Professional Documents
Culture Documents
discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/317394791
CITATIONS READS
0 17
1 author:
Zhenzhou Wang
Chinese Academy of Sciences
47 PUBLICATIONS 180 CITATIONS
SEE PROFILE
All content following this page was uploaded by Zhenzhou Wang on 08 June 2017.
The user has requested enhancement of the downloaded file. All in-text references underlined in blue are added to the original document
and are linked to publications on ResearchGate, letting you access and read them immediately.
Accepted Manuscript
Zhenzhou Wang
PII: S0957-4174(17)30416-5
DOI: 10.1016/j.eswa.2017.06.008
Reference: ESWA 11378
Please cite this article as: Zhenzhou Wang , Image Segmentation by Combining the Global and Local
Properties, Expert Systems With Applications (2017), doi: 10.1016/j.eswa.2017.06.008
This is a PDF file of an unedited manuscript that has been accepted for publication. As a service
to our customers we are providing this early version of the manuscript. The manuscript will undergo
copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please
note that during the production process errors may be discovered which could affect the content, and
all legal disclaimers that apply to the journal pertain.
ACCEPTED MANUSCRIPT
1
Highlights
We calculate the means of different pixel classes from slope difference distribution.
The image is segmented by clustering the pixels to its nearest mean.
The segmentation is further refined by minimizing the energy of its Gibbs distribution.
The boundary of the refined segmentation is deformed to the nearest detected canny edges.
T
IP
CR
US
AN
M
ED
PT
CE
AC
1
ACCEPTED MANUSCRIPT
T
IP
ABSTRACT
Image segmentation plays a fundamental role in many computer vision applications. It is challenging because of
CR
the vast variety of images involved and the diverse segmentation requirements in different applications. As a
result, it remains an open problem after so many years of study by researchers all over the world. In this paper, we
propose to segment the image by combing its global and local properties. The global properties of the image are
characterized by the mean values of different pixel classes and the continuous boundary of the object or region.
US
The local properties are characterized by the interactions of neighboring pixels and the image edge. The proposed
approach consists of four basic parts corresponding to the global or local property of the image respectively: (1),
the slope difference distribution that is used to compute the global mean values of different pixel classes; (2),
Energy minimization to remove inhomogeneity based on Gibbs distribution that complies with local interactions of
neighboring pixels; (3), the Canny operator that is used to detect the local edge of the object or the region; (4), the
AN
polynomial spline that is used to smooth the boundary of the object or the region. These four basic parts are
applied one by one and each of them is indispensable for the achieved high accuracy. A large variety of images are
used to validate the proposed approach and the results are favorable.
Keywords:
Segmentation; Histogram; Gibbs distribution; Slope difference distribution
M
T
until it converges. (4), to improve the accuracy of the extracted
variances of different pixel classes during image segmentation boundaries from the labeled regions, we deform them to the
although its effectiveness has been widely accepted (Carson et
IP
nearest detected Canny edges and then use the polynomial
al., 2002; Won and Gray, 2004). The other popular parameter interpolation to smooth them.
estimation algorithm, k-means clustering method (Jain, 2010) To detect the global peaks from the smoothed histogram
could not effectively deal with the first problem and the second
CR
distribution robustly, we utilize the slope difference distribution
problem either. The estimated global parameters by EM or K- that is defined as the variation rate of the histogram distribution
means are frequently inaccurate in image segmentation (Wang, 2016). The peaks and valleys of the histogram
applications. For the popular thresholding methods (Osuna- distribution usually have much greater variation rates compared
Encisa et al., 2013), their accuracies are also affected by the first to other parts of the histogram. In addition, the global peaks of
two problems. Some researchers have tried to solve the second
problem by estimating the noise separately and apply the de-
noising technique to suppress the estimated noise (Sagar et al.,
2014, Manjon et al., 2015, Chan et al., 2006), which achieved
US the histogram distribution correspond to the cluster centers of the
pixel classes when they are Gaussian distributed, which is true in
most image segmentation cases. The slope difference distribution
is computed by calculating the difference of the slope values on
AN
significant improvement in segmentation accuracy. However, it the left side and the right side of each point on the smoothed
is also very difficult to estimate the parameters of the noise histogram. The slope values are computed by fitting two straight
model accurately. The overlap of the gray-scale distributions of lines on both sides of the point on the smoothed histogram with N
different pixel classes, the different levels of noise magnitudes points. The proper selection of N could suppress smaller local
and the different forms of noise distributions make it difficult to peaks while retain larger global peaks. The means of different
M
estimate the parameters with adequate accuracy in most cases. pixel classes correspond to the global peaks of the slope
To address the third problem, the image had been assumed as difference distribution distinctly and are resistant to the problem
a Markov Random Field (MRF) that is subject to the Gibbs caused by the distribution overlap of different pixel classes.
