{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T21:15:43Z","timestamp":1776978943942,"version":"3.51.4"},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T00:00:00Z","timestamp":1774224000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100017439","name":"Liaoning Province Government","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100017439","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100019033","name":"Key Research and Development Program of Liaoning Province","doi-asserted-by":"publisher","award":["LJKZZ20220033"],"award-info":[{"award-number":["LJKZZ20220033"]}],"id":[{"id":"10.13039\/501100019033","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.neucom.2026.133418","type":"journal-article","created":{"date-parts":[[2026,3,21]],"date-time":"2026-03-21T23:35:46Z","timestamp":1774136146000},"page":"133418","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Category-aware deep perspective transformation research"],"prefix":"10.1016","volume":"681","author":[{"given":"Xiaofei","family":"Ji","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sixu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangtao","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133418_bib0005","first-page":"1","article-title":"Docscanner: robust document image rectification with progressive learning","author":"Feng","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.133418_bib0010","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/j.jmsy.2024.02.009","article-title":"Deep learning-based augmented reality work instruction assistance system for complex manual assembly","volume":"73","author":"Li","year":"2024","journal-title":"J. Manuf. Syst."},{"issue":"1","key":"10.1016\/j.neucom.2026.133418_bib0015","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1007\/s00371-023-02791-4","article-title":"Image stitching based on human visual system and SIFT algorithm","volume":"40","author":"Zhang","year":"2024","journal-title":"The Vis. Comput."},{"issue":"3","key":"10.1016\/j.neucom.2026.133418_bib0020","doi-asserted-by":"crossref","first-page":"4457","DOI":"10.1007\/s40747-024-01358-7","article-title":"Human face identification after plastic surgery using surf, multi-knn and bpnn techniques","volume":"10","author":"Sabharwal","year":"2024","journal-title":"Complex Intell. Syst."},{"key":"10.1016\/j.neucom.2026.133418_bib0025","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.neucom.2022.01.099","article-title":"Evolutionary deep learning: a survey","volume":"483","author":"Zhan","year":"2022","journal-title":"Neurocomputing"},{"issue":"11","key":"10.1016\/j.neucom.2026.133418_bib0030","doi-asserted-by":"crossref","first-page":"13521","DOI":"10.1007\/s10462-023-10466-8","article-title":"Deep learning modelling techniques: current progress, applications, advantages, and challenges","volume":"56","author":"Ahmed","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.neucom.2026.133418_bib0035","article-title":"Spatial transformer networks","volume":"28","author":"Jaderberg","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133418_bib0040","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4168","article-title":"Robust scene text recognition with automatic rectification","author":"Shi","year":"2016"},{"key":"10.1016\/j.neucom.2026.133418_bib0045","series-title":"European Conference on Computer Vision","first-page":"345","article-title":"M\u00f6bius transform for mitigating perspective distortions in representation learning","author":"Chhipa","year":"2024"},{"key":"10.1016\/j.neucom.2026.133418_bib0050","series-title":"Proceedings of the Asian Conference on Computer Vision","first-page":"3275","article-title":"LCM: log conformal maps for robust representation learning to mitigate perspective distortion","author":"Chippa","year":"2024"},{"key":"10.1016\/j.neucom.2026.133418_bib0055","article-title":"Alexnet architecture variations with transfer learning for classification of wound images","volume":"45","author":"Eldem","year":"2023","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"10.1016\/j.neucom.2026.133418_bib0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2023.107660","article-title":"Resnet and its application to medical image processing: research progress and challenges","volume":"240","author":"Xu","year":"2023","journal-title":"Comput. Methods Programs Biomed."},{"issue":"18","key":"10.1016\/j.neucom.2026.133418_bib0065","doi-asserted-by":"crossref","first-page":"13285","DOI":"10.1007\/s00500-022-07406-z","article-title":"Densenet-ii: an improved deep convolutional neural network for melanoma cancer detection","volume":"27","author":"Girdhar","year":"2023","journal-title":"Soft Comput."