2.845

2023影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

一种鲁棒的基于对抗结构的生物特征ROI提取方法

刘凤 刘浩哲 张文天 陈嘉树 沈琳琳 王磊

刘凤, 刘浩哲, 张文天, 陈嘉树, 沈琳琳, 王磊. 一种鲁棒的基于对抗结构的生物特征ROI提取方法. 自动化学报, 2023, 49(6): 1339−1353 doi: 10.16383/j.aas.c200156
引用本文: 刘凤, 刘浩哲, 张文天, 陈嘉树, 沈琳琳, 王磊. 一种鲁棒的基于对抗结构的生物特征ROI提取方法. 自动化学报, 2023, 49(6): 1339−1353 doi: 10.16383/j.aas.c200156
Liu Feng, Liu Hao-Zhe, Zhang Wen-Tian, Chen Jia-Shu, Shen Lin-lin, Wang Lei. A robust ROI extraction method for biometrics using adversarial structure. Acta Automatica Sinica, 2023, 49(6): 1339−1353 doi: 10.16383/j.aas.c200156
Citation: Liu Feng, Liu Hao-Zhe, Zhang Wen-Tian, Chen Jia-Shu, Shen Lin-lin, Wang Lei. A robust ROI extraction method for biometrics using adversarial structure. Acta Automatica Sinica, 2023, 49(6): 1339−1353 doi: 10.16383/j.aas.c200156

一种鲁棒的基于对抗结构的生物特征ROI提取方法

doi: 10.16383/j.aas.c200156
基金项目: 国家自然科学基金(62076163, 91959108, 61672357), 深圳市基础研究基金(JCYJ20190808163401646, JCYJ20180305125822769), 腾讯“犀牛鸟”深圳大学青年教师科学研究基金资助
详细信息
    作者简介:

    刘凤:深圳大学计算机与软件学院副教授. 2014年获得香港理工大学计算机系的计算机科学博士学位. 主要研究方向为模式识别和图像处理以及相关技术在指纹领域中的应用. 本文通信作者.E-mail: feng.liu@szu.edu.cn

    刘浩哲:深圳大学硕士研究生. 主要研究方向为计算机视觉和模式识别. E-mail: liuhaozhe2019@email.szu.edu.cn

    张文天:深圳大学硕士研究生. 主要研究方向为模式识别和生物特征识别. E-mail: zhangwentianml@gmail.com

    陈嘉树:英国纽卡斯尔大学硕士研究生. 主要研究方向为计算机视觉与生物识别. E-mail: gaasyu.chan@gmail.com

    沈琳琳:获得英国诺丁汉大学博士学位. 现为深圳市“鹏城学者” 特聘教授、英国诺丁汉大学计算机学院荣誉教授. 主要研究方向为深度学习理论及其在人脸识别/分析以及医学图像分析上的应用. E-mail: llshen@szu.edu.cn

    王磊:中国科学院深圳先进技术研究院副研究员. 主要研究方向为图像变换, 计算机视觉, 视觉语义理解, 视频分析, 深度学习. E-mail: lei.wang1@siat.ac.cn

A Robust ROI Extraction Method for Biometrics Using Adversarial Structure

Funds: Supported by National Natural Science Foundation of China (62076163, 91959108, 61672357), Shenzhen Fundamental Research Fund (JCYJ20190808163401646, JCYJ20180305125822769), and Tencent “Rhinoceros Birds” Scientific Research Foundation for Young Teachers of Shenzhen University
More Information
    Author Bio:

    LIU Feng Associate professor at the College of Computer Science and Software Engineering, Shenzhen University. She received her Ph.D. degree in computer science from the Department of Computing at Hong Kong Polytechnic University in 2014. Her research interest covers pattern recognition and image processing, and their applications to fingerprints. Corresponding author of this paper

    LIU Hao-Zhe Master student at Shenzhen University. His research interest covers computer vision and pattern recognition

    ZHANG Wen-Tian Master student at Shenzhen University. His research interest covers pattern recognition and biometrics