distribution (Derin and Elliott, 1987; Caillol et al., 1993; Wang
ED
of the MRF-based method is that it could distinguish different challenging problems one by one. Firstly, the means of different
textured regions, especially for the textures that could be pixel classes are computed from the global peaks of the
modeled and defined with parameters. The major drawback of histogram distribution. The advantages of computing the mean
MRF-based methods is that they could not estimate the values of the pixel classes based on the global peaks of the
histogram distribution include: (1), If we calculate the cluster
AC
T
yi axi b (3)
BT B BT Y
1
a, b
T
IP
(4)
x1 1
CR
x 1
B 2
(a) (b)
(5)
xN 1
y1 , y2 ,, yN
Y
US
T
(6)
Two slopes at point i , a1 i and a2 i are obtained from Eq.
(4). The slope difference, s i , at point i is computed:
AN
s i a2 i a1 i ; i G1 N ,..., G2 N (7)
(c) (d)
Fig. 1. Demonstration of finding the global peaks by the slope difference
The number N of the fitting points in the line model is critical distribution. (a) Synthesized image with noise level 0, 10 ; (b)
for magnifying the global peaks while suppressing the local Synthesized image with noise level 0, 20 ; (c) Finding the global
peaks. Thus, its selection is very important and needs some peaks by slope difference distribution computed for the first synthezied image;
M
calibration process to determine its value for a specific class of (d) Finding the global peaks by slope difference distribution computed for the
images. Fortunately, there is a wide range of N values that could second synthezied image.
meet the requirement and its default value is chosen as 15 for the From Fig. 1 (d), we see the second problem that the noise
histogram in the interval of [0, 255]. modifies the histogram distribution and causes great errors during
ED
The positions where the global peaks occur correspond to the calculation of the pixel mean values. To eliminate or reduce the
mean values of the pixel classes in the image. To compute the bad impact of noise, we propose the following low-pass filtering
peaks positions from the slope difference distribution, we set the method in the frequency domain. The histogram distribution,
derivative of the slope difference distribution s x to zero and P x is transformed into the frequency domain by the Discrete
PT
select the solutions corresponding to the peak parts. Fourier Transformation (DFT):
G2 2 kx
ds i
dx
0; s( x) 0 (8) F k P x e
x G1
T
; k G1 ,..., G2 (9)
CE
peaks are sorted. The number of pixel classes is determined by kept while the high frequency parts of it are eliminated by the
the total number of the sorted means or manual input. When the following equation.
F k ; k G1 , G1 1,..., G1 B 1
number of pixel classes is determined manually, the means are
selected one by one based on their magnitudes. The mean value
that corresponds to the peak with the greatest magnitude is F k F k ; k G2 B 1,..., G2 1, G2 (11)
selected as the first mean. 0; k G1 B,..., G2 B
To demonstrate the process of finding the global peaks by
slope difference distribution, we synthesized two images with where B denotes the bandwidth of the low pass filter and we
two objects and one background in Fig. 1 (a) and (b) respectively. set its default value as 10 based on testing a great variety of
The synthesized image in Fig. 1 (a) is with the pixel mean value images. After transforming the histogram from the frequency
of the background equal 50, the pixel mean value of the first domain back into the time domain by the following equation, we
object equal 100 and the pixel mean value of the second object get the smoothed histogram, P x .
equal 150. For the first synthesized image, we add the Gaussian 2 xk
1 G2
P x F k e T ; x G1 ,, G2
i
noise with the magnitude 0, 10 and the image model (12)
T k G1
is 0 50, 0 10; 1 100,1 10; 2 150, 2 10 . For
the second synthesized image, we add the Gaussian noise with
the magnitude 0, 20 and the image model is
4
ACCEPTED MANUSCRIPT
eliminated successfully. For the practical implementation of the
Gibbs energy minimization, please refer Wang and Zhang, 2012.
