簡易檢索 / 詳目顯示

回結果列表
研究生： 陳鼎介
Chen, Ding-Jie
論文名稱： 自動導引之互動式分割
Automatic Guided Interactive Segmentation
指導教授： 陳煥宗
Chen, Hwann-Tzong
張隆紋
Chang, Long-Wen
口試委員: 劉庭祿
Liu, Tyng-Luh
賴尚宏
Lai, Shang-Hong
王聖智
Wang, Sheng-Jyh
陳朝欽
Chen, Chaur-Chin
杭學鳴
Hang, Hsueh-Ming
學位類別： 博士
Doctor
系所名稱：
論文出版年： 2018
畢業學年度： 106
語文別： 英文
論文頁數： 106
中文關鍵詞： 互動式影像分割 、單位元使用者反饋 、種子提案法 、自動編碼器
外文關鍵詞： interactive image segmentation, 1-bit user feedback, seed proposals, auto-encoder
相關次數： 點閱：3  下載：0 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 從影像中分割出使用者感興趣的區域是電腦視覺領域中一個基本且具挑戰性之研究課題。分割出使用者感興趣的影像區域尤其難在當影像包含多個物件或是含有雜亂背景之情形。因此，衍生出的一個稱作互動式分割之子題目，亦即有人類使用者參與之循環影像分割，後來被提出來利用使用者提供之資訊來協助推估何謂使用者感興趣的區域，藉以求得準確的分割結果。然而大多數的互動式分割演算法僅完全仰賴使用者自身來提供準確的標示資訊來引導其演算法做分割，使得分割品質高度相關於使用者所提供的標示資訊。此篇論文旨在提出三個高效率之互動式影像分割演算法，讓非專業的使用者亦可藉由演算法的輔助來取得高品質之影像分割結果。

    我們開發三個演算法來處理互動式影像分割的問題。第一個演算法旨在增強基於單位元使用者反饋之互動式分割的效率與效能，該演算法特徵是將標示位置的責任從使用者轉嫁到演算法上。再來我們介紹利用種子提案法來設計介面，用以處理因在小型觸控式螢幕上難以提供精確標示所衍生的互動式分割問題。最後我們展示一個利用拍照時隱含的攝影資訊做分割之新穎演算法，該演算法植基於學習方式來利用所抽取之影像資訊實現互動式分割。

    我們演算法的性能評估於數個公開可用的數據集上。評估結果表明我們的演算法實現了高分割精度、短響應時間、與更少使用者反饋數。因此，所開發演算法可提供更好之處理方案於互動式影像分割問題是顯而易見的。

    One of the fundamental challenges in the field of computer vision is segmenting what the user-preferred region of interests (ROIs) of a given image. Segmenting the ROIs for an image is not a trivial task, especially for images that contain multiple objects and cluttered backgrounds. Interactive image segmentation, or image segmentation with a human in the loop, can make the region of interest (ROI) more clearly defined for obtaining accurate segmentation. However, most of the existing interactive image segmentation algorithms rely on the user to provide accurate annotations as the guidance, and the segmentation results usually greatly depend on the qualities of the user-provided annotations. This thesis aims to introduce three efficient algorithms to make the non-expert users can obtain high-quality image segmentations with machine assistance.

    We develop three efficient algorithms to address the problem of interactive image segmentation. The first algorithm aims to improve the effectiveness and efficiency of interactive 1-bit user feedback image segmentation. The most interesting property is that the responsibility to define the annotation locations is transferred from the user to the machine. Then, we introduce a seed proposals approach in an interface manner for addressing the interactive segmentation task on a small touchscreen device. The interface aims to address the problem that the precise annotations are difficult to provide while annotating on the small display device. Finally, we present a new segmentation algorithm that leverages the latent photographic information available at the moment of taking pictures. A learning-based segmentation approach is proposed to collect available cues while taking pictures for carrying out the interactive segmentation in a common tap-and-shoot photographing process.

    The performances of our algorithms are evaluated on several publicly available datasets. The evaluation results show that our algorithms achieve high segmentation accuracy, with short response time and fewer user feedback. The evidence that our algorithms can provide the superior solutions to the interactive image segmentation problem is clear.

