148 工程科学学报，第43卷，第1期 [2]Zhang Y Z.Image Engineering.4th Ed.Beijing:Tsinghua semantic segmentation /Proceedings of the 2015 IEEE Confe- University Press,2018 rence on Computer Vision and Pattern Recognition.Boston,2015: (章毓晋.图像工程.4版.北京：清华大学出版社，2018) 3431 [3]Xu R.An overview of image segmentation technique and [18]Ronneberger O,Fischer P,Brox T.U-Net:Convolutional networks performance evaluation.J Ningbo Univ Technol,2011,23(3):76 for biomedical image segmentation /International Conference on (徐瑞.图像分割方法及性能评价综述.宁波工程学院学报 Medical Image Computing and Computer-Assisted Intervention 2011,23(3):76) Springer,Cham,2015:234 [4]Gonzalez R C,Woods R E.Digital Image Processing.3rd Ed. [19]Li W,Field K G,Morgan D.Automated defect analysis in electron Upper Saddle River:Prentice Hall Press,2008 microscopic images.npj Comput Mater,2018,4:36 [5] Wang J,Xu X L,Liang K Y,et al.Thermal conductivity [20]Azimi S M,Britz D,Engstler M,et al.Advanced steel enhancement of porous shape-stabilized composite phase change microstructural classification by deep learning methods.Sci Rep, material for thermal energy storage applications:a review.ChinJ 2018,8:2128 Emg,2020,42(1):26 [21]Ma B Y,Ban X J,Huang H Y,et al.Deep learning-based image (王静静，徐小亮，梁凯彦度，等.多孔基定形复合相变材料传热性 segmentation for Al-La alloy microscopic images.Symmetry, 能提升研究进展.工程科学学报，2020,42(1)：26) 2018,10(4)107 [6]Cong M,Wu T,Liu D.et al.Prostate MR/TRUS image [22]Powers D M.Evaluation:from precision,recall and F-measure to segmentation and registration methods based on supervised ROC,informedness,markedness and correlation.J Mach Learn learning.Chin J Eng,2020,42(10):1362 Technol,.2011,2(1):37 (丛明，吴童，刘冬，等.基于监督学习的前列腺MR/TRUS图像分 [23]Dice L R.Measures of the amount of ecologic association between 割和配准方法.工程科学学报，2020,42(10)：1362) species.Ecology,1945,26(3):297 [7]Song X Y.Progress on the multi-disciplinary relationship of [24]Abdou I E,Pratt W K.Quantitative design and evaluation of stereology,image analysis and computational materials science. enhancement/thresholding edge detectors.Proc IEEE,1979, Chin J Stereol Image Anal,2008,13(4):280 67(5):753 (宋晓艳.体视学，图像分析与计算材料学之间的关系及进展 [25]Mosinska A,Marquez-Neila P,Kozinski M,et al.Beyond the 中国体视学与图像分析，2008,13(4)：280) pixel-wise loss for topology-aware delineation /Proceedings of [8]Rajan K.Materials informatics:The materials "gene"and big the 2018 IEEE/CVF Conference on Computer Vision and Pattern data.Ann Rev Mater Res,2015,45:153 Recognition.Salt Lake City,2018:3136 [9]Butler K T.Davies D W.Cartwright H,et al.Machine learning for [26]Yeung K Y,Ruzzo W L.Details of the adjusted rand index and molecular and materials science.Nature,2018,559(7715):547 clustering algorithms,supplement to the paper an empirical study [10]LeCun Y,Bengio Y,Hinton G.Deep learning.Nature,2015, on principal component analysis for clustering gene expression 521(7553):436 data.Bioinformatics,2001,17(9):763 [11]Otsu N.A threshold selection method from gray-level histograms. [27]Rand W M.Objective criteria for the evaluation of clustering IEEE Trans Syst Man Cybern,1979,9(1):62 methods.JAm Stat Assoc,1971,66(336):846 [12]Lakshmi S,Sankaranarayanan D V.A study of edge detection [28]Hubert L,Arabie P.Comparing partitions.J Classific,1985,2(1): techniques for segmentation computing approaches.Int/Compur 193 4ppl,2010,1(1):35 [29]Meila M.Comparing clusterings-an information based distance. [13]Roerdink J B T M,Meijster A.The watershed transform: JMultivar Anal,2007,98(5):873 definitions,algorithms and parallelization strategies.Fuodam [30]Nunez-Iglesias J,Kennedy R,Parag T,et al.Machine learning of mfom,2000,41(1-2:187 hierarchical clustering to segment 2D and 3D images.PLoS ONE, [14]Adams R,Bischof L.Seeded region growing.IEEE Trans Pattern 2013,8(8):e71715 Anal Mach Intell,1994,16(6):641 [31]Booz Allen Hamilton.Data Science BowlfJ/OL].Kaggle (2018- [15]Jain A K.Data clustering:50 years beyond K-means.Pattern 05-21)[2020-12-02].https://www.kaggle.com/c/data-science-bowl- Recognit Lett,2010,31(8):651 2018/overview/evaluation [16]Ma B Y,Ban X J,Su Y,et al.Fast-FineCut:Grain boundary [32]Lin T Y,Maire M,Belongie S,et al.Microsoft COCO:Common detection in microscopic images considering 3D information Objects in Contextl/European Conference on Computer Vision. Micron,2019,116:5 Zurich,2014:740 [17]Long J,Shelhamer E,Darrell T.Fully convolutional networks for [33]Waggoner J,Zhou Y J,Simmons J,et al.3D materials imageZhang  Y  Z. 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） [2] Xu  R.  