Gr."},{"issue":"3","key":"454_CR15","doi-asserted-by":"publisher","first-page":"1076","DOI":"10.1109\/TIP.2017.2772838","volume":"27","author":"J Liu","year":"2017","unstructured":"Liu, J., He, S., Lau, R.W.: l_ $$\\{0\\}$$ -regularized image downscaling. IEEE Trans. Image Process. 27(3), 1076\u20131085 (2017)","journal-title":"IEEE Trans. Image Process."},{"key":"454_CR16","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.patcog.2016.01.030","volume":"55","author":"Y Liu","year":"2016","unstructured":"Liu, Y., Zhang, Y.M., Zhang, X.Y., Liu, C.L.: Adaptive spatial pooling for image classification. Pattern Recogn. 55, 58\u201367 (2016)","journal-title":"Pattern Recogn."},{"key":"454_CR17","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1109\/TIP.2022.3227503","volume":"32","author":"A Stergiou","year":"2022","unstructured":"Stergiou, A., Poppe, R.: Adapool: exponential adaptive pooling for information-retaining downsampling. IEEE Trans. Image Process. 32, 251\u2013266 (2022)","journal-title":"IEEE Trans. Image Process."},{"issue":"4","key":"454_CR18","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1007\/s10278-019-00227-x","volume":"32","author":"MH Hesamian","year":"2019","unstructured":"Hesamian, M.H., Jia, W., He, X., Kennedy, P.: Deep learning techniques for medical image segmentation: achievements and challenges. J. Digit. Imaging 32(4), 582\u2013596 (2019)","journal-title":"J. Digit. Imaging"},{"issue":"8","key":"454_CR19","doi-asserted-by":"publisher","first-page":"e0236493","DOI":"10.1371\/journal.pone.0236493","volume":"15","author":"B Lee","year":"2020","unstructured":"Lee, B., Yamanakkanavar, N., Choi, J.Y.: Automatic segmentation of brain mri using a novel patch-wise u-net deep architecture. Plos one 15(8), e0236493 (2020)","journal-title":"Plos one"},{"key":"454_CR20","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1109\/TSMC.1973.4309314","volume":"6","author":"RM Haralick","year":"1973","unstructured":"Haralick, R.M., Shanmugam, K., Dinstein, I.H.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. 6, 610\u2013621 (1973)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"454_CR21","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1007\/978-0-387-73003-5_196","volume":"741","author":"DA Reynolds","year":"2009","unstructured":"Reynolds, D.A.: Gaussian mixture models. Encycl. Biometr. 741, 659\u2013663 (2009)","journal-title":"Encycl. Biometr."},{"issue":"12","key":"454_CR22","doi-asserted-by":"publisher","first-page":"5702","DOI":"10.1109\/TIP.2016.2614133","volume":"25","author":"B Sun","year":"2016","unstructured":"Sun, B., Li, S., Zhang, X.P., Sun, J.: Blind bleed-through removal for scanned historical document image with conditional random fields. IEEE Trans. Image Process. 25(12), 5702\u20135712 (2016)","journal-title":"IEEE Trans. Image Process."},{"key":"454_CR23","volume-title":"Handbook of Statistics","author":"V Chandola","year":"2015","unstructured":"Chandola, V., Vatsavai, R.R., Kumar, D., Ganguly, A.: Big data analytics. In: Govindaraju, V., Raghavan, V.V., Rao, C. (eds.) Handbook of Statistics. Elsevier, Amsterdam (2015)"},{"key":"454_CR24","unstructured":"Shepard, D.: Proceedings of the 1968 23rd ACM national conference (1968), pp. 517\u2013524"},{"issue":"3","key":"454_CR25","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s10032-021-00380-6","volume":"24","author":"S Biswas","year":"2021","unstructured":"Biswas, S., Riba, P., Llad\u00f3s, J., Pal, U.: Beyond document object detection: instance-level segmentation of complex layouts. Int. J. Doc. Anal. Recogn. 24(3), 269\u2013281 (2021)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"454_CR26","doi-asserted-by":"crossref","unstructured":"Arvanitopoulos, N., S\u00fcsstrunk, S.: 2014 14th International Conference on Frontiers in Handwriting Recognition (IEEE, 2014), pp. 726\u2013731","DOI":"10.1109\/ICFHR.2014.127"},{"key":"454_CR27","doi-asserted-by":"crossref","unstructured":"Lucas, S.M., Panaretos, A., Sosa, L., Tang, A., Wong, S., Young, R., Ashida, K., Nagai, H., Okamoto, M., Yamamoto, H., et al.: Icdar 2003 robust reading competitions: entries, results, and future directions. IJDAR 7(2), 105\u2013122 (2005)","DOI":"10.1007\/s10032-004-0134-3"},{"issue":"3","key":"454_CR28","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s10032-021-00376-2","volume":"24","author":"Y Hamdi","year":"2021","unstructured":"Hamdi, Y., Boubaker, H., Alimi, A.M.: Data augmentation using geometric, frequency, and beta modeling approaches for improving multi-lingual online handwriting recognition. Int. J. Doc. Anal. Recogn. 24(3), 283\u2013298 (2021)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"454_CR29","doi-asserted-by":"crossref","unstructured":"Liebl, B., Burghardt, M.: 2020 25th International Conference on Pattern Recognition (ICPR) (IEEE, 2021), pp. 5153\u20135160","DOI":"10.1109\/ICPR48806.2021.9412571"},{"key":"454_CR30","unstructured":"Clausner, C., Papadopoulos, C., Pletschacher, S., Antonacopoulos, A.: 2015 13th International Conference on Document Analysis and Recognition (ICDAR) (IEEE, 2015), pp. 931\u2013935"},{"key":"454_CR31","unstructured":"of\u00a0Luxembourg, N.L.: Historical newspapers - bnl open data (2020). https:\/\/data.bnl.lu\/data\/historical-newspapers"},{"key":"454_CR32","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"1","key":"454_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12864-019-6413-7","volume":"21","author":"D Chicco","year":"2020","unstructured":"Chicco, D., Jurman, G.: The advantages of the matthews correlation coefficient (mcc) over f1 score and accuracy in binary classification evaluation. BMC Genomics 21(1), 1\u201313 (2020)","journal-title":"BMC Genomics"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-023-00454-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-023-00454-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-023-00454-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T10:25:42Z","timestamp":1730197542000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-023-00454-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,28]]},"references-count":33,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["454"],"URL":"https:\/\/doi.org\/10.1007\/s10032-023-00454-7","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"type":"print","value":"1433-2833"},{"type":"electronic","value":"1433-2825"}],"subject":[],"published":{"date-parts":[[2023,9,28]]},"assertion":[{"value":"3 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}