Intelligent Automatic Extraction of Canine Cataract Object with Dynamic Controlled Fuzzy C-Means based Quantization

International Journal of Electrical and Computer Engineering (IJECE)
Vol. 8, No. 2, April 2018, pp. 666~672
ISSN: 2088-8708, DOI: 10.11591/ijece.v8i2.pp666-672  666
Journal homepage: http://iaescore.com/journals/index.php/IJECE
Intelligent Automatic Extraction of Canine Cataract Object
with Dynamic Controlled Fuzzy C-Means based Quantization
Kwang Baek Kim1
, Doo Heon Song2
1
Division of Computer Software Engineering, Silla University, Busan 46958, Korea
2
Department of Computer Games, Yong-In SongDam College, Yong-in 17145, Korea
Article Info ABSTRACT
Article history:
Received Nov 12, 2017
Revised Feb 2, 2018
Accepted Feb 10, 2018
Canine cataract is developed with aging and can cause the blindness or
surgical treatment if not treated timely. Since the pet owner do not have
professional knowledge nor professional equipment, there is a growing need
of providing pre-diagnosis software that can extract cataract-suspicious
regions from simple photographs taken by cellular phones for the sake of
preventive public health. In this paper, we propose a software that is highly
successful for that purpose. The proposed software uses dynamic control of
FCM clusters in quantification and trapezoid membership function in fuzzy
stretching in order to enhance the intensity contrast from such rough
photograph input. Through experiment, the proposed system demonstrates
sufficiently enough accuracy in extraction (successful in 42 out of 45 cases)
with better quality comparing with previous attempt.
Keyword:
Canine cataract
Dynamic cluster control
Fuzzy c-means
Fuzzy stretching
Pre-diagnosis Copyright © 2018 Institute of Advanced Engineering and Science.
All rights reserved.
Corresponding Author:
Kwang Baek Kim,
Division of Computer Software Engineering,
Silla University,
140, Baegyang-daero(Blvd) 700 beon-gil(Rd), Sasang-gu, Busan 46958, Korea.
Email: gbkim@silla.ac.kr
1. INTRODUCTION
A cataract is an opacity of the lens or lens capsule, histologically death and disruption of lens
epithelial causing opacity. The cataract usually progresses to involve larger areas of the lens and rate of
progression is difficult to predict in the speed or the magnitude of the development [1]. The causes of the
cataract formation are genetic, secondary to ocular diseases, traumatic, toxic, age-related, radiation-induced,
and/or caused by electrocution [2]. The treatment of canine cataract can be injection of eye drops to delay the
development or artificial lens insertion by surgery and the surgical methodology may be decided by the age
of the dog and symptoms in consideration of postoperative treatment [3]. Surgery is generally recommended
when the cataracts cause diminished vision, or for progressive cataracts where vision loss is anticipated [4].
However, an accurate evaluation of the lens is obligatory before its removal in order to achieve the best
postoperative result [5].
The cataract for dogs are found usually in the process of regular checkup by veterinarian. However,
it needs pet breeder's continuous care and knowledge about the pet's status. As noted in [6], there have been
several researches using ultrasonography [7], MRI [8], endoscopic evaluation technique [9] and, if we can
extract characteristic features for the diagnosis, even machine learning techniques might be applicable [10] to
assist the medical expert.
However, there are many misconceptions about cataracts in society of pet owners in that it is a film
over the eye or a type of cancer or can spread from one eye to the other or causes irreversible blindness [1].
Usually a pet dog gives a sign to its owner by expressing unusual behavior or by the change of its body when
its health is at risk or having a disease. Without deep knowledge about the pet dog’s disease, owners tend to
neglect such signs only to make the situation worse [11].

Int J Elec & Comp Eng ISSN: 2088-8708 
Intelligent Automatic Extraction of Canine Cataract Object with Dynamic …. (Kwang Baek Kim)
667
Thus, we have developed a handy pre-diagnostic tool for pet owners that detects cataract-suspicious
object from normal cellular phone photographs. The system may not need to be as accurate as the medical
doctor’s professional analyzing tools like MRI but its role is to draw attention to the public to listen to their
pet’s complaints for preventive public healthcare.
We have tried various image processing algorithms in conjunction with some artificial intelligent
techniques such as ART2 learning, and Fuzzy C-Means (FCM) image to overcome given noise prone cellular
phone image analysis [6], [11], [12].
In this paper, we apply dynamic control of FCM in quantization process and trapezoid type
membership function in fuzzy stretching for brightness enhancement. When we applied ART2 [6], the
software can not discriminate white hair around eyes from cataract in ART2 clustering process thus there was
an inaccurate cataract extraction case. FCM was considered as the alternative of ART2 to overcome that
problem. However, the static FCM that has predefined number of clusters in quantization process was found
too much sensitive to the environment - brightness distribution near cataract region and other region - and
time consuming [12]. Dynamic cluster control can be a solution in this environment thus we modified the
FCM as such.
2. BRIGHTNESS ENHANCEMENT WITH FUZZY STRETCHING
The input image in this paper is a simple digital camera image that may contain irregular pixel
values. The first task of our software is to find the boundary lines of cataract-suspicious object. Then, we
nned to enhance the brightness contrast between the “bright” side and the “dark” side.
In this paper, we apply fuzzy stretching for that purpose like we used in [6] but change the
membership function from the usual triangle type to trapezoid type that has been successful in many
applications where the intensity distribution seems to be irregular [13].
Let Xi
G
be the grey value of pixel Xi , then the average intensity value Xm
G
is defined as formula (1).