After the image is labeled and its inside inhomogeneity is
eliminated, the boundaries of the labeled objects are extracted as
shown in Fig. 4 (a). It is seen that the Gibbs energy minimization
causes the boundary to be noisy and the extracted boundary does
not match the objects true boundary well. In addition, there are
two different boundaries extracted for the brightest object, which
Fig. 2. Demonstration of the effectiveness of the proposed filter and the is caused by the fourth challenging problem that the boundary of
correctness of finding the global peaks by the computed slope difference
distribution.
the labeled region is affected greatly by the overlap the grayscale
To demonstrate the effectiveness of the proposed low-pass distributions of different pixel classes. We define the problem
filtering method, we show the process of finding global peaks by that multiple boundaries are extracted from the segmentation
the slope difference distribution computed from the smoothed result for the same object as the pixel distribution overlapping
histogram distribution for the synthesized image (Fig. 1 (b)) in problem. This problem could not be avoided for the labelling
Fig. 2. As can be seen, the proposed filter could remove the noise method based on the Euclidean distance (Eqs. (13-14)) and it
from the histogram distribution effectively and the global peaks frequently appears in other literatures (Carson et al., 2002;
could be detected correctly after the slope difference distribution Felzenszwalb and Huttenlocher, 2004).
T
was computed from the smoothed histogram distribution. The
reason we use the Fourier transform based low pass filter instead
IP
of other filters is that it is capable of preserving the shape of the
low frequency part well while removing the high frequency parts
effectively.
CR
After the mean values of all the pixel classes, l ; l 1,.., L are (a) (b)
Fig. 4. Demonstration of boundary delineation. (a) Extracted boundary
computed, the image is labeled by the following equation. from the labelled image with Gibbs energy minimization; (b) Delineated
Ilabel (u, v) l; u 1,..,U ; v 1,..,V (13) boundary after deforming the bounday in (a) to the nearest Canny edges.
where (u, v) denotes the position of the pixel in the image and
U V denotes the resolution of the image. L denotes the total
number of pixel classes in the image and l denotes the pixel class
that is computed as:
l arg min I (u, v) l
US
AN
(14) (a) (b)
Fig. 5. Comparison of boundary with detected canny edges. (a) Extracted
boundary overlaying on the detected canny edges; (b) Final smooth boundary
overlaying on the detected canny edges.
To refine the extracted boundary B , we propose the
following boundary deformation method.
M
regions in the image are usually not homogeneous at the same object by Eqs (1)-(18) . R and r denote the total number of
spatial scale. This local property could be formulated by the points and the index of the points on it respectively. E denotes
Gibbs distribution that characterizes the image as a Markov the detected canny edges. Q and q denote the total number of
random field X = {Xs} with a joint distribution (Derin and Elliott, points and the index of the points on it respectively. The total
CE
1987; Caillol et al., 1993; Wang and Zhang, 2012). number of points R on the canny edges are usually much greater
e cC c
1 V ( x) than the total number of the points Q on the extracted boundary.
P( X x) (15)
V ( x)
e cC c There exist R points on the extracted canny edges that make
xL
Eq. (19) minimum and they form the deformed boundary that is
AC
T
(d) respectively. The corresponding segmentation results are
shown in Fig. (e), (f), (g) and (h) respectively. As can be seen,
IP
the number of the peaks and valleys of the slope difference
distributions decrease with the increase of the value of N. The
automatic computed clustering centers are correct when N equals
CR
5, 15 and 25. However, when N equals 45, the computed (c) (d)
clustering center is incorrect. This demonstration indicates that
there is a wide range of N that could meet the requirement to
make the proposed method to achieve an acceptable performance
(at least the range [5 25] meets the requirement).
(a) (b) when the bandwidth equals 50; (e) the segmentation result when the
bandwidth equals 5; (f) the segmentation result when the bandwidth equals 20;
(g) the segmentation result when the bandwidth equals 40; (h) the
segmentation result when the bandwidth equals 50.