An  overview  of  image  segmentation  technique  and performance evaluation. J Ningbo Univ Technol, 2011, 23（3）: 76 （徐瑞. 图像分割方法及性能评价综述. 宁波工程学院学报, 2011, 23（3）：76） [3] Gonzalez  R  C,  Woods  R  E. Digital Image Processing.  3rd  Ed. Upper Saddle River: Prentice Hall Press, 2008 [4] Wang  J,  Xu  X  L,  Liang  K  Y,  et  al.  Thermal  conductivity enhancement  of  porous  shape-stabilized  composite  phase  change material for thermal energy storage applications: a review. Chin J Eng, 2020, 42（1）: 26 （王静静, 徐小亮, 梁凯彦, 等. 多孔基定形复合相变材料传热性 能提升研究进展. 工程科学学报, 2020, 42（1）：26） [5] Cong  M,  Wu  T,  Liu  D,  et  al.  Prostate  MR/TRUS  image segmentation  and  registration  methods  based  on  supervised learning. Chin J Eng, 2020, 42（10）: 1362 （丛明, 吴童, 刘冬, 等. 基于监督学习的前列腺MR/TRUS图像分 割和配准方法. 工程科学学报, 2020, 42（10）：1362） [6] Song  X  Y.  Progress  on  the  multi-disciplinary  relationship  of stereology,  image  analysis  and  computational  materials  science. Chin J Stereol Image Anal, 2008, 13（4）: 280 （宋晓艳. 体视学, 图像分析与计算材料学之间的关系及进展. 中国体视学与图像分析, 2008, 13（4）：280） [7] Rajan  K.  Materials  informatics:  The  materials “ gene” and  big data. Ann Rev Mater Res, 2015, 45: 153 [8] Butler K T, Davies D W, Cartwright H, et al. Machine learning for molecular and materials science. Nature, 2018, 559（7715）: 547 [9] LeCun  Y,  Bengio  Y,  Hinton  G.  Deep  learning. Nature,  2015, 521（7553）: 436 [10] Otsu N. A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern, 1979, 9（1）: 62 [11] Lakshmi  S,  Sankaranarayanan  D  V.  A  study  of  edge  detection techniques for segmentation computing approaches. Int J Comput Appl, 2010, 1（1）: 35 [12] Roerdink  J  B  T  M,  Meijster  A.  The  watershed  transform: definitions,  algorithms  and  parallelization  strategies. Fundam Inform, 2000, 41（1-2）: 187 [13] Adams R, Bischof L. Seeded region growing. IEEE Trans Pattern Anal Mach Intell, 1994, 16（6）: 641 [14] Jain  A  K.  Data  clustering:  50  years  beyond  K-means. Pattern Recognit Lett, 2010, 31（8）: 651 [15] Ma  B  Y,  Ban  X  J,  Su  Y,  et  al.  Fast-FineCut:  Grain  boundary detection  in  microscopic  images  considering  3D  information. Micron, 2019, 116: 5 [16] [17] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic  segmentation  // Proceedings of the 2015 IEEE Confe￾rence on Computer Vision and Pattern Recognition. Boston, 2015: 3431 Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation // International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 2015: 234 [18] Li W, Field K G, Morgan D. Automated defect analysis in electron microscopic images. npj Comput Mater, 2018, 4: 36 [19] Azimi  S  M,  Britz  D,  Engstler  M,  et  al.  Advanced  steel microstructural  classification  by  deep  learning  methods. Sci Rep, 2018, 8: 2128 [20] Ma B Y, Ban X J, Huang H Y, et al. Deep learning-based image segmentation  for  Al−La  alloy  microscopic  images. Symmetry, 2018, 10（4）: 107 [21] Powers D M. Evaluation: from precision, recall and F-measure to ROC,  informedness,  markedness  and  correlation. J Mach Learn Technol, 2011, 2（1）: 37 [22] Dice L R. Measures of the amount of ecologic association between species. Ecology, 1945, 26（3）: 297 [23] Abdou  I  E,  Pratt  W  K.  Quantitative  design  and  evaluation  of enhancement/thresholding  edge  detectors. Proc IEEE,  1979, 67（5）: 753 [24] Mosinska  A,  Marquez-Neila  P,  Koziński  M,  et  al.  Beyond  the pixel-wise  loss  for  topology-aware  delineation  // Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 3136 [25] Yeung  K  Y,  Ruzzo  W  L.  Details  of  the  adjusted  rand  index  and clustering algorithms, supplement to the paper an empirical study on  principal  component  analysis  for  clustering  gene  expression data. Bioinformatics, 2001, 17（9）: 763 [26] Rand  W  M.  Objective  criteria  for  the  evaluation  of  clustering methods. J Am Stat Assoc, 1971, 66（336）: 846 [27] Hubert L, Arabie P. Comparing partitions. J Classific, 1985, 2（1）: 193 [28] Meilă M. Comparing clusterings — an information based distance. J Multivar Anal, 2007, 98（5）: 873 [29] Nunez-Iglesias J, Kennedy R, Parag T, et al. Machine learning of hierarchical clustering to segment 2D and 3D images. PLoS ONE, 2013, 8（8）: e71715 [30] Booz  Allen  Hamilton.  Data  Science  Bowl[J/OL]. Kaggle (2018- 05-21)[2020-12-02]. https://www.kaggle.com/c/data-science-bowl- 2018/overview/evaluation [31] Lin T Y, Maire M, Belongie S, et al. Microsoft COCO: Common Objects  in  Context// European Conference on Computer Vision. Zurich, 2014: 740 [32] [33] Waggoner  J,  Zhou  Y  J,  Simmons  J,  et  al.  3D  materials  image · 148 · 工程科学学报，第 43 卷，第 1 期