An Integrated De-noise and enhancement Method for Ancient Chinese Tablet Images
Zhenghao Shi
School of Computer Science and Engineering
Xi’an University of Technology
Xi’an,china
Email:ylshi@xaut.edu.cn
Binxin Xu
School of Computer Science and Engineering
Xi’an University of Technology
Xi’an,china
Email:1534026834@qq.com
Xia Zheng
Departmentof Culture Heritage Museology
Zhejiang University
Hangzhou,china
Email:zhengxia@zju.edu.cn
Mei Jia
Forest of Stone Steles Museum
Xi’an,china
Email:714001221@qq.com
Abstract—Image noise can severely affect Chinese tablet
image comprehension. In this paper, a novel integrated de-
noising and enhancement method for Chinese tablet image
is proposed. The method consists of three stages de-noising
operations. First, granular bright spots are smoothed by convo-
luting input Chinese tablet images with the bilateral filter. For
obtaining more clear edge detail image, contrast enhancement
between the foreground and background of the Chinese tablet
image is followed by Top-Hat and Bottom-Hat transformations.
Next, a mixture of run-length statistics and connected region
techniques is employed to remove the random block noises in
the images. Then, two mathematical morphological operators,
erosion and dilation, are used to remove small holes and linear
noises. Experimental results show that the proposed method
can effectively remove most image noise (including block noise,
and linear noise) and preserve characters better than existing
methods.
Keywords-Chinese tablet images; integrated de-noising; bi-
lateral filter; run-length; erosion; dilation;
I. INTRODUCTION
The tablet is important for preserving ancient Chinese
calligraphy, and digital tablet images provide a convenient
way to study and reproduce ancient rubbing calligraphy tech-
niques. However image noise greatly affects post-processing
of digital tablet images [1]. Therefore it is important to
remove image noise without damaging the intricate details of
Chinese calligraphy. In general, there are five basic strokes
in Chinese characters: Dian (dot stroke), Heng (horizontal
stroke), Shu (vertical stroke), Pie (left-falling stroke) and Na
(right-falling stroke) [2](Figure 1). These traditional basic
strokes are used to make all other compound strokes or
complex strokes. All these strokes have distinct orientations
and variant widths in a continuous manner (Figure 1). While
image noise is usually randomly distributed in isolation
with irregular shapes and sizes, and the size of image
noise is usually not bigger than the width of the stroke
in most cases. In order to reduce the noise influence, a
novel integrated de-noising and enhancement method for
Chinese tablet images is proposed in this study. First, an
input tablet image is smoothed using a bilateral filter. Next,
the contrast between the foreground and background of the
Chinese tablet image is enhanced using the Top-Hat and
Bottom-Hat transformations. Finally, the image binarization
is performed using the Otsu thresholding method. A mixture
of run-length statistics and connected region is employed to
remove most of the random and block noise from the images.
To the best of our knowledge, our work is the first to apply
a mixture method to tablet image de-noising. Compared to
existing de-noising methods, the proposed method can more
effectively remove image noise from tablet images, enhance
text details, and achieve ideal visual effects.
Figure 1. The five basic Chinese character strokes and their directions
The primary contributions of the work are summarized as
follows:
(1) A three-stage de-noising method for Chinese tablet
images is proposed.
(2) A mixture of run-length statistics and connected
2015 14th International Conference on Computer-Aided Design and Computer Graphics
978-1-4673-8020-1/15 $31.00 © 2015 IEEE
DOI 10.1109/CADGRAPHICS.2015.47
149