{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T18:48:50Z","timestamp":1767984530825,"version":"3.49.0"},"reference-count":58,"publisher":"MIT Press - Journals","issue":"7","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2018,7]]},"abstract":"<jats:p> As the optical lenses for cameras always have limited depth of field, the captured images with the same scene are not all in focus. Multifocus image fusion is an efficient technology that can synthesize an all-in-focus image using several partially focused images. Previous methods have accomplished the fusion task in spatial or transform domains. However, fusion rules are always a problem in most methods. In this letter, from the aspect of focus region detection, we propose a novel multifocus image fusion method based on a fully convolutional network (FCN) learned from synthesized multifocus images. The primary novelty of this method is that the pixel-wise focus regions are detected through a learning FCN, and the entire image, not just the image patches, are exploited to train the FCN. First, we synthesize 4500 pairs of multifocus images by repeatedly using a gaussian filter for each image from PASCAL VOC 2012, to train the FCN. After that, a pair of source images is fed into the trained FCN, and two score maps indicating the focus property are generated. Next, an inversed score map is averaged with another score map to produce an aggregative score map, which take full advantage of focus probabilities in two score maps. We implement the fully connected conditional random field (CRF) on the aggregative score map to accomplish and refine a binary decision map for the fusion task. Finally, we exploit the weighted strategy based on the refined decision map to produce the fused image. To demonstrate the performance of the proposed method, we compare its fused results with several start-of-the-art methods not only on a gray data set but also on a color data set. Experimental results show that the proposed method can achieve superior fusion performance in both human visual quality and objective assessment. <\/jats:p>","DOI":"10.1162\/neco_a_01098","type":"journal-article","created":{"date-parts":[[2018,6,12]],"date-time":"2018-06-12T21:54:50Z","timestamp":1528840490000},"page":"1775-1800","source":"Crossref","is-referenced-by-count":80,"title":["Fully Convolutional Network-Based Multifocus Image Fusion"],"prefix":"10.1162","volume":"30","author":[{"given":"Xiaopeng","family":"Guo","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University, Kunming, Yunnan 650091, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rencan","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University, Kunming, Yunnan 650091, China, and School of Automation, Southeast University, Jiangsu, Nanjing 210096, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinde","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Mathematics, Southeast University, Jiangsu, Nanjing 210096, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongming","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University, Kunming, Yunnan 650091, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhua","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Yunnan University, Kunming, Yunnan 650091, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2010.06.011"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2017.02.003"},{"key":"B3","first-page":"1","volume-title":"Proceedings of the International Conference on Pattern Recognition and Image Analysis","author":"Azarang A.","year":"2017"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2012.01.007"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859376"},{"key":"B8","author":"Everingham M.","year":"2011","journal-title":"The Pascal visual object classes challenge 2012 (voc2012) results (2012)"},{"key":"B9","first-page":"2758","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Fischer P.","year":"2015"},{"key":"B10","first-page":"249","volume":"9","author":"Glorot X.","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.213"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2007.01.013"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2014.2376034"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073609"},{"key":"B17","first-page":"109","volume-title":"Advances in neural information processing systems","volume":"24","author":"Kr\u00e4henb\u00fchl P.","year":"2011"},{"key":"B18","first-page":"1097","volume-title":"Advances in neural information processing systems","volume":"25","author":"Krizhevsky A.","year":"2012"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-012-0361-x"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-013-0556-9"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2005.09.006"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1006\/gmip.1995.1022"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2244222"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2011.07.001"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/S1566-2535(01)00038-0"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(02)00029-6"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2007.10.012"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.23919\/ICIF.2017.8009769"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2016.12.001"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.10.007"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2014.05.004"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2017.02.006"},{"key":"B35","volume-title":"Information theory, inference and learning algorithms","author":"MacKay D. J.","year":"2003"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2014.10.004"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2004.03.010"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2017.2668299"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.823821"},{"key":"B40","first-page":"1","volume-title":"Proceedings of the International Workshop on Remote Sensing with Intelligent Processing","author":"Rao Y.","year":"2017"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2005.1550194"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2005.859378"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"B44","author":"Simonyan K.","year":"2014","journal-title":"Very deep convolutional networks for large-scale image recognition"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925972"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2002.801588"},{"key":"B47","volume-title":"Image fusion: Algorithms and applications","author":"Stathaki T.","year":"2008"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2012.01.027"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1016\/j.optcom.2010.08.085"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.01.011"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2017.2736020"},{"key":"B52","first-page":"1395","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Xie S.","year":"2016"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1049\/el:20000267"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2009.05.001"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.07.039"},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2009.01.012"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2016.09.006"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2013.11.005"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/neco_a_01098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:42:34Z","timestamp":1615585354000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/30\/7\/1775-1800\/8402"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":58,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2018,7]]}},"alternative-id":["10.1162\/neco_a_01098"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_01098","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,7]]}}}