ED
T
segmentation results for these four synthesized images are shown
in Fig. 9 (a)-(h) respectively. As can be seen, the quality of the
IP
detected Canny edges decreases with the increase of the noise 3.2. Results of segmenting synthesized images
level, so does the segmentation performance. However, the To control the image model precisely, we synthesized several
increase of the noise level has more adverse effect on the images to demonstrate the advantage of the proposed approach
CR
detected Canny edges than on the clustering accuracy of slope over state of the art methods. We compared the performance of
difference distribution. Hence, we conclude that the canny the proposed approach with eleven methods with available
detection could withstand less Salt and Pepper noise level than MATLAB codes: (1), Kernel Graph Cuts (Salah et al., 2011); (2),
the slope difference distribution could withstand. Normalized Graph Cuts (Shi and Malik, 2000); (3) Graph
segmentation performance with the systhesize image. (a) canny edges of the
synthesized image with Salt and Pepper noise density 0.8; (b) final
segmentation result of the synthesized image with Salt and Pepper noise
density 0.8; (c) canny edges of the synthesized image with Salt and Pepper
noise density 1.6; (d) final segmentation result of the synthesized image with
Salt and Pepper noise density 1.6; (e) canny edges of the synthesized image
PT
density 3.2.
To prove the DFT low pass filter is good at preserving the (g) (h) (i) (j) (k) (l)
shape of the low frequency part well, we design the following Fig.10. Results of segmenting synthesized noisy images; (a) Proposed; (b)
experiments. We compare it with other well-known filters Kernel Graph Cuts (Salah et al., 2011); (c) Normalized Graph Cuts (Shi and
quantitatively in maintaining the means of the pixel classes. We Malik, 2000); (d) Graph (Felzenszwalb and Huttenlocher, 2004); (e) EM
AC
T
We blur the synthesized image in Fig. 10 by minimizing the
Gibbs distribution of the image to get the fuzzy image. The
IP
segmentation results are shown in Fig. 11 (a)-(j). At this time, k-
means failed to segment the image correctly while the proposed (a) (b) (c) (d) (e) (f)
approach and normalized cuts still perform well. All the other
CR
tested methods perform unsatisfactorily.
Cuts (Shi and Malik, 2000); (d) Graph (Felzenszwalb and Huttenlocher,
2004); (e) EM (Dempster et al., 1977); (f) K-means (Jain, 2010); (g) Active segment the image into some regions unexpectedly. The Graph,
contours without edge (Chan and Vese, 2001); (h) GM (Chan et al., 2006); (i) EM and K-means methods yield too many regions. The active
Distance regularized level set (Li et al., 2010); (j) Region based active contour without edge, GM, GMM, FFCM, Distance regularized
contour (Lankton and Tannenbaum, 2008); (k) GMM (Nguyen et al., 2013);
ED
(l) FFCM (Nguyen and Wu, 2013).. level set and region based active contour methods failed to
We synthesize a more complex image with four rectangular delineate the boundaries of the plane accurately. The result of the
objects on the background in Fig. 12 and their means and proposed approach appears to be better. We compare the
variances are {230, 30}, {180, 30}, {140, 30}, {90, 30} and {40, segmentation results on another 3 images in Figs. 15-17. The
30} respectively. As can be seen, only the proposed approach visual results verified the superiority of the proposed approach
PT
could segment the rectangles successfully while all the other over state of the art methods.
methods perform badly, but differently. In addition, some state of
the art methods performed relatively better than other state of the
art methods. For instance, FFCM performs the second best in this
CE
specific case.
We blur the synthesized image in Fig. 12 by minimizing the (a) (b) (c) (d) (e) (f)
Gibbs distribution of the image again to get next fuzzy image.
The segmentation results are shown in Fig. 13 (a)-(j). At this time,
AC
T
synthesize another 100 images with only one object and segment
the object from the background by different methods. The
IP
computed F-measures are compared in Fig. 21 and the average F-
measures are compared in Table. 5. As can be seen, the proposed
method also achieves better accuracy. We show the ground truth
CR
(g) (h) (i) (j) (k) (l) boundaries for the first dataset and for the second dataset in Fig.
Fig.17. Results of segmenting a typical image from Berkeley dataset; (a) 22 (a) and (b) respectively for better understanding of the
Proposed; (b) Kernel Graph Cuts (Salah et al., 2011); (c) Normalized Graph
Cuts (Shi and Malik, 2000); (d) Graph (Felzenszwalb and Huttenlocher, designed experiments. The ground truth boundaries are computed
2004); (e) EM (Dempster et al., 1977); (f) K-means (Jain, 2010); (g) Active when the noise level is zero and they are overlaying on the
contours without edge (Chan and Vese, 2001); (h) GM (Chan et al., 2006); (i) synthesized fuzzy image with the magnitude of the Gaussian
contour (Lankton and Tannenbaum, 2008); (k) GMM (Nguyen et al., 2013);
(l) FFCM (Nguyen and Wu, 2013)..
