{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T05:29:42Z","timestamp":1771306182447,"version":"3.50.1"},"reference-count":59,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T00:00:00Z","timestamp":1745798400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>Due to the many difficulties in accurately locating edges or boundaries in images of animals, plants, buildings, and the like with complex backgrounds, edge detection has become one of the most challenging tasks in the field of computer vision and is also a key step in many computer vision applications. Although existing deep learning-based methods can detect the edges of images relatively well, when the image background is rather complex and the key target is small, accurately detecting the edge of the main body and removing background interference remains a daunting task. Therefore, this paper proposes a multi-scale edge detection network based on spatial-frequency domain interactive attention, aiming to achieve accurate detection of the edge of the main target on multiple scales. The use of the spatial-frequency domain interactive attention module can not only perform significant edge extraction by filtering out some interference in the frequency domain. Moreover, by utilizing the interaction between the frequency domain and the spatial domain, edge features at different scales can be extracted and analyzed more accurately. The obtained results are superior to the current edge detection networks in terms of performance indicators and output image quality.<\/jats:p>","DOI":"10.3389\/fnbot.2025.1550939","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T05:29:52Z","timestamp":1745818192000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Multi-scale image edge detection based on spatial-frequency domain interactive attention"],"prefix":"10.3389","volume":"19","author":[{"given":"Yongfei","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weilong","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,4,28]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/T-C.1974.223784","article-title":"Discrete cosine transform","volume":"100","author":"Ahmed","year":"1974","journal-title":"IEEE Trans. Comp"},{"key":"B2","doi-asserted-by":"publisher","first-page":"74646","DOI":"10.1109\/ACCESS.2021.3078411","article-title":"Rhn: A residual holistic neural network for edge detection","volume":"9","author":"Al-Amaren","year":"2021","journal-title":"IEEE Access"},{"key":"B3","first-page":"1055","article-title":"The jpeg image compression algorithm","volume":"6","author":"Al-Ani","year":"2013","journal-title":"Int. J. Adv. Eng. Technol"},{"key":"B4","doi-asserted-by":"crossref","first-page":"875","DOI":"10.1007\/978-3-030-63416-2_660","article-title":"\u201cObject detection,\u201d","volume-title":"Computer Vision: A Reference Guide","author":"Amit","year":"2021"},{"key":"B5","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1109\/TPAMI.2010.161","article-title":"Contour detection and hierarchical image segmentation","volume":"33","author":"Arbelaez","year":"2010","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B6","doi-asserted-by":"publisher","first-page":"4380","DOI":"10.1109\/CVPR.2015.7299067","article-title":"\u201cDeepEdge: a multi-scale bifurcated deep network for top-down contour detection,\u201d","author":"Bertasius","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B7","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.patcog.2018.05.008","article-title":"An adaptive-scale active contour model for inhomogeneous image segmentation and bias field estimation","volume":"82","author":"Cai","year":"2018","journal-title":"Pattern Recognit"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3083888","article-title":"Multiscale adaptive edge detector for images based on a novel standard deviation map","volume":"70","author":"Cui","year":"2021","journal-title":"IEEE Trans. Instrum. Meas"},{"key":"B9","first-page":"562","article-title":"\u201cLearning to predict crisp boundaries,\u201d","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Deng","year":"2018"},{"key":"B10","doi-asserted-by":"publisher","first-page":"3539","DOI":"10.1109\/TPAMI.2022.3180556","article-title":"Mvss-net: Multi-view multi-scale supervised networks for image manipulation detection","volume":"45","author":"Dong","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B11","doi-asserted-by":"publisher","first-page":"109361","DOI":"10.1016\/j.patcog.2023.109361","article-title":"Refined edge detection with cascaded and high-resolution convolutional network","volume":"138","author":"Elharrouss","year":"2023","journal-title":"Pattern Recognit"},{"key":"B12","doi-asserted-by":"publisher","first-page":"613","DOI":"10.3390\/rs14030613","article-title":"Semantic segmentation and edge detection approach to road detection in very high resolution satellite images","volume":"14","author":"Ghandorh","year":"2022","journal-title":"Remote Sens"},{"key":"B13","doi-asserted-by":"publisher","first-page":"722","DOI":"10.3390\/rs10050722","article-title":"Speckle suppression by weighted euclidean distance anisotropic diffusion","volume":"10","author":"Guo","year":"2018","journal-title":"Remote Sens"},{"key":"B14","doi-asserted-by":"publisher","first-page":"141824","DOI":"10.1109\/ACCESS.2020.3012997","article-title":"Road identification algorithm for remote sensing images based on wavelet transform and recursive operator","volume":"8","author":"Guobin","year":"2020","journal-title":"IEEE Access"},{"key":"B15","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.camwa.2021.03.029","article-title":"An efficient anisotropic diffusion model for image denoising with edge