Face Sketch Synthesis From a Single Photo-Sketch Pair

被引:17
|
作者
Zhang, Shengchuan [1 ]
Gao, Xinbo [2 ]
Wang, Nannan [3 ]
Li, Jie [1 ]
机构
[1] Xidian Univ, Sch Elect Engn, Video & Image Proc Syst Lab, Xian 710071, Peoples R China
[2] Xidian Univ, Sch Elect Engn, State Key Lab Integrated Serv Networks, Xian 710071, Peoples R China
[3] Xidian Univ, Sch Telecommun Engn, State Key Lab Integrated Serv Networks, Xian 710071, Peoples R China
基金
中国国家自然科学基金;
关键词
Bayesian inference (BI); cascaded regression; face sketch synthesis; sparse coding; ALGORITHM;
D O I
10.1109/TCSVT.2015.2511482
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Face sketch synthesis is crucial in many practical applications, such as digital entertainment and law enforcement. Previous methods relying on many photo-sketch pairs have made great progress. State-of-the-art face sketch synthesis algorithms adopt Bayesian inference (BI) (e.g., Markov random fields) to select local sketch patches around corresponding position from a set of training data. However, these methods have two limitations: 1) they depend on many training photo-sketch pairs and 2) they cannot tackle nonfacial factors (e.g., hairpins, glasses, backgrounds, and image size) if these factors are excluded in training data. In this paper, we propose a novel face sketch synthesis method that is capable of handling nonfacial factors only using a single photo-sketch pair from coarse to fine. Our method proposes a cascaded image synthesis (CIS) strategy and integrates sparse representation-based greedy search (SRGS) and BI for face sketch synthesis. We first apply SRGS to select candidate sketch patches from the whole training photo-sketch pairs sampled from the only photo-sketch pair. We then employ BI to estimate an initial sketch. Afterward, the input photo and the estimated initial sketch are taken as an additional photosketch pair for training. Finally, we adopt CIS with the given two photo-sketch pairs to further improve the quality of the initial sketch. The experimental results on several databases demonstrate that our algorithm outperforms state-of-the-art methods.
引用
收藏
页码:275 / 287
页数:13
相关论文
共 50 条
  • [21] Smoothness-Constrained Face Photo-Sketch Synthesis Using Sparse Representation
    Chang, Liang
    Deng, Xiaoming
    Zhou, Mingquan
    Duan, Fuqing
    Wu, Zhongke
    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 3025 - 3029
  • [22] Feature Encoder Guided Generative Adversarial Network for Face Photo-Sketch Synthesis
    Zheng, Jieying
    Song, Wanru
    Wu, Yahong
    Xu, Ran
    Liu, Feng
    IEEE ACCESS, 2019, 7 : 154971 - 154985
  • [23] Face photo-sketch portraits transformation via generation pipeline
    Guo, Mengsi
    Xiong, Mingfu
    Huang, Jin
    Hu, Xinrong
    Peng, Tao
    VISUAL COMPUTER, 2025, 41 (02): : 1183 - 1196
  • [24] Face Photo-Sketch Recognition Based on Joint Dictionary Learning
    Liu, Jixuan
    Bae, Seho
    Park, Hanjae
    Li, Lei
    Yoon, Seongbeak
    Yi, Juneho
    2015 14TH IAPR INTERNATIONAL CONFERENCE ON MACHINE VISION APPLICATIONS (MVA), 2015, : 77 - 80
  • [25] Photo-sketch synthesis and recognition based on subspace learning
    Xiao, Bing
    Gao, Xinbo
    Tao, Dacheng
    Yuan, Yuan
    Li, Jie
    NEUROCOMPUTING, 2010, 73 (4-6) : 840 - 852
  • [26] Coupled Information-Theoretic Encoding for Face Photo-Sketch Recognition
    Zhang, Wei
    Wang, Xiaogang
    Tang, Xiaoou
    2011 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2011, : 513 - 520
  • [27] Anchored Neighborhoods Search Based on Global Dictionary Atoms for Face Photo-Sketch Synthesis
    Liu, Feng
    Xu, Ran
    Zheng, Jieying
    Lin, Qiuli
    Gan, Zongliang
    ELEVENTH INTERNATIONAL CONFERENCE ON DIGITAL IMAGE PROCESSING (ICDIP 2019), 2019, 11179
  • [28] IsGAN: Identity-sensitive generative adversarial network for face photo-sketch synthesis
    Yan, Lan
    Zheng, Wenbo
    Gou, Chao
    Wang, Fei-Yue
    PATTERN RECOGNITION, 2021, 119
  • [29] Toward Realistic Face Photo-Sketch Synthesis via Composition-Aided GANs
    Yu, Jun
    Xu, Xingxin
    Gao, Fei
    Shi, Shengjie
    Wang, Meng
    Tao, Dacheng
    Huang, Qingming
    IEEE TRANSACTIONS ON CYBERNETICS, 2021, 51 (09) : 4350 - 4362
  • [30] Face Photo-Sketch Recognition using Local and Global Texture Descriptors
    Galea, Christian
    Farrugia, Reuben A.
    2016 24TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2016, : 2240 - 2244