    摘 要 i Abstract ii 誌 謝 iv List of Tables viii List of Figures ix 1 Introduction 1 1.1 Interactive Segmentation . . . . . . . . . . . . . . . . . 1 1.2 Interaction with 1-bit User Feedback . . . . . . . . . . . 2 1.3 Interaction with Seed Proposals . . . . . . . . . . . . . .3 1.4 Interaction in Tap-and-Shoot Scenario . . . . . . . . . . .5 1.5 Organization and Contribution of the Thesis . . . . . . . .5 2 Related Work 8 2.1 Passive Interactive Image Segmentation . . . . . . . . . . 8 2.2 Active Interactive Image Segmentation . . . . . . . . . . 9 2.3 Proposal Generation . . . . . . . . . . . . . . . . . . . 10 2.4 Defocus Blur Estimation . . . . . . . . . . . . . . . . . 10 2.5 Deep Network Architectures for Semantic Segmentation . . 11 3 Interactive Segmentation with 1-Bit User Feedback 13 3.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . 15 3.1.1 Usage . . . . . . . . . . . . . . . . . . . . . . . . . 15 3.1.2 Twenty Questions Game . . . . . . . . . . . . . . . . . 16 3.1.3 Similar Works . . . . . . . . . . . . . . . . . . . . . 16 3.2 Approach . . . . . . . . . . . . . . . . . . . . . . . . .18 3.2.1 Preprocessing . . . . . . . . . . . . . . . . . . . . . 18 3.2.2 Interaction . . . . . . . . . . . . . . . . . . . . . . 22 3.2.3 Postprocessing . . . . . . . . . . . . . . . . . . . . .26 3.3 Experiments . . . . . . . . . . . . . . . . . . . . . . . 29 3.3.1 Effects of Different Parameter Settings . . . . . . . . 30 3.3.2 Comparisons on Segmentation Regions . . . . . . . . . . 31 3.3.3 Comparisons on Boundary Refinement . . . . . . . . . . .38 3.4 Summary . . . . . . . . . . . . . . . . . . . . . . . . . 44 4 Interactive Segmentation with Seed Proposals 45 4.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . .47 4.1.1 Segmenting on Small Touchscreen Devices . . . . . . . . 47 4.1.2 Similar Works . . . . . . . . . . . . . . . . . . . . . 49 4.2 Problem Statement . . . . . . . . . . . . . . . . . . . . 49 4.2.1 Interactive Image Segmentation . . . . . . . . . . . . .50 4.2.2 Diversified Seed Proposals . . . . . . . . . . . . . . .51 4.3 Approach . . . . . . . . . . . . . . . . . . . . . . . . .52 4.3.1 Query-seed Proposal Scheme . . . . . . . . . . . . . . .52 4.3.2 Label Propagation Scheme . . . . . . . . . . . . . . . .55 4.3.3 Implementation Details . . . . . . . . . . . . . . . . .55 4.4 Experiments . . . . . . . . . . . . . . . . . . . . . . . 58 4.4.1 Effects of Different Parameter Settings . . . . . . . . 60 4.4.2 One Query Seed Per Interaction . . . . . . . . . . . . .60 4.4.3 Multiple Query Seeds Per Interaction . . . . . . . . . .65 4.4.4 Evaluating the User Interactions . . . . . . . . . . . .68 4.4.5 Segmentation Examples . . . . . . . . . . . . . . . . . 69 4.5 Summary . . . . . . . . . . . . . . . . . . . . . . . . . 74 5 Interactive Segmentation in Tap-and-Shoot Scenario 75 5.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . .77 5.1.1 Tab-and-Shoot Scenario . . . . . . . . . . . . . . . . .77 5.1.2 Similar Work . . . . . . . . . . . . . . . . . . . . . .78 5.2 Approach . . . . . . . . . . . . . . . . . . . . . . . . .78 5.2.1 Network Architecture . . . . . . . . . . . . . . . . . .80 5.2.2 Implementation Details . . . . . . . . . . . . . . . . .80 5.3 Experiments . . . . . . . . . . . . . . . . . . . . . . . 83 5.3.1 Quantitative Results . . . . . . . . . . . . . . . . . .84 5.3.2 Qualitative Results . . . . . . . . . . . . . . . . . . 86 5.4 Discussions . . . . . . . . . . . . . . . . . . . . . . . 88 5.4.1 Network Comparison . . . . . . . . . . . . . . . . . . .88 5.4.2 Defocus Blur Learning . . . . . . . . . . . . . . . . . 89 5.5 Summary . . . . . . . . . . . . . . . . . . . . . . . . . 91 6 Conclusions 92 A Prior Publications 94

    [1] 20q.net. http://www.20q.net/.