    CHEN Jia-Shu Master student at Newcastle University, UK. His research interest covers computer vision and biometrics

    SHEN Lin-Lin Received his Ph.D. degree from the University of Nottingham, Nottingham, UK. He is currently a Pengcheng Scholar Distinguished Professor at the College of Computer Science and Software Engineering, Shenzhen University. He is also a honorary professor at the School of Computer Science, University of Nottingham, UK. His research interest covers deep learning, facial recognition, analysis/synthesis and medical image processing

    WANG Lei Associate professor at Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences. His research interest covers image transforms, machine learning, computer vision, visual semantic understanding, video analysis, and deep learning

  • 摘要: 感兴趣区域(Region of interest, ROI) 提取在生物特征识别中, 常用于减少后续处理的计算消耗, 提高识别模型的准确性, 是生物识别系统中预处理的关键步骤. 针对生物识别数据, 提出了一种鲁棒的ROI提取方法. 方法使用语义分割模型作为基础, 通过增加全局感知模块, 与分割模型形成对抗结构, 为模型提供先验知识, 补充全局视觉模式信息, 解决了语义分割模型的末端收敛困难问题, 提高了模型的鲁棒性和泛化能力. 在传统二维(2D)指纹、人脸、三维(3D)指纹和指纹汗孔数据集中验证了方法的有效性. 实验结果表明, 相比于现有方法, 所提出的ROI提取方法更具鲁棒性和泛化能力, 精度最高.
  • 图  1  基于PASCAL VOC 2011验证集的分割结果(第1行是以马作为提取目标的案例; 第2行是以飞行器作为提取目标的案例)

    Fig.  1  Sample segmentation results on the PASCAL VOC 2011 validation set (The first row shows the ROI extraction result for horse and the second row shows the result for aircraft extraction)

    图  2  拥有不同域信息的指纹图像

    Fig.  2  Samples of 2D fingerprint images in different domains

    图  3  基于语义分割的ROI提取模型, 模型分为两部分: 基础网络和分割网络

    Fig.  3  The flowchart of ROI extraction network based on semantic segmentation

    图  4  在生物特征识别中, 基于语义分割的ROI提取模型存在的问题(第1行是人脸提取的案例分析[3536]; 第2行是指纹ROI提取的案例分析[2124])

    Fig.  4  ROI extraction issues we observe on biometrics cases (The first row shows the ROI extraction result for face[3536] and the second row presents the result for fingerprint ROI extraction[2124])

    图  5  像素级损失函数的失效情况(分割结果II是分割结果I向左平移一个像素得到, 结果显示两个分割结果的交叉熵为264.80, L2为23.00)

    Fig.  5  Failure of pixel level loss functions (Result I translates one pixel to the left to get Result II. Cross entropy between I and II is 264.80 and L2 is 23.00)

    图  6  基于对抗结构的全局损失模块的结构图

    Fig.  6  Adversarial structure based global perceptual loss module

    图  7  基于全局损失函数的ROI提取模型

    Fig.  7  Overview of our proposed ROI extraction model

    图  8  一个3D指纹的带标注横截面样例图 ((a) 标注了生物组织结构的指纹横截面图像; (b)该横截面对应的ROI区域; (c) 指尖的生物结构[39])

    Fig.  8  An example of X-Z cross-section image labeled for 3D fingerprints ((a) The cross-section image marked with biological structure; (b) The labeled image mark with the ROI; (c) Physical structure of human skin[39])

    图  9  ROI提取模型的收敛折线图(第1列的评价指标为交并比; 第2列的评价指标为像素级准确率)

    Fig.  9  The convergent plots for ROI extraction model (The evaluation metric of the first column is mean IoU, that of the second column is pixel Acc.)