3.4. Quantitative results
US
Distance regularized level set (Li et al., 2010); (j) Region based active noise equal 10.
AN
In this section, we evaluate the proposed approach
quantitatively. In this study, we first compare the accuracy of the
proposed approach with that of the EM and K-means methods in (a) (b)
finding the pixel mean values. We synthesize an image dataset Fig.18. Demonstration of the synthesized images in the dataset (a) The
with 100 images in total. In the synthesized dataset, one hundred synthesized noisy image; (b) The fuzzy image obtained by minimizing the
M
classes with mean values equal to 50, 100, 150 and 200
respectively and their variances are denoted by V . Fig. 18 (a)
shows the first synthesized image with V equal to 10. Before
computing the pixel mean values by the compared methods, we
PT
(a) (b)
Fig. 22. Demonstration of groundtruth boundary overlaying on the
synthesized fuzzy image with Gaussian noise magnitude equal 10. (a)
Groundtruth boundary for the first synthesized image set; (b) Groundtruth
boundary for the second synthesized image set.
T
second synthesized image set (LR-AC represents localized region based
active contour; NE-AC represents active contour without edge; DR-LS
IP
represents distance regularized level set.)
CR
Methods Average error Average time
EM 7.8360 1.07 s
K-means 7.8177 0.11 s
Proposed 5.7431 0.12 s
Measure
PRI
VoI
Proposed
0.7984
2.2247
Kernel graph cuts
0.7650
2.4091
US
Table. 3 Comparison of the proposed approach with state of the art methods
N- cuts
0.7229
2.9329
Graph
0.7841
2.6647
Mean-shift
0.7555
2. 477
K-means
0.7882
2. 304
AN
Table. 4 Comparison of the average F-measure computed by different methods from the first synthesized image
Measure Proposed Region based Active contours Distance regularized GM EM K-means FFCM GMM
active contour without edge level set
F-measure 0.9860 0.8937 0.9482 0.9385 0.7893 0.9277 0.8051 0.8001 0.7990
M
Table. 5 Comparison of the average F-measure computed by different methods from the second synthesized image
Measure Proposed Region based Active contours Distance regularized GM EM K-means FFCM GMM
active contour without edge level set
F-measure 0.9801 0.9369 0.9617 0.9015 0.4015 0.9438 0.7038 0.5080 0.5658
ED
image segmentation algorithms to solve specific problems. After deal with the noise and overlaps of multiple distributions. As it
decades of evolution, the segmentation methods converge to turned out that the slope difference distribution method is more
several categories, e.g. graph based methods (Felzenszwalb and accurate than EM and K-means methods. For the local property
Huttenlocher, 2004; Shi and Malik, 2000; Salah et al., 2011),
CE
2011). Unfortunately, these methods are only good at segmenting nature, the proposed approach is different from the traditional
some specific types of images while perform poorly in other categories of state of the art segmentation methods. In
types of images. As a result, it is necessary to exploit new theory performance, the proposed approach is more robust than state of
or directions to come up with more effective methods that could the art methods because it utilizes the properties of the image
segment more classes of images robustly. more generally.
Image segmentation remains challenging because the vast
variety of images are usually with different properties. For 5. Conclusion
instance, the histogram distributions of different types of images
In this paper, a new direction of image segmentation based on
might comply with different mathematic formulations, although
both the local property and the global property of the image is
they are assumed to be Gaussian distributed in most cases. The
exploited. The proposed approach calculates the means of
noise and the overlapping of different pixel classes in the
different pixel classes from the slope difference distribution and
histogram distribution make the estimation of the parameters
it is significantly more accurate than the benchmark EM and K-
challenging. Furthermore, the inhomogeneous spatial scale of
means methods. The image is labelled by clustering the pixel to
different regions makes the segmentation more difficult. In
the nearest means. To improve the accuracy of the labelled result,
general, the image has local properties and global properties that
we suppress the inhomogeneity inside the image by minimizing
should be utilized effectively during segmentation. EM and K-
the Gibbs energy function. To improve the accuracy of the
means have been served in estimating the global parameters in
extracted boundary, we deform the boundary to the nearest
many image segmentation applications. Unfortunately, their
Canny edges and then optimize the whole boundary with
accuracies are limited by the complexity and variety of the image
10
ACCEPTED MANUSCRIPT
polynomial splines. Experiments were conducted on a large Wang, Z.Z., Zhang, Y.M., 2012 Segmentation of fuzzy images: a novel and
quantity of images and experimental results show that this new fast two-step pseudo MAP method, Machine Vision and Applications,
23(6), 1209-1218.
segmentation approach is very promising. Won, C.S., Gray, R.M., 2004 Stochastic image processing. Information
technology: Transmission, Processing, and Storage.