preservation","volume":"93","author":"Gupta","year":"2021","journal-title":"Comp. Mathem. Appl"},{"key":"B16","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1109\/TPAMI.2020.3007074","article-title":"Bdcn: Bi-directional cascade network for perceptual edge detection","volume":"44","author":"He","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B17","first-page":"770","article-title":"\u201cDeep residual learning for image recognition,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"key":"B18","doi-asserted-by":"publisher","first-page":"4694","DOI":"10.1109\/TPAMI.2022.3201185","article-title":"Image feature information extraction for interest point detection: a comprehensive review","volume":"45","author":"Jing","year":"","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B19","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/j.neucom.2022.06.083","article-title":"Recent advances on image edge detection: a comprehensive review","volume":"503","author":"Jing","year":"","journal-title":"Neurocomputing"},{"key":"B20","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1007\/978-3-030-29888-3_20","article-title":"\u201cObject contour and edge detection with refinecontournet,\u201d","volume-title":"Computer Analysis of Images and Patterns","author":"Kelm","year":"2019"},{"key":"B21","doi-asserted-by":"publisher","first-page":"90153","DOI":"10.1109\/ACCESS.2020.2994160","article-title":"REDN: a recursive encoder-decoder network for edge detection","volume":"8","author":"Le","year":"2020","journal-title":"IEEE Access"},{"key":"B22","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1109\/TRPMS.2024.3473929","article-title":"Semi-supervised 3d medical image segmentation using multi-consistency learning with fuzzy perception-guided target selection","author":"Lei","year":"2024","journal-title":"IEEE Trans. Radiat. Plasma Med. Sci"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3568678","article-title":"Multi-scale edge-guided learning for 3d reconstruction","volume":"19","author":"Li","year":"2023","journal-title":"ACM Trans. Multimedia Comp. Commun. Appl"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1109\/ACCESS.2019.2962520","article-title":"Multi-scale anisotropic gaussian kernels for image edge detection","volume":"8","author":"Li","year":"2019","journal-title":"IEEE Access"},{"key":"B25","doi-asserted-by":"publisher","first-page":"111607","DOI":"10.1016\/j.patcog.2025.111607","article-title":"Dynamic accumulated attention map for interpreting evolution of decision-making in vision transformer","volume":"2025","author":"Liao","year":"2025","journal-title":"Pattern Recognit"},{"key":"B26","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.patrec.2022.01.006","article-title":"Edge detection with attention: from global view to local focus","volume":"154","author":"Liu","year":"2022","journal-title":"Pattern Recognit. Lett"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1939","DOI":"10.1109\/TPAMI.2018.2878849","article-title":"Richer convolutional features for edge detection","volume":"41","author":"Liu","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B28","first-page":"3000","article-title":"\u201cRicher convolutional features for edge detection,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Liu","year":"2017"},{"key":"B29","doi-asserted-by":"publisher","first-page":"104550","DOI":"10.1016\/j.dsp.2024.104550","article-title":"A laplace operator-based active contour model with improved image edge detection performance","volume":"151","author":"Ma","year":"2024","journal-title":"Digit. Signal Process"},{"key":"B30","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1016\/j.inffus.2020.08.014","article-title":"Multi-scale spatial context-based semantic edge detection","volume":"64","author":"Ma","year":"2020","journal-title":"Inform. Fusion"},{"key":"B31","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.visres.2015.11.007","article-title":"A systematic comparison between visual cues for boundary detection","volume":"120","author":"M\u00e9ly","year":"2016","journal-title":"Vision Res"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2003.08235","article-title":"CafeNet: class-agnostic few-shot edge detection network","author":"Park","year":"2020","journal-title":"arXiv"},{"key":"B33","first-page":"1402","article-title":"\u201cEdter: edge detection with transformer,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Pu","year":"2022"},{"key":"B34","doi-asserted-by":"publisher","first-page":"492","DOI":"10.3390\/jpm11060492","article-title":"Recurrent convolutional neural networks for 3D mandible segmentation in computed tomography","volume":"11","author":"Qiu","year":"2021","journal-title":"J. Pers. Med"},{"key":"B35","doi-asserted-by":"publisher","first-page":"405","DOI":"10.3390\/ai5010020","article-title":"Few-shot fine-grained image classification: a comprehensive review","volume":"5","author":"Ren","year":"2024","journal-title":"AI"},{"key":"B36","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1016\/j.cam.2018.08.006","article-title":"Edge detection methods based on rbf interpolation","volume":"349","author":"Romani","year":"2019","journal-title":"J. Comput. Appl. Math"},{"key":"B37","doi-asserted-by":"publisher","first-page":"806","DOI":"10.1016\/j.patcog.2011.07.020","article-title":"Noise-robust edge detector combining isotropic and anisotropic gaussian kernels","volume":"45","author":"Shui","year":"2012","journal-title":"Pattern Recognit"},{"key":"B38","first-page":"746","article-title":"\u201cIndoor segmentation and support inference from RGBD images,\u201d","volume-title":"Proceedings of the European Conference on