    [2] Radhakrishna Achanta, Sheila S. Hemami, Francisco J. Estrada, and Sabine Süsstrunk. Frequency-tuned salient region detection. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 1597–1604, 2009.
    [3] Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurélien Lucchi, Pascal Fua, and Sabine Süsstrunk. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell., 34(11):2274–2282, 2012.
    [4] Rolf Adams and Leanne Bischof. Seeded region growing. IEEE Trans. Pattern Anal. Mach. Intell., 16(6):641–647, 1994.
    [5] Pablo Arbelaez, Michael Maire, Charless C. Fowlkes, and Jitendra Malik. Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 33(5):898–916, 2011.
    [6] Pablo Andrés Arbeláez, Jordi Pont-Tuset, Jonathan T. Barron, Ferran Marqués, and Jitendra Malik. Multiscale combinatorial grouping. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 328–335, 2014.
    [7] Anais Badoual, Daniel Schmitter, Virginie Uhlmann, and Michael Unser. Multiresolution subdivision snakes. IEEE Trans. Image Processing, 26(3):1188–1201, 2017.
    [8] Junjie Bai and Xiaodong Wu. Error-tolerant scribbles based interactive image segmentation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 392–399, 2014.
    [9] Dhruv Batra, Adarsh Kowdle, Devi Parikh, Jiebo Luo, and Tsuhan Chen. icoseg: Interactive co-segmentation with intelligent scribble guidance. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 3169–3176, 2010.
    [10] Amy L. Bearman, Olga Russakovsky, Vittorio Ferrari, and Fei-Fei Li. What’s the point: Semantic segmentation with point supervision. In Proc. European Conference on Computer Vision, pages 549–565, 2016.
    [11] Yuri Boykov and Marie-Pierre Jolly. Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In Proc. IEEE International Conference on Computer Vision, pages 105–112, 2001.
    [12] Steve Branson, Catherine Wah, Florian Schroff, Boris Babenko, Peter Welinder, Pietro Perona, and Serge J. Belongie. Visual recognition with humans in the loop. In Proc. European Conference on Computer Vision, pages 438–451, 2010.
    [13] Jaime G. Carbonell and Jade Goldstein. The use of mmr, diversity-based reranking for reordering documents and producing summaries. In Proc. International Conference on Research and Development in Information Retrieval, pages 335–336, 1998.
    [14] João Carreira and Cristian Sminchisescu. Constrained parametric min-cuts for automatic object segmentation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 3241–3248, 2010.
    [15] Olivier Chapelle, Jason Weston, and Bernhard Schölkopf. Cluster kernels for semi-supervised learning. In Proc. Neural Information Processing Systems, pages 585–592, 2002.
    [16] Ding-Jie Chen, Hwann-Tzong Chen, and Long-Wen Chang. Video object cosegmentation. In Proc. ACM Multimedia Conference, pages 805–808, 2012.
    [17] Ding-Jie Chen, Hwann-Tzong Chen, and Long-Wen Chang. Interactive segmentation from 1-bit feedback. In Proc. Asian Conference on Computer Vision, pages 261–274, 2016.
    [18] Ding-Jie Chen, Hwann-Tzong Chen, and Long-Wen Chang. Video object segmentation via cellular automata refinement. In Proc. IAPR Asian Conference on Pattern Recognition, 2017. to appear.
    [19] Ding-Jie Chen, Hwann-Tzong Chen, and Long-Wen Chang. Video segmentation via boundary-aware flow. In Proc. IEEE International Conference on Image Processing, 2017. to appear.
    [20] Ding-Jie Chen, Chi-Yun Liu, and Long-Wen Chang. Matching based image co-segmentation. In Proc. IEEE International Conference on Information Science, Electronics and Electrical Engineering, pages 818–822, 2014.
    [21] Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L. Yuille. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. CoRR, abs/1606.00915, 2016.
    [22] Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. Rethinking atrous convolution for semantic image segmentation. CoRR, abs/1706.05587, 2017.
    [23] Ming-Ming Cheng, Niloy J. Mitra, Xiaolei Huang, Philip H. S. Torr, and Shi-Min Hu. Global contrast based salient region detection. IEEE Trans. Pattern Anal. Mach. Intell., 37(3):569–582, 2015.
    [24] Ming-Ming Cheng, Victor Adrian Prisacariu, Shuai Zheng, Philip H. S. Torr, and Carsten Rother. Densecut: Densely connected crfs for realtime grabcut. Comput. Graph. Forum, 34(7):193–201, 2015.
