Fast Face Sketch Synthesis via KD-Tree Search

详细信息    查看全文

• 关键词：Neighbor selection ; KD ; Tree ; Local search ; Face sketch synthesis
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9913
• 期：1
• 页码：64-77
• 全文大小：3,065 KB
• 参考文献：1.Beis, J., Lowe, D.: Shape indexing using approximate nearest-neighbour search in high-dimensional spaces. In: Conference on Computer Vision and Pattern Recognition, pp. 1000–1006 (1997)
  2.Belhumeur, P., Hespanha, J., Kriegman, D.: Eigenfaces vs. fisherfaces: recognition using class specific linear projection. IEEE Trans. Pattern Anal. Mach. Intell. 19(7), 711–720 (1997)CrossRef
  3.Bentley, J.: Multidimensional binary search trees used for associative searching. Commun. ACM 18(9), 509–517 (1975)MathSciNet CrossRef MATH
  4.Chen, H., Xu, Y., Shum, H., Zheng, N.: Example based facial sketch generation with non-parametric sampling. In: Proceedings of IEEE Conference on Computer Vision, pp. 433–438 (2010)
  5.Chen, L., Liao, H., Ko, M.: A new lda-based face recognition system which can solve the small sample size problem. Pattern Recogn. 33(10), 1713–1726 (2000)CrossRef
  6.Gao, X., Wang, N., Tao, D., Li, X.: Face sketch-photo synthesis and retrieval using sparse representation. IEEE TCSVT 22, 1213–1226 (2012)
  7.Gastal, E., Oliveira, M.: Domain transform for edge-aware image and video processing. ACM Trans. Graph. 30(4), 1244–1259 (2011)CrossRef
  8.Liu, Q., Tang, X., Jin, H., Lu, H., Ma, S.: A nonlinear approach for face sketch synthesis and recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1005–1010 (2005)
  9.Lu, C., Xu, L., Jia, J.: Combining sketch and tone for pencil drawing production. In: Eurographics Association, pp. 65–73 (2012)
  10.Martinez, A., Benavente, R.: The AR face database. Technical report 24, CVC, Barcelona, Spain, June 1998
  11.Messer, K., Matas, J., Kittler, J., Luettin, J., Maitre, G.: XM2VTSDB: the extended M2VTS database. In: Proceedings of the International Conference on Audio- and Video-Based Biometric Person Authentication, pp. 72–77, April 1999
  12.Peng, C., Gao, X., Wang, N., Li, J.: Superpixel-based face sketch-photo synthesis. IEEE TCSVT PP, 1 (2015)
  13.Peng, C., Gao, X., Wang, N., Li, J.: Graphical representation for heterogeneous face recognition. IEEE TPAMI (2016)
  14.Peng, C., Gao, X., Wang, N., Tao, D., Li, X., Li, J.: Multiple representations-based face sketch-photo synthesis. IEEE TNNLS (2015)
  15.Sheikh, H., Bovik, A.: Image information and visual quality. IEEE Trans. Image Process. 15(2), 430–444 (2006)CrossRef
  16.Song, Y., Bao, L., Yang, Q., Yang, M.: Real-time exemplar-based face sketch synthesis. In: Proceedings of Eureopean Conference on Computer Vision, pp. 800–813 (2014)
  17.Song, Y., Bao, L., Yang, Q., Yang, M.: Real-time exemplar-based face sketch synthesis (2014). http://​www.​cs.​cityu.​edu.​hk/​yibisong/​eccv14/​index.​html . Accessed 19 June 2016
  18.Tang, X., Wang, X.: Face sketch synthesis and recognition. In: IEEE International Conference on Computer Vision, p. 687 (2003)
  19.Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of Computer Vision and Pattern Recognition, p. 511 (2001)
  20.Wang, N., Li, J., Tao, D., Li, X., Gao, X.: Heterogeneous image transformation. Pattern Recogn. Lett. 34(1), 77–84 (2013)CrossRef
  21.Wang, N., Tao, D., Gao, X., Li, X., Li, J.: Transductive face sketch-photo synthesis. IEEE TNNLS 24(9), 1364–1376 (2013)
  22.Wang, N., Tao, D., Gao, X., Li, X., Li, J.: A comprehensive survey to face hallucination. IJCV 31(1), 9–30 (2014)CrossRef
  23.Wang, X., Tang, X.: Face photo-sketch synthesis and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 31(11), 1955–1967 (2009)CrossRef
  24.Wang, X., Tang, X.: Style and abstraction in portrait sketching. ACM Trans. Graph. 32(4), 96–96 (2013)CrossRef
  25.Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)CrossRef
  26.Wikipedia: k-d tree (2016). https://​en.​wikipedia.​org/​wiki/​K-d_​tree . Accessed 19 June 2016
  27.Xu, Z., Chen, H., Zhu, S., Luo, J.: A hierarchical compositional model for face representation and sketching. IEEE Trans. Pattern Anal. Mach. Intell. 30(6), 955–969 (2008)CrossRef
  28.Zhou, H., Kuang, Z., Wong, K.: Markov weight fields for face sketch synthesis. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1091–1097 (2012)
  
• 作者单位：Yuqian Zhang (15)
  Nannan Wang (15)
  Shengchuan Zhang (15)
  Jie Li (15)
  Xinbo Gao (15)
  
  15. State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China
  
• 丛书名：Computer Vision – ECCV 2016 Workshops
• ISBN：978-3-319-46604-0
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9913

文摘

Automatic face sketch synthesis has been widely applied in digital entertainment and law enforcement. Currently, most sketch synthesis algorithms focus on generating face portrait of good quality, but ignoring the time consumption. Existing methods have large time complexity due to dense computation of patch matching in the neighbor selection process. In this paper, we propose a simple yet effective fast face sketch synthesis method based on K dimensional-Tree (KD-Tree). The proposed method employs the idea of divide-and-conquer (i.e. piece-wise linear) to learn the complex nonlinear mapping between facial photos and sketches. In the training phase, all the training images are divided into regions and every region is divided into some small patches, then KD-Tree is built up among training photo patches in each region. In the test phase, the test photo is first divided into some patches as the same way in the training phase. KD-Tree search is conducted for K nearest neighbor selection by matching the test photo patches in each region against the constructed KD-Tree of training photo patches in the same region. The KD-Tree process builds index structure which greatly reduces the time consumption for neighbor selection. Compared with synthesis methods using classical greedy search strategy (i.e. KNN), the proposed method is much less time consuming but with comparable synthesis performance. Experiments on the public CUHK face sketch (CUFS) database illustrate the effectiveness of the proposed method. In addition, the proposed neighbor selection strategy can be further extended to other synthesis algorithms.