Computer","author":"Silberman","year":"2012"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.1556","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv"},{"key":"B40","doi-asserted-by":"publisher","first-page":"109461","DOI":"10.1016\/j.patcog.2023.109461","article-title":"Dense extreme inception network for edge detection","volume":"139","author":"Soria","year":"2023","journal-title":"Pattern Recognit"},{"key":"B41","first-page":"5117","article-title":"\u201cPixel difference networks for efficient edge detection,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Su","year":"2021"},{"key":"B42","doi-asserted-by":"publisher","first-page":"7737","DOI":"10.3390\/s24237737","article-title":"An unbiased feature estimation network for few-shot fine-grained image classification","volume":"24","author":"Wang","year":"2024","journal-title":"Sensors"},{"key":"B43","first-page":"3892","article-title":"\u201cDeep crisp boundaries,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Wang","year":"2017"},{"key":"B44","doi-asserted-by":"publisher","first-page":"110112","DOI":"10.1016\/j.patcog.2023.110112","article-title":"Feature fusion method based on spiking neural convolutional network for edge detection","volume":"147","author":"Xian","year":"2024","journal-title":"Pattern Recognit"},{"key":"B45","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s11263-017-1004-z","article-title":"Holistically-nested edge detection","volume":"125","author":"Xie","year":"2017","journal-title":"Int. J. Comput. Vis"},{"key":"B46","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1016\/j.neunet.2021.10.022","article-title":"Fcl-net: Towards accurate edge detection via fine-scale corrective learning","volume":"145","author":"Xuan","year":"2022","journal-title":"Neural Netw"},{"key":"B47","first-page":"6675","article-title":"\u201cDiffusionedge: diffusion probabilistic model for crisp edge detection,\u201d","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Ye","year":"2024"},{"key":"B48","doi-asserted-by":"publisher","first-page":"1837","DOI":"10.3390\/app13031837","article-title":"Research on image denoising in edge detection based on wavelet transform","volume":"13","author":"You","year":"2023","journal-title":"Appl. Sci"},{"key":"B49","doi-asserted-by":"publisher","first-page":"3300533","DOI":"10.1109\/TGRS.2023.3300533","article-title":"AERNet: an attention-guided edge refinement network and a dataset for remote sensing building change detection","volume":"17","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"B50","doi-asserted-by":"publisher","first-page":"1213","DOI":"10.1109\/TPAMI.2019.2949302","article-title":"Corner detection using second-order generalized gaussian directional derivative representations","volume":"43","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B51","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1007\/s11263-019-01257-2","article-title":"Corner detection using multi-directional structure tensor with multiple scales","volume":"128","author":"Zhang","year":"2020","journal-title":"Int. J. Comput. Vis"},{"key":"B52","doi-asserted-by":"publisher","first-page":"4444","DOI":"10.1109\/TIP.2019.2910655","article-title":"Discrete curvature representations for noise robust image corner detection","volume":"28","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Image Proc"},{"key":"B53","doi-asserted-by":"publisher","first-page":"9883","DOI":"10.1109\/TPAMI.2023.3240129","article-title":"Image intensity variation information for interest point detection","volume":"45","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B54","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.patcog.2016.10.008","article-title":"Noise robust image edge detection based upon the automatic anisotropic gaussian kernels","volume":"63","author":"Zhang","year":"2017","journal-title":"Pattern Recognit"},{"key":"B55","doi-asserted-by":"publisher","first-page":"110158","DOI":"10.1016\/j.patcog.2023.110158","article-title":"Re-abstraction and perturbing support pair network for few-shot fine-grained image classification","volume":"148","author":"Zhang","year":"2024","journal-title":"Pattern Recognit"},{"key":"B56","doi-asserted-by":"publisher","first-page":"2785","DOI":"10.1016\/j.patcog.2015.03.021","article-title":"Contour-based corner detection via angle difference of principal directions of anisotropic gaussian directional derivatives","volume":"48","author":"Zhang","year":"2015","journal-title":"Pattern Recognit"},{"key":"B57","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1049\/iet-ipr.2013.0641","article-title":"Corner detection using gabor filters","volume":"8","author":"Zhang","year":"2014","journal-title":"IET Image Process"},{"key":"B58","doi-asserted-by":"crossref","DOI":"10.3233\/ATDE220014","article-title":"\u201cEdge detection algorithm based on threshold function de-noising and wavelet neural network,\u201d","volume-title":"Applied Mathematics, Modeling and Computer Simulation","author":"Zhang","year":"2022"},{"key":"B59","doi-asserted-by":"publisher","first-page":"122063","DOI":"10.1088\/1742-6596\/2478\/12\/122063","article-title":"Edge detection ghost imaging using frequency-domain filtering","volume":"2478","author":"Zheng","year":"2023","journal-title":"J. Phys"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2025.1550939\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T05:29:56Z","timestamp":1745818196000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2025.1550939\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,28]]},"references-count":59,"alternative-id":["10.3389\/fnbot.2025.1550939"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2025.1550939","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,28]]},"article-number":"1550939"}}