    图  10  不同训练次数下的2D指纹、人脸和3D指纹ROI的提取结果(从左至右依次是不同的迭代次数的模型分割结果. 上面一行是Baseline的分割结果, 下面一行是本文方法的分割结果)

    Fig.  10  The results for 2D fingerprint, face and 3D fingerprint ROI extraction with different iteration numbers (From left to right, there are the extraction results with different iteration numbers. The upper row corresponds to the extraction results of baseline, and the lower row shows the results of the proposed method)

    图  11  人脸ROI提取和2D指纹ROI提取结果

    Fig.  11  The results for face ROI extraction and 2D fingerprint ROI extraction

    图  12  基于全局感知模块的3D指纹ROI提取结果

    Fig.  12  A set of images which show the ROI extraction result of our proposed method for 3D fingerprint

    图  13  基于全局感知模块的汗孔提取结果

    Fig.  13  The ROI extraction result of our proposed method for pore extraction

    表  1  不同设置下的全局感知模块表现

    Table  1  Investigation of global perceptual loss module with different settings

    优化策略2D传统指纹(Pixel Acc.(%)/Mean IoU)人脸(Pixel Acc.(%)/Mean IoU)3D指纹(Pixel Acc.(%)/Mean IoU)
    本文方法Baseline本文方法Baseline本文方法Baseline
    损失函数IoU loss[2]92.07/0.863290.66/0.838092.05/0.857990.03/0.825496.97/0.885995.18/0.8640
    Lovasz loss[25]92.48/0.864893.14/0.882297.21/0.947596.71/0.938895.74/0.878895.69/0.8767
    L2 loss93.33/0.861389.33/0.821996.99/0.943496.90/0.942095.70/0.885094.14/0.8331
    CrossEntropy loss (base)92.58/0.860682.71/0.718097.06/0.942996.77/0.938996.13/0.897595.43/0.8719
    优化器AMSGrad[29]93.65/0.886392.39/0.867296.50/0.935396.17/0.928993.56/0.823090.45/0.7540
    Radam[30]92.72/0.869492.27/0.866596.72/0.939096.52/0.935095.77/0.880695.19/0.8676
    Adam (base)[27]92.58/0.860682.71/0.718097.06/0.942996.77/0.938996.13/0.897595.43/0.8719
    下载: 导出CSV

    表  2  2D指纹ROI提取实验结果

    Table  2  ROI extraction results of 2D fingerprints

    方法FVCs vs. NIST 29
    pixel Acc. (%)/Mean IoU
    NIST 29 vs. FVCs
    pixel Acc. (%)/Mean IoU
    平均值(Average)
    pixel Acc. (%)/Mean IoU
    Mean and variance based method[13]76.71/0.685277.23/0.755176.97/0.7202
    Orientation based method[12]75.37/0.753274.46/0.621374.92/0.6873
    Fourier based method[13]65.45/0.634965.45/0.634965.45/0.6349
    PSPNet[17]87.74/0.800079.41/0.720983.58/0.7605
    FCN[15]87.20/0.793275.77/0.673681.49/0.7334
    U-Net[16]85.83/0.783976.46/0.725181.15/0.7545
    Baseline82.71/0.718073.12/0.734177.92/0.7261
    Baseline+Dense-CRF[48]90.33/0.783578.30/0.734784.32/0.7591
    本文方法92.58/0.860680.29/0.746986.44/0.8038
    本文方法+Dense-CRF94.67/0.885282.73/0.785288.70/0.8352
    下载: 导出CSV

    表  3  人脸提取案例实验结果

    Table  3  ROI extraction results of face images

    方法 Pixel Acc. (%) Mean IoU
    PSPNet[17] 93.62 0.8803
    FCN[15] 95.90 0.9212
    U-Net[16] 95.55 0.9147
    Baseline 96.77 0.9389
    Baseline+Dense-CRF[48] 95.77 0.9712
    本文方法 97.06 0.9429
    本文方法+Dense-CRF 96.41 0.9734
    下载: 导出CSV