},{"key":"10.1016\/j.neucom.2026.133418_bib0070","doi-asserted-by":"crossref","DOI":"10.1016\/j.cma.2024.117109","article-title":"Vito: vision transformer-operator","volume":"428","author":"Ovadia","year":"2024","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"10.1016\/j.neucom.2026.133418_bib0075","series-title":"2024 4th International Conference on Artificial Intelligence and Signal Processing (AISP)","first-page":"1","article-title":"Crbc-an automated approach for handwriting OCR","author":"Purohit","year":"2024"},{"key":"10.1016\/j.neucom.2026.133418_bib0080","series-title":"2024 IEEE 3rd International Conference on Problems of Informatics, Electronics and Radio Engineering (PIERE)","first-page":"1780","article-title":"A system for classifying Kazakh language documents: morphological analysis and automatic keyword identification","author":"Yergesh","year":"2024"},{"issue":"7","key":"10.1016\/j.neucom.2026.133418_bib0085","doi-asserted-by":"crossref","first-page":"1824","DOI":"10.3390\/agronomy13071824","article-title":"A lightweight yolov8 tomato detection algorithm combining feature enhancement and attention","volume":"13","author":"Yang","year":"2023","journal-title":"Agronomy"},{"key":"10.1016\/j.neucom.2026.133418_bib0090","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105190","article-title":"Ldconv: linear deformable convolution for improving convolutional neural networks","volume":"149","author":"Zhang","year":"2024","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.neucom.2026.133418_bib0095","series-title":"2019 International Conference on Document Analysis and Recognition (ICDAR)","first-page":"615","article-title":"A new approach for integrated recognition and correction of texts from images","author":"Wei","year":"2019"},{"key":"10.1016\/j.neucom.2026.133418_bib0100","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.patrec.2022.04.022","article-title":"Harrisz+: Harris corner selection for next-gen image matching pipelines","volume":"158","author":"Bellavia","year":"2022","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.neucom.2026.133418_bib0105","first-page":"241","article-title":"An improved Shi-tomasi corner detection method","volume":"39","author":"Peng","year":"2022","journal-title":"Comput. Appl. Softw."},{"issue":"8","key":"10.1016\/j.neucom.2026.133418_bib0110","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1007\/s11128-023-04047-5","article-title":"Quantum fast corner detection algorithm","volume":"22","author":"Yuan","year":"2023","journal-title":"Quantum Inf. Process."},{"key":"10.1016\/j.neucom.2026.133418_bib0115","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106944","article-title":"Unmanned Aerial vehicle remote sensing image registration based on an improved oriented fast and rotated brief-random sample consensus algorithm","volume":"126","author":"Zhu","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.133418_bib0120","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","first-page":"224","article-title":"Superpoint: self-supervised interest point detection and description","author":"DeTone","year":"2018"},{"key":"10.1016\/j.neucom.2026.133418_bib0125","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"5836","article-title":"Key. Net: keypoint detection by handcrafted and learned CNN filters","author":"Barroso-Laguna","year":"2019"},{"key":"10.1016\/j.neucom.2026.133418_bib0130","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5551","article-title":"East: an efficient and accurate scene text detector","author":"Zhou","year":"2017"},{"key":"10.1016\/j.neucom.2026.133418_bib0135","series-title":"2022 Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems (SCIS&ISIS)","first-page":"1","article-title":"Soccer players real location determination using perspective transformation","author":"Karungaru","year":"2022"},{"key":"10.1016\/j.neucom.2026.133418_bib0140","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1879","article-title":"Iterative deep homography estimation","author":"Cao","year":"2022"},{"key":"10.1016\/j.neucom.2026.133418_bib0145","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9833","article-title":"Recurrent homography estimation using homography-guided image warping and focus transformer","author":"Cao","year":"2023"},{"key":"10.1016\/j.neucom.2026.133418_bib0150","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3712","article-title":"Taskonomy: disentangling task transfer learning","author":"Zamir","year":"2018"},{"key":"10.1016\/j.neucom.2026.133418_bib0155","first-page":"18878","article-title":"Conflict-averse gradient descent for multi-task learning","volume":"34","author":"Liu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133418_bib0160","series-title":"International Conference on Machine Learning","first-page":"794","article-title":"Gradnorm: gradient normalization for adaptive loss balancing in deep multitask