[Back to Home]
IEEE TCSVT 2017

Superpixel-based Face Sketch-Photo Synthesis

Chunlei Peng      Xinbo Gao      Nannan Wang      Jie Li

Xidian University

The face image is divided into (a) regular rectangular patches and (b) superpixels. Overlap between neighboring image patches of (c) rectangular division and (d) superpixel division.

Abstract

    Face sketch-photo synthesis technique has attracted growing attentions in many computer vision applications, such as law enforcement and digital entertainment. Existing methods either simply perform the face sketch-photo synthesis on the holistic image, or divide the face image into regular rectangular patches ignoring the inherent structure of the face image. In view of such situations, this paper presents a novel superpixelbased face sketch-photo synthesis method by estimating the face structures through image segmentation. In our proposed method, face images are first segmented into superpixels, which are then dilated to enhance the compatibility of neighboring superpixels. Each input face image induces a specific graphical structure modeled by Markov networks. We employ a two-stage synthesis process to learn the face structures through Markov networks constructed from two scales of dilation respectively. Experiments on several public databases demonstrate that our proposed face sketch-photo synthesis method achieves superior performance compared with state-of-the-art methods.

Contribution Highlights

• The superpixel is introduced to deal with the face sketch-photo synthesis problem, which can estimate the inherent face structure through image segmentation
• An effective two-stage synthesis framework is designed for face sketch-photo synthesis, which can learn the face structures by Markov networks constructed from two different scales of dilation respectively

Framework

Framework of superpixel based face sketch synthesis.

Protocols

The protocols used in the paper "Superpixel-based Face Sketch-Photo Synthesis" are available :
[Link on Github]
[Link on Baidu (access code: 7yqt)]

Citation

• C. Peng, X. Gao, N. Wang, and J. Li. Superpixel-based Face Sketch-Photo Synthesis. IEEE Transactions on Circuits and Systems for Video Technology, vol. 27, no. 2, pp. 288-299, 2017. [PDF]