    表  4  3D指纹的ROI提取结果

    Table  4  ROI extraction results of 3D fingerprint

    方法 Pixel Acc. (%) Mean IoU
    PSPNet[17] 93.67 0.8296
    FCN[15] 94.62 0.8526
    U-Net[16] 94.82 0.8614
    Baseline 95.43 0.8719
    Baseline+Dense-CRF[48] 95.50 0.8718
    本文方法 96.13 0.8975
    本文方法+Dense-CRF 96.12 0.8898
    下载: 导出CSV

    表  5  指纹汗孔提取实验结果

    Table  5  Fingerprint pore extraction results

    $ R_T$(%)$ R_F$(%)
    Gabor Filter[44]75.90 (7.5)23.00 (8.2)
    Adapt. Dog[14]80.80 (6.5)22.20 (9.0)
    DAPM[14]84.80 (4.5)17.60 (6.3)
    Xu等[45]84.80 (4.5)17.60 (6.3)
    Labati等[46]84.69 (7.81)15.31 (6.2)
    DeepPore[47]93.09 (4.63)8.64 (4.15)
    DeepPore*96.33 (6.57)6.45 (17.22)
    Baseline97.48 (9.63)7.57 (5.85)
    本文方法98.30 (9.2927)7.83 (4.18)
    下载: 导出CSV
  • [1] Caelles S, Maninis K K, Pont-Tuset J, Leal-Taixé L, Cremers D, Van Gool L. One-shot video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE, 2017. 5320−5329
    [2] Rahman A, Wang Y. Optimizing intersection-over-union in deep neural networks for image segmentation. In: Proceedings of the 12th International Symposium on Visual Computing (ISVC). Las Vegas, USA: Springer, 2016. 234−244
    [3] Wei Y C, Feng J S, Liang X D, Cheng M M, Zhao Y, Yan S C. Object region mining with adversarial erasing: A simple classification to semantic segmentation approach. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE, 2017. 6488−6496
    [4] Xu X W, Lu Q, Yang L, Hu S, Chen D, Hu Y, et al. Quantization of fully convolutional networks for accurate biomedical image segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, USA: IEEE, 2018. 8300−8308
    [5] 刘青山, 卢汉清, 马颂德. 综述人脸识别中的子空间方法. 自动化学报, 2003, 29(6): 900-911

    Liu Qing-Shan, Lu Han-Qing, Ma Song-De. A survey: Subspace analysis for face recognition. Acta Automatica Sinica, 2003, 29(6): 900-911
    [6] 高全学, 潘泉, 梁彦, 张洪才, 程咏梅. 基于描述特征的人脸识别研究. 自动化学报, 2006, 32(3): 386-392