    [25] Jui-Ting Chien, Chia-Jung Chou, Ding-Jie Chen, and Hwann-Tzong Chen. Detecting nonexistent pedestrians. In Proc. IEEE International Conference on Computer Vision Workshops, pages 182–189, 2017.
    [26] Xingping Dong, Jianbing Shen, Ling Shao, and Ming-Hsuan Yang. Interactive cosegmentation using global and local energy optimization. IEEE Trans. Image Processing, 24(11):3966–3977, 2015.
    [27] Florian Dubost, Loïc Peter, Christian Rupprecht, Benjamín Gutiérrez-Becker, and Nassir Navab. Hands-free segmentation of medical volumes via binary inputs. In Proc. Deep Learning and Data Labeling for Medical Applications, pages 259–268, 2016.
    [28] James H. Elder and Steven W. Zucker. Local scale control for edge detection and blur estimation. IEEE Trans. Pattern Anal. Mach. Intell., 20(7):699–716, 1998.
    [29] M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. The PASCAL Visual Object Classes Challenge 2007 Results. http://www.pascal-network.org/challenges/VOC/voc2007/workshop/index.html.
    [30] Alireza Fathi, Maria-Florina Balcan, Xiaofeng Ren, and James M. Rehg. Combining self training and active learning for video segmentation. In Proc. British Machine Vision Conference, pages 1–11, 2011.
    [31] Pedro F. Felzenszwalb and Daniel P. Huttenlocher. Efficient graph-based image segmentation. International Journal of Computer Vision, 59(2):167–181, 2004.
    [32] Jie Feng, Brian Price, Scott Cohen, and Shih-Fu Chang. Interactive segmentation on rgbd images via cue selection. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 156–164, 2016.
    [33] Charless C. Fowlkes, David R. Martin, and Jitendra Malik. Local figure-ground cues are valid for natural images. Journal of Vision, 7(8):1–9, 2007.
    [34] Stephen Gould, Richard Fulton, and Daphne Koller. Decomposing a scene into geometric and semantically consistent regions. In Proc. IEEE International Conference on Computer Vision, pages 1–8, 2009.
    [35] Leo Grady. Random walks for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell., 28(11):1768–1783, 2006.
    [36] Matthias Grundmann, Vivek Kwatra, Mei Han, and Irfan A. Essa. Efficient hierarchical graph-based video segmentation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 2141–2148, 2010.
    [37] Varun Gulshan, Carsten Rother, Antonio Criminisi, Andrew Blake, and Andrew Zisserman. Geodesic star convexity for interactive image segmentation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 3129–3136, 2010.
    [38] Kaiming He, Jian Sun, and Xiaoou Tang. Guided image filtering. IEEE Trans. Pattern Anal. Mach. Intell., 35(6):1397–1409, 2013.
    [39] Gao Huang, Zhuang Liu, Laurens van der Maaten, and Kilian Q. Weinberger. Densely connected convolutional networks. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 2261–2269, 2017.
    [40] Simon Jégou, Michal Drozdzal, David Vázquez, Adriana Romero, and Yoshua Bengio. The one hundred layers tiramisu: Fully convolutional densenets for semantic segmentation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 1175–1183, 2017.
    [41] Michael Kass, Andrew P. Witkin, and Demetri Terzopoulos. Snakes: Active contour models. International Journal of Computer Vision, 1(4):321–331, 1988.
    [42] Adarsh Kowdle, Yao-Jen Chang, Andrew C. Gallagher, and Tsuhan Chen. Active learning for piecewise planar 3d reconstruction. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 929–936, 2011.
    [43] Philipp Krähenbühl and Vladlen Koltun. Geodesic object proposals. In Proc. European Conference on Computer Vision, pages 725–739, 2014.
    [44] Daniel Küttel and Vittorio Ferrari. Figure-ground segmentation by transferring window masks. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 558–565, 2012.
    [45] Hongdong Li and Chunhua Shen. Interactive color image segmentation with linear programming. Mach. Vis. Appl., 21(4):403–412, 2010.
    [46] Yin Li, Jian Sun, Chi-Keung Tang, and Heung-Yeung Shum. Lazy snapping. ACM Trans. Graph., 23(3):303–308, 2004.
    [47] Bo-Chen Lin, Ding-Jie Chen, and Long-Wen Chang. Unsupervised image co-segmentation based on cooperative game. In Proc. Asian Conference on Computer Vision, pages 51–63, 2014.
