Colorization for Gray Scale Facial Image
by Locality-Constrained Linear Coding
Yang Liang, Mingli Song, Jiajun Bu, and Chun Chen
Zhejiang Provincial Key Laboratory of Service Robot
College of Computer Science, Zhejiang University
{liangyang,brooksong,bjj,chenc}@zju.edu.cn
Abstract. Colorization for gray scale facial image is an important tech-
nique in various practical applications. However, the methods that have
been proposed are essentially semi-automatic. In this paper, we present a
new probabilistic framework based on Maximum A Posteriori (MAP) es-
timation to automatically transform the given gray scale facial image to
corresponding color one. Firstly, the input image is divided into several
patches and non-parametric Markov random field (MRF) is employed to
formulate the global energy. Secondly, Locality-constrained Linear Cod-
ing (LLC) is employed to learn the color distribution for each patch.
At the same time, the simulated annealing algorithm is employed to
iteratively update the patches chosen by LLC to optimize the MRF by
decreasing global energy cost. The experimental results demonstrate that
the proposed framework is effective to colorize the gray scale facial im-
ages to corresponding color ones.
Keywords: Colorization,MAP,MRF,LLC.
1 Introduction
Human face conveys lots of information such as identity, appearance, etc. during
social communication or in security systems. However, sometimes only gray scale
images or portraits can be obtained whose facial details like skin color, lip luster,
etc. are lost. For example, because of the quality of surveillance cameras or
storage space restriction, only gray scale images may be obtained. The same for
archeologists, they may only obtain historical gray scale images. So colorization
for gray scale facial image is useful.
In 1970 Wilson Markle[1] introduced the term colorization to describe the
computer assisted process of adding color to a gray scale image. Several ap-
proaches have been presented towards successful image colorization. In general,
the existing colorization approaches can be classified into two groups, one is
example-based method and the other is optimization-based method.
The example-based method colorizes the gray scale image by choosing a sim-
ilar image as a reference, and transferring its colors to the input gray scale
image[2][3]. Welsh in [2] transfers the entire color mood by matching the lumi-
nance and texture of the example image to the target gray scale image pixel by
W. Lin et al. (Eds.): PCM 2012, LNCS 7674, pp. 57–67, 2012.
c
Springer-Verlag Berlin Heide lberg 2012
剩余10页未读，继续阅读
资源评论
