印象等：面向显微影像的多聚焦多图融合中失焦扩散效应消除方法 ·1181 [3]Zhang Y J.Image Engineering.4th ed.Beijing:Tsinghua Based on Deep Learning [Dissertation].Kunming:Yunnan University Press,2018 University,2018 (章毓晋.图像工程.4版.北京：清华大学出版社，2018) (王镖堡.基于深度学习的多聚焦图像算法研究学位论文1.昆 [4]Burt P,Adelson E.The Laplacian pyramid as a compact image 明：云南大学，2018) code.IEEE Trans Commun,1983,31(4大：532 [20]Ma H,Liao Q,Zhang J,et al.An a-Matte Boundary Defocus [5]Toet A.Image fusion by a ratio of low-pass pyramid.Partern Model Based Cascaded Network for Multi-focus Image Recognit Lett,1989,9(4):245 Fusion[J/OL].ArXiv Preprint (2019-10-30)[2021-01-12] [6]Li H,Manjunath B S,Mitra S K.Multisensor image fusion using https://arxiv.org/abs/1910.13136 the wavelet transform.Graph Models Image Process,1995,57(3): [21]He K,Wei Y,Wang Y,et al.An improved non-rigid image 235 registration approach.Chin J Eng,2019,41(7):955 [7]Li S T,Kwok J T,Wang Y N.Combination of images with diverse (何凯，魏颖，王阳，等.一种改进的非刚性图像配准算法.工程 focuses using the spatial frequency.InfFusion,001,2(3):169 科学学报，2019,41(7)：955) [8]Li S T,Kang X D,Hu J W.Image fusion with guided filtering [22]Chen S W,Zhang S X,Yang X G,et al.Registration of visual- IEEE Trans Image Process,2013,22(7):2864 infrared images based on ellipse symmetrical orientation moment [9]Zhou Z Q,Li S,Wang B.Multi-scale weighted gradient-based Chin J Eng,2017,39(7):1107 fusion for multi-focus images.Inf Fusion,2014,20:60 (陈世伟，张胜修，杨小冈，等.基于椭圆对称方向矩的可见光与 [10]Liu Y,Liu S P,Wang Z F.Multi-focus image fusion with dense 红外图像配准算法.工程科学学报，2017,39(7)：1107) SIFT.Inf Fusion,2015,23:139 [23]Hu J,Shen L.Sun G.Squeeze-and-excitation networks//2018 [11]LeCun Y,Bengio Y,Hinton G.Deep learning.Namre,2015, IEEEICVF Conference on Computer Vision and Pattern 521(7553):436 Recognition.Salt Lake City,2018:7132 [12]Liu Y,Chen X,Peng H,et al.Multi-focus image fusion with a [24]Lin T Y,Maire M,Belongie S,et al.Microsofi COCO:Common deep convolutional neural network.InfFusion,2017,36:191 Objects in Context.Computer Vision ECCV 2014.Cham: [13]Ma,B Y,Zhu Y,Yin X,et al.SESF-Fuse:An unsupervised deep Springer International Publishing,2014 model for multi-focus image fusion.Neural Comput Appl,2021. 33:5793 [25]Ma B Y,Yin X.The Code of SESF-Fuse for multi-focus image [14]Xu H,MaJY,Jiang JJ,et al.U2Fusion:A unified unsupervised fusion [J/OL].Github (2019-08-21)[2021-01-12].https://github. com/Keep-Passion/SESF-Fuse image fusion network.IEEE Trans Pattern Anal Mach Intell, 10.1109/TPAM1.2020.3012548 (马博渊，印象.SESF-Fuse的多聚焦图像融合开源代码卩/OL]. [15]Prabhakar K R,Srikar V S,Babu R V.DeepFuse:A deep Github (2019-08-21)[2021-01-121.https://github.com/Keep- Passion/SESF-Fuse) unsupervised approach for exposure fusion with extreme exposure image pairs//IEEE International Conference on Computer Vision [26]Kingma D,Ba J.Adam:A method for stochastic Venice,2017:4724 optimization[J/OL].ArXiv Preprint (2017-01-30)[2021-01-121. [16]Ma B Y,Yin X.Wu D,et al.Gradient Aware Cascade Network for https://arxiv.org/abs/1412.6980 Multi-Focus Image Fusion[J/OLl.ArXiv Preprint (2020-10-01) [27]Paszke A,Gross S,Massa F,et al.Py Torch:An imperative style. [2021-01-12].https://arxiv..org/abs/2010.08751 high-performance deep learning library[J/OL].ArXiv Preprint [17]Xu H,Fan F,Zhang H,et al.A deep model for multi-focus image (2019-12-3)[2021-01-12].https:/axiv.org/abs/1912.01703 fusion based on gradients and connected regions.IEEE Access, [28]Mao X Y.Introduction to OpenCV3 Programming.Beijing 2020,8:26316 Electronics industry publishing house,2015 [18]Huang J,Le Z L,Ma Y,et al.A generative adversarial network (毛星云.0 penCV3编程入门.北京：电子工业出版社，2015) with adaptive constraints for multi-focus image fusion.Neural [29]Xu S,Ji L Z,Wang Z,et al.Towards reducing severe defocus Comput4pl,2020,32(18):15119 spread effects for multi-focus image fusion via an optimization [19]Wang BB.Research on Multi-Focus Image Fusion Algorithm based strategy.IEEE Trans Comput Imaging,2020,6:1561Zhang  Y  J. Image Engineering.  4th  ed.  Beijing:  Tsinghua University Press, 2018 （ 章毓晋. 图像工程. 4版. 北京: 清华大学出版社, 2018） [3] Burt  P,  Adelson  E.  The  Laplacian  pyramid  as  a  compact  image code. IEEE Trans Commun, 1983, 31（4）: 532 [4] Toet  A.  