    [48] Tie Liu, Jian Sun, Nanning Zheng, Xiaoou Tang, and Heung-Yeung Shum. Learning to detect A salient object. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2007.
    [49] Jonathan Long, Evan Shelhamer, and Trevor Darrell. Fully convolutional networks for semantic segmentation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 3431–3440, 2015.
    [50] Santiago Manen, Matthieu Guillaumin, and Luc J. Van Gool. Prime object proposals with randomized prim’s algorithm. In Proc. IEEE International Conference on Computer Vision, pages 2536–2543, 2013.
    [51] David R. Martin, Charless C. Fowlkes, Doron Tal, and Jitendra Malik. A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics. In Proc. IEEE International Conference on Computer Vision, pages 416–425, 2001.
    [52] Kevin McGuinness and Noel E. O’Connor. A comparative evaluation of interactive segmentation algorithms. Pattern Recognition, 43(2):434–444, 2010.
    [53] Eric N. Mortensen and William A. Barrett. Intelligent scissors for image composition. In Proc. Annual Conference on Computer Graphics and Interactive Techniques, pages 191–198, 1995.
    [54] Yan-Tsung Peng, Xiangyun Zhao, and Pamela C. Cosman. Single underwater image enhancement using depth estimation based on blurriness. In Proc. IEEE International Conference on Image Processing, pages 4952–4956, 2015.
    [55] Olaf Ronneberger, Philipp Fischer, and Thomas Brox. U-net: Convolutional networks for biomedical image segmentation. In Proc. Medical Image Computing and Computer-Assisted Intervention, pages 234–241, 2015.
    [56] Carsten Rother, Vladimir Kolmogorov, and Andrew Blake. ”grabcut”: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph., 23(3):309–314, 2004.
    [57] Carsten Rother, Thomas P. Minka, Andrew Blake, and Vladimir Kolmogorov. Cosegmentation of image pairs by histogram matching - incorporating a global constraint into mrfs. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 993–1000, 2006.
    [58] Christian Rupprecht, Loïc Peter, and Nassir Navab. Image segmentation in twenty questions. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 3314–3322, 2015.
    [59] Jianping Shi, Li Xu, and Jiaya Jia. Just noticeable defocus blur detection and estimation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 657–665, 2015.
    [60] Jianping Shi, Qiong Yan, Li Xu, and Jiaya Jia. Hierarchical image saliency detection on extended CSSD. IEEE Trans. Pattern Anal. Mach. Intell., 38(4):717–729, 2016.
    [61] Thorvald Søensen. A method of establishing groups of equal amplitude in plant sociology based on similarity of species and its application to analyses of the vegetation on danish commons. Kongelige Danske Videnskabernes Selskab, 5(4):1–34, 1948.
    [62] Andrew N. Stein, Thomas S. Stepleton, and Martial Hebert. Towards unsupervised whole-object segmentation: Combining automated matting with boundary detection. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2008.
    [63] Christoph N. Straehle, Ullrich Köthe, Graham Knott, Kevin L. Briggman, Winfried Denk, and Fred A. Hamprecht. Seeded watershed cut uncertainty estimators for guided interactive segmentation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 765–772, 2012.
    [64] Kartic Subr, Sylvain Paris, Cyril Soler, and Jan Kautz. Accurate binary image selection from inaccurate user input. Comput. Graph. Forum, 32(2):41–50, 2013.
    [65] Meng Tang, Lena Gorelick, Olga Veksler, and Yuri Boykov. Grabcut in one cut. In Proc. IEEE International Conference on Computer Vision, pages 1769–1776, 2013.
    [66] Jasper R. R. Uijlings, Koen E. A. van de Sande, Theo Gevers, and Arnold W. M. Smeulders. Selective search for object recognition. International Journal of Computer Vision, 104(2):154–171, 2013.
    [67] Vladimir Vezhnevets and Vadim Konushin. ”growcut” - interactive multi-label n-d image segmentation by cellular automata. In Proc. Conference and School-Seminar on Computer Graphics and Vision, 2005.
    [68] Sara Vicente, Carsten Rother, and Vladimir Kolmogorov. Object cosegmentation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 2217–2224, 2011.
    [69] Jarrell W. Waggoner, Youjie Zhou, Jeff P. Simmons, Marc De Graef, and Song Wang. Graph-cut based interactive segmentation of 3d materials-science images. Mach. Vis. Appl., 25(6):1615–1629.
