Face Image Generation


Example-based caricature synthesis techniques have been attracting large attentions for being able to generate attractive caricatures of various styles. This research proposes a new example-based caricature synthesis system using a feature deviation matching method as a cross-modal distance metric. It employs the deviation values from average features across different feature spaces rather than the values of features themselves to search for similar components from caricature examples directly. Compared with traditional example-based systems, the proposed system can generate various styles of caricatures without requiring paired photograph–caricature example databases. The newly designed features can effectively capture visual characteristics of the hairstyles and facial components in input portrait images. In addition, this system can control the exaggeration of individual facial components and provide several similarity-based candidates to satisfy users’ different preferences. Experiments are conducted to prove the above ideas.

Face image synthesis has potential applications in public safety, such as video surveillance and law enforcement. For example, creating a portrait of a suspect from an eyewitness can greatly help the police identify criminals. Also, a similar technique can be used for giving concrete form to imagined ideas of romantic ‘types’ and translate other imagined faces into explicit images. However, drawing an image based on descriptions of what is in one’s mind is not an easy task for the majority of people. In this research, we propose a user-friendly system that can create a facial image from a corresponding image in the user’s mind.


  1. Yixuan Ju, Jianhai Zhang, Xiaoyang Mao, Jiayi Xu, “Adaptive semantic attribute decoupling for precise face image editing,” The Visual Computer, Springer, Vol.37, pp.2907-2918, 2021-7.
  2. Jiayi Xu, Xinying Xue, Yitiao Wu, and Xiaoyang Mao, “Matching a composite sketch to a photographed face using fused HOG and deep feature models,” The Visual Computer, 2020-9.
  3. Caie Xu, Ying Tang, Masahiro Toyoura, Jiayi Xu, Xiaoyang Mao, “Generating Users’ Desired Face Image Using the Conditional Generative Adversarial Network and Relevance Feedback,” IEEE Access, 2019-11.
  4. Honglin Li, Masahiro Toyoura, Xiaoyang Mao, “Caricature Synthesis with Feature Deviation Matching under Example-Based Framework,” The Visual Computer, Vol.35, No.5, pp.653-666, 2019-3.
  5. Caie Xu, Shota Fushimi, Masahiro Toyoura, Jiayi Xu, Xiaoyang Mao, “Synthesizing Imagined Faces Based on Relevance Feedback,” Transactions on Computational Science, Vol.32, pp.90-105, 2018-3.
  6. Caie Xu, Shota Fushimi, Masahiro Toyoura, Jiayi Xu, Honglin Li, Xiaoyang Mao, “Synthesis of Facial Images Based on Relevance Feedback,” Cyberworlds, pp.1-4, 2017-9.
  7. Honglin Li, Masahiro Toyoura, Kazumi Shimizu, Wei Yang, Xiaoyang Mao, “Retrieval of Clothing Images based on Relevance Feedback with Focus on Collar Designs,” The Visual Computer, Vol.32, No.10, pp.1351-1363, 2016-10.
  8. Honglin Li, Wei Yang, Hongcang Sun, Masahiro Toyoura, Xiaoyang Mao, “Example-based Caricature Synthesis via Feature Deviation Matching,” Computer Graphics International, pp.81-84, Article S8, 2016-6.
  9. Wei Yang, Masahiro Toyoura, Jiayi Xu, Fumio Ohnuma, Xiaoyang Mao, “Example-Based Caricature Generation with Exaggeration Control,” The Visual Computer, Vol.32, No.3, pp.383-392, 2016-3.
  10. 孫 宏昌,楊 薇,豊浦 正広,大沼 富美男,茅 暁陽,“特徴偏差の対応付けによる事例ベース似顔絵合成”,Visual Computing/グラフィクスとCAD合同シンポジウム,Article 2,2015-6.
  11. 孫 宏昌,楊 薇,豊浦 正広,茅 暁陽,“事例ベース似顔絵の生成”,画像電子学会ビジュアルコンピューティングワークショップ,Article 10,2014-11.
  12. Jiayi Xu, Wei Yang, Xiaoyang Mao, Masahiro Toyoura, Xiaogang Jin, “A Study on Perceived Similarity between Photograph and Shape Exaggerated Caricature,” Cyberworlds, pp.213-220, 2014-10.
  13. Wei Yang, Kouki Tajima, Jiayi Xu, Masahiro Toyoura, Xiaoyang Mao, “Example-Based Automatic Caricature Generation,” Cyberworlds, pp.237-244, 2014-10.
  14. Shota Fushimi, Kazumi Shimizu, Masahiro Toyoura, Motonobu Hattori, Xiaoyang Mao, “Semiautomatic Synthesis of Face in Mind,” Image Electronics and Visual Computing Workshop, 4B-1, 2014-10.
  15. 伏見 翔太,清水 和美,豊浦 正広,服部 元信,茅 暁陽,“想像上の顔の半自動作成”,Visual Computing/グラフィクスとCAD合同シンポジウム,2014-6.
  16. 田島 洸城,楊 薇,豊浦 正広,茅 暁陽,“見た目の特徴の誇張による事例ベース似顔絵生成”,Visual Computing/グラフィクスとCAD合同シンポジウム,Article 32,2013-6.