    Gao Quan-Xue, Pan Quan, Liang Yan, Zhang Hong-Cai, Cheng Yong-Mei. Face recognition based on expressive features. Acta Automatica Sinica, 2006, 32(3): 386-392
    [7] Wang S, Zhang W W, Wang Y S. New features extraction and application in fingerprint segmentation. Acta Automatica Sinica, 2003, 29(4): 622-627
    [8] Yu C Q, Wang J B, Peng C, Gao C X, Yu G, Sang N. Learning a discriminative feature network for semantic segmentation. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Salt Lake City, USA: IEEE, 2018. 1857−1866
    [9] Hsu C Y, Yang C H, Wang H C. Multi-threshold level set model for image segmentation. EURASIP Journal on Advances in Signal Processing, 2010, 2010(1): Article No. 950438 doi: 10.1155/2010/950438
    [10] Taheri S, Ong S H, Chong V F H. Level-set segmentation of brain tumors using a threshold-based speed function. Image and Vision Computing, 2010, 28(1): 26-37 doi: 10.1016/j.imavis.2009.04.005
    [11] Xu A P, Wang L J, Feng S, Qu Y X. Threshold-based level set method of image segmentation. In: Proceedings of the 3rd International Conference on Intelligent Networks and Intelligent Systems. Shenyang, China: IEEE, 2010. 703−706
    [12] Feng J J, Zhou J, Jain A K. Orientation field estimation for latent fingerprint enhancement. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(4): 925-940 doi: 10.1109/TPAMI.2012.155
    [13] Maltoni D, Maio D, Jain A K, Prabhakar S. Handbook of Fingerprint Recognition (2nd edition). London: Springer, 2009.
    [14] Zhao Q J, Zhang D, Zhang L, Luo N. Adaptive fingerprint pore modeling and extraction. Pattern Recognition, 2010, 43(8): 2833-2844 doi: 10.1016/j.patcog.2010.02.016
    [15] Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, USA: IEEE, 2015. 3431−3440
    [16] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation. In: Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). Munich, Germany: Springer, 2015. 234−241
    [17] Zhao H S, Shi J P, Qi X J, Wang X G, Jia J Y. Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, USA: IEEE, 2017. 6230−6239
    [18] Lazebnik S, Schmid C, Ponce J. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). New York, USA: IEEE, 2006. 2169−2178
    [19] Chen L C, Zhu Y K, Papandreou G, Schroff F, Adam H. Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the 15th European Conference on Computer Vision (ECCV). Munich, Germany: Springer, 2018. 833−851
    [20] Wang P Q, Chen P F, Yuan Y, Liu D, Huang Z H, Hou X D, et al. Understanding convolution for semantic segmentation. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV). Lake Tahoe, USA: IEEE, 2018. 1451−1460
    [21] Maio D, Maltoni D, Cappelli R, Wayman J L, Jain A K. FVC2000: Fingerprint verification competition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(3): 402-412 doi: 10.1109/34.990140
    [22] Maio D, Maltoni D, Cappelli R, Wayman J L, Jain A K. FVC2002: Second fingerprint verification competition. In: Proceedings of the International Conference on Pattern Recognition. Quebec City, Canada: IEEE, 2002. 811−814
    [23] Maio D, Maltoni D, Cappelli R, Wayman J L, Jain A K. FVC2004: Third fingerprint verification competition. In: Proceedings of the 1st International Conference on Biometric Authentication (ICBA). Hong Kong, China: Springer, 2004. 1−7
    [24] Watson C I. NIST Special Database 29: Plain and Rolled Images from Paired Fingerprint Cards, Internal Report 6801, National Institute of Standards and Technology, Gaithersburg, USA, 2001
    [25] Berman M, Triki A R, Blaschko M B. The lovasz-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, USA: IEEE, 2018. 4413−4421
    [26] Tieleman T, Hinton G. Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning, 2012, 4(2): 26-31
    [27] Kingma D P, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv: 1412.6980, 2014.
    [28] Wilson A C, Roelofs R, Stern M, Srebro N, Recht B. The marginal value of adaptive gradient methods in machine learning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, USA: Curran Associates Inc., 2017. 4151−4161
    [29] Luo L C, Xiong Y H, Liu Y, Sun X. Adaptive gradient methods with dynamic bound of learning rate. In: Proceedings of the 7th International Conference on Learning Representations (ICLR). New Orleans, USA: OpenReview.net, 2019.