    [70] Catherine Wah, Steve Branson, Pietro Perona, and Serge J. Belongie. Multiclass recognition and part localization with humans in the loop. In Proc. IEEE International Conference on Computer Vision, pages 2524–2531, 2011.
    [71] Chaoyang Wang, Long Zhao, Shuang Liang, Liqing Zhang, Jinyuan Jia, and Yichen Wei. Object proposal by multi-branch hierarchical segmentation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 3873–3881, 2015.
    [72] Qi Wang, Junyu Gao, and Yuan Yuan. A joint convolutional neural networks and context transfer for street scenes labeling. IEEE Trans. Intelligent Transportation Systems. [Online]. Available: http://ieeexplore.ieee.org/document/8012463/.
    [73] Qi Wang, Junyu Gao, and Yuan Yuan. Embedding structured contour and location prior in siamesed fully convolutional networks for road detection. IEEE Trans. Intelligent Transportation Systems, 19(1):230–241, 2018.
    [74] Tinghuai Wang, Bo Han, and John P. Collomosse. Touchcut: Fast image and video segmentation using single-touch interaction. Computer Vision and Image Understanding, 120:14–30, 2014.
    [75] Wenguan Wang, Jianbing Shen, and Fatih Porikli. Saliency-aware geodesic video object segmentation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 3395–3402, 2015.
    [76] Yichen Wei, Fang Wen, Wangjiang Zhu, and Jian Sun. Geodesic saliency using background priors. In Proc. European Conference on Computer Vision, pages 29–42, 2012.
    [77] Jiajun Wu, Yibiao Zhao, Jun-Yan Zhu, Siwei Luo, and Zhuowen Tu. Milcut: A sweeping line multiple instance learning paradigm for interactive image segmentation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 256–263, 2014., 2014.
    [78] Min Xian, Yingtao Zhang, Heng-Da Cheng, Fei Xu, and Jianrui Ding. Neutro-connectedness cut. IEEE Trans. Image Processing, 25(10):4691–4703, 2016.
    [79] Yao Xiao, Cewu Lu, Efstratios Tsougenis, Yongyi Lu, and Chi-Keung Tang. Complexity-adaptive distance metric for object proposals generation. In IEEE Conference on Computer Vision and Pattern Recognition, pages 778–786, 2015.
    [80] Chenliang Xu, Spencer Whitt, and Jason J. Corso. Flattening supervoxel hierarchies by the uniform entropy slice. In Proc. IEEE International Conference on Computer Vision, pages 2240–2247, 2013.
    [81] Jia Xu, Maxwell D. Collins, and Vikas Singh. Incorporating user interaction and topological constraints within contour completion via discrete calculus. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 1886–1893, 2013.
    [82] Ning Xu, Brian L. Price, Scott Cohen, Jimei Yang, and Thomas S. Huang. Deep interactive object selection. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 373–381, 2016.
    [83] Chenggang Yan, Hongtao Xie, Shun Liu, Jian Yin, Yongdong Zhang, and Qiong-hai Dai. Effective uyghur language text detection in complex background images for traffic prompt identification. IEEE Trans. Intelligent Transportation Systems, 19(1):220–229, 2018.
    [84] Fisher Yu and Vladlen Koltun. Multi-scale context aggregation by dilated convolutions. In Proc. International Conference on Learning Representations, 2016.
    [85] Ling Zhang, Xinguang Peng, Gang Li, and Haifang Li. A novel active contour model for image segmentation using local and global region-based information. Mach. Vis. Appl., 28(1-2):75–89, 2017.
    [86] Yi Zhang and Keigo Hirakawa. Blur processing using double discrete wavelet transform. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 1091–1098, 2013.
    [87] Hengshuang Zhao, Jianping Shi, Xiaojuan Qi, Xiaogang Wang, and Jiaya Jia. Pyramid scene parsing network. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, pages 6230–6239, 2017.
    [88] Dengyong Zhou, Olivier Bousquet, Thomas Navin Lal, Jason Weston, and Bern-hard Schölkopf. Learning with local and global consistency. In Proc. Neural Information Processing Systems, pages 321–328, 2003.
    [89] Xiang Zhu, Scott Cohen, Stephen Schiller, and Peyman Milanfar. Estimating spatially varying defocus blur from A single image. IEEE Trans. Image Processing, 22(12):4879–4891, 2013.
    [90] Shaojie Zhuo and Terence Sim. Defocus map estimation from a single image. Pattern Recognition, 44(9):1852–1858, 2011.

    QR CODE