networks","author":"Chen","year":"2018"},{"issue":"5","key":"10.1016\/j.neucom.2026.133418_bib0165","first-page":"818","article-title":"Midv-500: a dataset for identity document analysis and recognition on mobile devices in video stream","volume":"43","author":"Arlazarov","year":"2019","journal-title":"\u041a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u043d\u0430\u044f \u043e\u043f\u0442\u0438\u043a\u0430"},{"key":"10.1016\/j.neucom.2026.133418_bib0170","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4700","article-title":"Docunet: document image unwarping via a stacked u-net","author":"Ma","year":"2018"},{"issue":"6","key":"10.1016\/j.neucom.2026.133418_bib0175","first-page":"1","article-title":"Document rectification and illumination correction using a patch-based CNN","volume":"38","author":"Li","year":"2019","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.neucom.2026.133418_bib0180","series-title":"International Workshop on Document Analysis Systems","first-page":"131","article-title":"Dewarping document image by displacement flow estimation with fully convolutional network","author":"Xie","year":"2020"},{"key":"10.1016\/j.neucom.2026.133418_bib0185","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"131","article-title":"Dewarpnet: single-image document unwarping with stacked 3D and 2D regression networks","author":"Das","year":"2019"},{"key":"10.1016\/j.neucom.2026.133418_bib0190","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4268","article-title":"End-to-end piece-wise unwarping of document images","author":"Das","year":"2021"},{"key":"10.1016\/j.neucom.2026.133418_bib0195","series-title":"Proceedings of the 29th ACM International Conference on Multimedia","first-page":"273","article-title":"Doctr: document image transformer for geometric unwarping and illumination correction","author":"Feng","year":"2021"},{"key":"10.1016\/j.neucom.2026.133418_bib0200","series-title":"International Conference on Document Analysis and Recognition","first-page":"466","article-title":"Document dewarping with control points","author":"Xie","year":"2021"},{"key":"10.1016\/j.neucom.2026.133418_bib0205","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4573","article-title":"Fourier document restoration for robust document dewarping and recognition","author":"Xue","year":"2022"},{"key":"10.1016\/j.neucom.2026.133418_bib0210","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4543","article-title":"Revisiting document image dewarping by grid regularization","author":"Jiang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133418_bib0215","series-title":"European Conference on Computer Vision","first-page":"475","article-title":"Geometric representation learning for document image rectification","author":"Feng","year":"2022"},{"key":"10.1016\/j.neucom.2026.133418_bib0220","series-title":"ACM SIGGRAPH 2022 Conference Proceedings","first-page":"1","article-title":"Learning from documents in the wild to improve document unwarping","author":"Ma","year":"2022"},{"issue":"6","key":"10.1016\/j.neucom.2026.133418_bib0225","doi-asserted-by":"crossref","first-page":"4817","DOI":"10.1109\/TCSVT.2023.3336068","article-title":"Rethinking supervision in document unwarping: a self-consistent flow-free approach","volume":"34","author":"Liu","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133418_bib0230","series-title":"SIGGRAPH Asia 2023 Conference Papers","first-page":"1","article-title":"Uvdoc: neural grid-based document unwarping","author":"Verhoeven","year":"2023"},{"key":"10.1016\/j.neucom.2026.133418_bib0235","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"19574","article-title":"Foreground and text-lines aware document image rectification","author":"Li","year":"2023"},{"issue":"1","key":"10.1016\/j.neucom.2026.133418_bib0240","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3627818","article-title":"Layout-aware single-image document flattening","volume":"43","author":"Li","year":"2023","journal-title":"ACM Trans. Graph."},{"key":"10.1016\/j.neucom.2026.133418_bib0245","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"15137","article-title":"Forcennet: foreground-centric network for document image rectification","author":"Cai","year":"2025"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226008155?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226008155?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T20:27:15Z","timestamp":1776976035000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226008155"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":49,"alternative-id":["S0925231226008155"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133418","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Category-aware deep perspective transformation research","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133418","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"133418"}}