Neurocomputing 259 (2017) 154–158
Contents lists available at ScienceDirect
Neurocomputing
journal homepage: www.elsevier.com/locate/neucom
High resolution non-rigid dense matching based on optimized
sampling
Qian Zhang
a , b , ∗
, Changhe Tu
c
a
Key Laboratory of Software Engineering, Shandong University, Jinan 250101, China
b
School of Information Science and Technology, Taishan University, Taian 271021, China
c
School of Computer Science & Technology, Shandong University, Jinan 250101, China
a r t i c l e i n f o
Article history:
Received 22 February 2016
Revised 5 June 2016
Accepted 16 July 2016
Available online 7 February 2017
MSC:
00-01
99-00
Keywords:
Dense Matching
Non-rigid
Less texture
Gibbs dense sampling
High resolution image,
a b s t r a c t
A high resolution dense matching algorithm is presented for non-rigid image feature matching in the
paper. For high resolution non-rigid images, telephoto lens is helpful in capturing fine scale features like
cloth fold, pigmentation and skin pores. It brings us serious image noises which are less texture and
bokeh, respectively. In order to avoid mismatch and non-uniform matching, we propose an optimized
sampling method based on Gibbs dense sampling considering both texture feature similarity and spatial
consistency. In the processing, first we extract connected image patches by triangulation among confi-
dence matched point sets. Then our sampling method is executed in each connected image patch. We
propose a judgment for matching points on the image patch boundary. Markov Random Field (MRF)
model formulates the problem of dense matching as a Bayes decision task. Experiments are design to
demonstrate the effective and efficiency of our method with active skin image data.
©2017 Elsevier B.V. All rights reserved.
1. Introduction
When we recover object shape through binocular stereo vision,
stereo matching is a primary step. The distribution of matched
points is beneficial to the recovery of object shape, and the num-
ber of matched points determines the degree of recovery for de-
tails on object surface. There are two categories of stereo match-
ing phases: sparse matching and dense matching. In sparse match-
ing, candidate feature points are extracted by feature descriptor.
In a non-rigid image, we find that most of the extracted feature
points were distributed within the texture grid in the form of
bright spots. The slight differences between stereo images caused
by light influence are the bright spots. In our research, we consider
a dense matching algorithm by considering texture feature similar-
ity [1,2] and spatial consistency.
Compared with rigid dense matching research [3–5] , non-rigid
distortion and feature noise are the main important problems that
affect the efficiency of dense matching. A large amount of previous
work has been done for non-rigid surface reconstruction [6–10] .
Most of the previous approaches that bring the spatial arrange-
∗
Corresponding author.
E-mail addresses: aazhqg@hotmail.com (Q. Zhang), chtu@sdu.edu.cn (C. Tu).
ment of points into account are computationally expensive, and are
therefore not feasible for dense matching. HaCohen [11] proposed
a reliable local sets of dense matching between a pair of images
either sharing some content but exhibiting dramatic photometric
and geometric variation. By this algorithm matching two general
images that exhibit high variability in appearance is far more com-
plicated. Torki [12] proposed an efficient method for dense match-
ing in a lower-dimensional subspace that simultaneously encodes
spatial consistency and feature similarity. However, this method
still requires exact spectral decomposition for subspace learning.
Hamid [13] improved Torkis work by using the subset of high con-
fidence matches as spatial priors, and learning a subspace that
reduces the confusion among the remaining set of points. The
method of subspace matching could not complete dense match-
ing within less texture images. Except stereo matching, non-rigid
surface filtering was proposed by Zollhfer [14] with the help of
RGB-D camera. His method obtained the non-rigid shape without
dense matching. Tepole [15] combined multi-view stereo and iso-
geometric analysis together to characterize skin kinematics. They
used simple finite element meshes to parameterize the deforma-
tion with poor spatial resolution. From the coordinates of a few
material points, B-spline tensor product patches with a prescribed
parameterization can smoothly interpolate deformations. In our re-
http://dx.doi.org/10.1016/j.neucom.2016.07.076
0925-2312/© 2017 Elsevier B.V. All rights reserved.