Image  fusion  by  a  ratio  of  low-pass  pyramid. Pattern Recognit Lett, 1989, 9（4）: 245 [5] Li H, Manjunath B S, Mitra S K. Multisensor image fusion using the wavelet transform. Graph Models Image Process, 1995, 57（3）: 235 [6] Li S T, Kwok J T, Wang Y N. Combination of images with diverse focuses using the spatial frequency. Inf Fusion, 2001, 2（3）: 169 [7] Li  S  T,  Kang  X  D,  Hu  J  W.  Image  fusion  with  guided  filtering. IEEE Trans Image Process, 2013, 22（7）: 2864 [8] Zhou  Z  Q,  Li  S,  Wang  B.  Multi-scale  weighted  gradient-based fusion for multi-focus images. Inf Fusion, 2014, 20: 60 [9] Liu Y, Liu S P, Wang Z F. Multi-focus image fusion with dense SIFT. Inf Fusion, 2015, 23: 139 [10] LeCun  Y,  Bengio  Y,  Hinton  G.  Deep  learning. Nature,  2015, 521（7553）: 436 [11] Liu  Y,  Chen  X,  Peng  H,  et  al.  Multi-focus  image  fusion  with  a deep convolutional neural network. Inf Fusion, 2017, 36: 191 [12] Ma, B Y, Zhu Y, Yin X, et al. SESF−Fuse: An unsupervised deep model  for  multi-focus  image  fusion. Neural Comput Appl,  2021, 33: 5793 [13] Xu H, Ma J Y, Jiang J J, et al. U2Fusion: A unified unsupervised image  fusion  network. IEEE Trans Pattern Anal Mach Intell, 10.1109/TPAMI.2020.3012548 [14] Prabhakar  K  R,  Srikar  V  S,  Babu  R  V.  DeepFuse:  A  deep unsupervised approach for exposure fusion with extreme exposure image pairs// IEEE International Conference on Computer Vision. Venice, 2017: 4724 [15] Ma B Y, Yin X, Wu D, et al. Gradient Aware Cascade Network for Multi-Focus  Image  Fusion[J/OL]. ArXiv Preprint (2020-10-01) [2021-01-12]. https://arxiv.org/abs/2010.08751 [16] Xu H, Fan F, Zhang H, et al. A deep model for multi-focus image fusion  based  on  gradients  and  connected  regions. IEEE Access, 2020, 8: 26316 [17] Huang  J,  Le  Z  L,  Ma  Y,  et  al.  A  generative  adversarial  network with  adaptive  constraints  for  multi-focus  image  fusion. Neural Comput Appl, 2020, 32（18）: 15119 [18] [19] Wang  B  B. Research on Multi-Focus Image Fusion Algorithm Based on Deep Learning [Dissertation].  Kunming:  Yunnan University, 2018 （ 王镖堡. 基于深度学习的多聚焦图像算法研究[学位论文]. 昆 明: 云南大学, 2018） Ma  H,  Liao  Q,  Zhang  J,  et  al.  An  α-Matte  Boundary  Defocus Model  Based  Cascaded  Network  for  Multi-focus  Image Fusion[J/OL]. ArXiv Preprint (2019-10-30)  [2021-01-12]. https://arxiv.org/abs/1910.13136 [20] He  K,  Wei  Y,  Wang  Y,  et  al.  An  improved  non-rigid  image registration approach. Chin J Eng, 2019, 41（7）: 955 （何凯, 魏颖, 王阳, 等. 一种改进的非刚性图像配准算法. 工程 科学学报, 2019, 41（7）：955） [21] Chen  S  W,  Zhang  S  X,  Yang  X  G,  et  al.  Registration  of  visual￾infrared images based on ellipse symmetrical orientation moment. Chin J Eng, 2017, 39（7）: 1107 （陈世伟, 张胜修, 杨小冈, 等. 基于椭圆对称方向矩的可见光与 红外图像配准算法. 工程科学学报, 2017, 39（7）：1107） [22] Hu  J,  Shen  L,  Sun  G.  Squeeze-and-excitation  networks//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 7132 [23] Lin T Y, Maire M, Belongie S, et al. Microsoft COCO: Common Objects in Context. Computer Vision – ECCV 2014.  Cham: Springer International Publishing, 2014 [24] Ma B Y, Yin X. The Code of SESF−Fuse for multi-focus image fusion  [J/OL]. Github (2019-08-21)  [2021-01-12]. https://github. com/Keep-Passion/SESF-Fuse （ 马博渊, 印象. SESF−Fuse的多聚焦图像融合开源代码[J/OL]. Github (2019-08-21)  [2021-01-12]. https://github.com/Keep￾Passion/SESF-Fuse） [25] Kingma  D,  Ba  J.  Adam:  A  method  for  stochastic optimization[J/OL]. ArXiv Preprint (2017-01-30)  [2021-01-12]. https://arxiv.org/abs/1412.6980 [26] Paszke A, Gross S, Massa F, et al. Py Torch: An imperative style, high-performance  deep  learning  library[J/OL]. ArXiv Preprint (2019-12-3) [2021-01-12]. https://arxiv.org/abs/1912.01703 [27] Mao  X  Y. Introduction to OpenCV3 Programming.  Beijing: Electronics industry publishing house, 2015 （ 毛星云. OpenCV3编程入门. 北京: 电子工业出版社, 2015） [28] Xu  S,  Ji  L  Z,  Wang  Z,  et  al.  Towards  reducing  severe  defocus spread  effects  for  multi-focus  image  fusion via an  optimization based strategy. IEEE Trans Comput Imaging, 2020, 6: 1561 [29] 印    象等： 面向显微影像的多聚焦多图融合中失焦扩散效应消除方法 · 1181 ·