Acknowledgments Yang, A.Y., Wright, J., Ma, Y., Sastry, S.S., 2008 Unsupervised
segmentation of natural images via lossy data compression, Computer
The author would like to thank the Chinese Academy of Vision and Image Understanding, 110, 212225.
Sciences for the funding with the grant number Y5A1270101.
References
Arbelaez, P. , Maire, M., Fowlkes, C., Malik, J., 2011 Contour detection and
hierarchical image segmentation, IEEE Transactions on Pattern
Analysis and Machine Intelligence, 33(5), 898916.
Besag, J., 1986 On the statistical analysis of dirty pictures. Journal of the
Royal Statistical Society. Series B., 48(3), 259-302.
Caillol, H., Hillon A., Pieczynski, W., 1993 Fuzzy random fields and
T
unsupervised image segmentation. IEEE Transactions on Geoscience
and Remote Sensing GE-31, 4, 801810.
IP
Canny, J., 1986 A computational approach to edge detection, IEEE T PAMI,
8(6), 679-698.
Carson, C., Belongie, S., Greenspan, H., Malik, J., 2002 Blobworld: image
segmentation using expectation-maximization and its application to
CR
image querying, IEEE Transactions on Pattern Analysis and Machine
Intelligence, 24(8), 10261038.
Chan, T.F., Esedoglu, S., Nikolova, M., 2006 Algorithms for finding global
minimizers of image segmentation and denoising models, SIAM J. Appl.
Math., 66(5), 1632-1648.
Chan, T.F., Vese, L.A., 2001 Active contours without edges, IEEE
Transactions on image processing, 10(2), 266277.
Chen, S.F., Cao, L.L., Wang, Y.M., Liu, J.Z., Tang, X.O., 2010 Image
Segmentation by MAP-ML Estimations. IEEE Transactions on Image
Processing, 19(9), 2254-2264.
US
AN
Comaniciu, D., Meer, P., 2002 Mean shift: a robust approach toward feature
space analysis. IEEE Transactions on pattern analysis and machine
intelligence, 24(5), 603-619.
Dempster, A.P., Laird, N.M., Rubin, D.B., 1977 Maximum likelihood from
incomplete data via the EM algorithm. Journal of the Royal Statistical
Society, Series B, 39(1), 1-38.
M
Derin, H., Elliott, H., 1987 Modeling and segmentation of noisy and textured
images using gibbs random fields. IEEE Transactions on Pattern
Analysis and Machine Intelligence, 9(1), 3955.
Felzenszwalb, P.F., Huttenlocher, D.P., 2004 Efficient graph-based image
segmentation. International Journal of Computer Vision, 59(2), 167-181.
ED
Nguyen, T.M., Wu, Q.M., 2013 A fuzzy logic model based Markov random
field for medical image segmentation, Evolving systems, 4, 171-181.
Osuna-Encisa, V., Cuevas, E., Sossa, H, 2013 A comparison of nature
inspired algorithms for multi-threshold image segmentation, Expert
systems with applications, 40, 1213-1219.
Sagar, S., Brando, V.E., Sambridge, M., 2014 Noise estimation of remote
sensing reflectance using a segmentation approach suitable for optically
shallow waters, IEEE Trans. Geosci. Remote Sens., 52(12), 75047512.
Salah, M.B., Mitiche, A., Ayed, B., 2011 Multiregion image segmentation by
parametric kernel graph cuts, IEEE Trans. on Image Processing, 20(2),
545-557.
Shi, J., Malik, J., 2000 Normalized cuts and image segmentation, IEEE Trans.
on Pattern Anal. Mach. Intell., 22(8), 888905.
Unnikrishnan, R., Pantofaru, C., Hebert, M., 2005 A measure for objective
evaluation of image segmentation algorithms, in Proc. IEEE Int. Conf.
Comput. Vis. Pattern Recognit., 3, pp. 3441.
Wang, Z.Z., 2016 A new approach for segmentation and quantification of
cells or nanoparticles, IEEE T Ind. Inform., 12 (3), pp. 962-971.