    [30] Liu L Y, Jiang H M, He P C, Chen W Z, Liu X D, Gao J F, et al. On the variance of the adaptive learning rate and beyond. In: Proceedings of the 8th International Conference on Learning Representations (ICLR). Addis Ababa, Ethiopia: OpenReview.net, 2020.
    [31] Goodfellow I J, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial nets. In: Proceedings of the 27th International Conference on Neural Information Processing Systems. Montreal, Canada: MIT Press, 2014. 2672−2680
    [32] Ganin Y, Lempitsky V. Unsupervised domain adaptation by backpropagation. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning. Lille, France: JMLR.org, 2015. 1180−1189
    [33] Pan S J, Yang Q. A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering, 2010, 22(10): 1345-1359 doi: 10.1109/TKDE.2009.191
    [34] He K M, Zhang X Y, Ren S Q, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE, 2016. 770−778
    [35] Kaggle. AISegment.com-Matting human datasets [Online], available: https://www.kaggle.com/laurentmih/aisegmentcom-matting-human-datasets/, March 20, 2020
    [36] Shen X Y, Tao X, Gao H Y, Zhou C, Jia J Y. Deep automatic portrait matting. In: Proceedings of the 14th European Conference on Computer Vision (ECCV). Amsterdam, the Netherlands: Springer, 2016. 92−107
    [37] Arjovsky M, Chintala S, Bottou L. Wasserstein generative adversarial networks. In: Proceedings of the 34th International Conference on Machine Learning. Sydney, NSW, Australia: PMLR, 2017. 214−223
    [38] Maas A L, Hannun A Y, Ng A Y. Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the 30th International Conference on Machine Learning (ICML). Atlanta, USA: JMLR, 2013.
    [39] Madhero88. Layers of the skin [Online], available: https://en.wikipedia.org/wiki/File:Skin_layers.png, March 20, 2020
    [40] Liu F, Shen L L, Liu H Z, Shen C X, Liu G J, Liu Y H, et al. A-benchmark-database-using-optical-coherence-tomography-for-fingerprints [Online], available: https://github.com/CV-SZU/A-Benchmark-Database-using-Optical-Coherence-Tomography-for-Fingerprints, March 20, 2020
    [41] Liu F, Shen C X, Liu H Z, Liu G J, Liu Y H, Guo Z H, et al. A flexible touch-based fingerprint acquisition device and a benchmark database using optical coherence tomography. IEEE Transactions on Instrumentation and Measurement, 2020, 69(9): 6518-6529 doi: 10.1109/TIM.2020.2967513
    [42] Liu F, Liu G J, Wang X Z. High-accurate and robust fingerprint anti-spoofing system using optical coherence tomography. Expert Systems With Applications, 2019, 130: 31-44 doi: 10.1016/j.eswa.2019.03.053
    [43] Liu H Z, Zhang W T, Liu F, Qi Y. 3D fingerprint gender classification using deep learning. In: Proceedings of the 14th Chinese Conference on Biometric Recognition (CCBR). Zhuzhou, China: Springer, 2019. 37−45
    [44] Jain A, Chen Y, Demirkus M. Pores and ridges: Fingerprint matching using level 3 features. In: Proceedings of the 18th International Conference on Pattern Recognition (ICPR). Hong Kong, China: IEEE, 2006. 477−480
    [45] Xu Y R, Lu G M, Liu F, Li Y X. Fingerprint pore extraction based on multi-scale morphology. In: Proceedings of the 12th Chinese Conference on Biometric Recognition (CCBR). Shenzhen, China: Springer, 2017. 288−295
    [46] Labati R D, Genovese A, Muñoz E, Piuri V, Scotti F. A novel pore extraction method for heterogeneous fingerprint images using Convolutional Neural Networks. Pattern Recognition Letters, 2018, 113: 58-66 doi: 10.1016/j.patrec.2017.04.001
    [47] Jang H U, Kim D, Mun S M, Choi S, Lee H K. DeepPore: Fingerprint pore extraction using deep convolutional neural networks. IEEE Signal Processing Letters, 2017, 24(12): 1808-1812 doi: 10.1109/LSP.2017.2761454
    [48] Chen L C, Papandreou G, Kokkinos I, Murphy K, Yuille A L. Semantic image segmentation with deep convolutional nets and fully connected CRFs. arXiv preprint arXiv: 1412.7062, 2014.
    [49] Chen L C, Papandreou G, Kokkinos I, Murphy K, Yuille A L. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 834-848 doi: 10.1109/TPAMI.2017.2699184
  • 加载中
图(13) / 表(5)
计量
  • 文章访问数:  1540
  • HTML全文浏览量:  390
  • PDF下载量:  174
  • 被引次数: 0
出版历程
  • 收稿日期:  2020-03-24
  • 录用日期:  2020-06-23
  • 网络出版日期:  2023-05-17
  • 刊出日期:  2023-06-20

目录

    /

    返回文章
    返回