MN
i
G
i
G
m X
MN
X
0
1 (1)
where M, N denote the width and length of the input image.
Let Xl
G
, Xh
G
be the lowest and highest intensity value of the image, the maximum and minimum
differences from the average are defined as formula (2)
G
l
G
m
GG
m
G
h
G
XXDXXD  minmax , (2)
And then the adjustment rate adjustmentG
can be determined as following;
G
m
G
GGG
m
G
GGGG
m
G
m
GG
m
Xadjustmentelse
DadjustmentthenXDifelse
DadjustmentthenDXifelse
XadjustmentthenXif




maxmax
minmin
)(
)(
255)128(
(3)
Since the shape of the membership function is trapezoid, we need to find 1/3 and 2/3 points as
following;
)(
3
2
)(
3
1
minmaxmax
minmaxmin
min
max
GGG
mid
GGG
mid
GG
m
G
GG
m
G
III
III
adjustmentXI
adjustmentXI




(4)
Then the membership function for the fuzzy stretching as as shown in Figure 1.

 ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 8, No. 2, April 2018 : 666 – 672
668
Figure 1. Trapezoid Type Membership Function
The upper limit value (β) and the lower limit value (α) are defined as the highest and lowest Xi
among pixels that have higher membership degree than the cut point (α-cutG
) as following;
5.0
2/))/()/(()0( maxminminmin


G
GGGGG
cutelse
IIIcutIif


(5)
Then the final stretched value of the pixel is computed as following;.
255)( 


 GG
G
I
If


(6)
3. DYNAMIC CONTROLLED FUZZY C-MEANS IN QUANTIZATION
FCM Algorithm is an unsupervised clustering method that has been widely used for ultrasound
image analysis where pixels with the same features is grouped into the same cluster. Using FCM algorithm,
the colors in the image are segmented depending on the number of clusters that is usually predefined line we
used in [12].
From [12], we experienced that the quantization process was not sufficiently correct in that some
objects were incorrectly grouped due to the predefined number of clusters. The shape of the canine cataracts
may variate according to the different species in size of the eyeball and hair thus we need more adaptation in
this quantization process.
Thus, in this paper, we change the number of clusters dynamically based on the accumulated error
rate of membership degree.
Thus, the FCM used in this paper works as following;
Step 1: Initialize the number of cluster c (2≤c<n), exponential weight m(1≤m<∞), and the
membership degree u(0)
Step 2: Compute the central vector vij as Equation (7) for{vi|i=1,2,...,c}




 n
k
m
ik
n
k
kj
m
ik
ij
u
xu
v
1
1
)(
)(
(7)
Step 3: Compute the distance dik between the kth
pattern xk and the central vector of the ith
cluster by
the Equation (8).
2/1
1
2
)()( 





 
l
j
ijkjikik vxvxdd (8)
where l denotes the number of pattern nodes. Then, vik, the new membership degree of kth
pattern in ith
cluster is computed as Equation (9).

669
 












kIi
r
ik
kk
r
ikk
k
r
ik
kc
j
mr
jk
r
ik
r
ik
uAND
IcIdnciI
Iiiclassesallforuor
Ifor
dd
u
1
},...,2,1{
~
,0;2|
~
,0
)/(
1
)1(
)(
)1(
1
1/2
)1(

(9)
Step 4: Compute the difference between the new and the previous membership degree as shown in
Equation (10). Also, in this step, accumulate the differences based on the number of clusters c. If the
difference is larger than the error threshold (ε), then go to Step 2.
kkkif
uuUU
t
r
ik
r
ikik
rr

 
)(
max )()1()()1(

(10)
Step 5: Determine the number of clusters c as shown in Equation (11).






20
10
0
)20(
c
ce
n
j
jc
NN
NNcif
(11)
where c is the initial number of clusters and j is the real number of the clusters. ΔNj is the accumulated
differences and Nc is thus that of initialized c.
In his paper, we explore the number of clusters between 10 and 20 and then determines the final
number of cluster of the given data as the one which minimizes Ne. And repeat the procedure of FCM until
no more significant changes exist.
The effect of this dynamic control of FCM quantization is demonstrated as Figure 2 compared with
static controlled scheme.
(a) After Fuzzy stretching (b) Quantization by Static FCM [12]
(c) After Fuzzy stretching (d) Proposed FCM
Figure 2. The Effect of Dynamic FCM in Quantization

 ISSN: 2088-8708
670
In Figure 2, the static FCM had the number of clusters as 15. One can find the clear difference in
extracting cataract candidate region.
After quantization, we apply average binarization and morphological operators such as erosion and
expansion. Small objects in the region of interest(ROI) are removed as noise and a sufficiently big (over 3/5
of ROI in size) candidate object is chosen as the probable cataract as shown in Figure 3.
(a) ROI (b) After Average binarization
(c) Erosion and Expansion (d) Extracted Cataract
Figure 3. Extracting Cataract by the Proposed Method
4. EXPERIMENT
The system is implemented in Visual Studio 2013 C# with Intel(R) Core(TM) i5-3330U CPU @
1.80GHz and 4 GB RAM PC. 45 real world dog eye photographs having cataract taken by cellular phones are
used in this experiment. Figure 4 demonstrates a snapshot of the implemented system.
Figure 4. Snapshot of the System Output
Several real examples of extracting cataract suspicious regions are demonstrated in Figure 5.

671
Figure 5. Cataract Extraction Examples
Table 1 summarizes the performance result of the proposed method comparing with previous
attempt [12].
As one can see from Table 1 and Figure 6, the proposed method is much better in successful
extraction rate and the quality in general. A veterinarian is involved in this experiment to evaluate and verify
the quality of the system. Three failed cases of extraction does not meet the size constraint in this experiment.
Table 1. Cataract Extraction Performance
Previous [12] Proposed
Success 36 / 45 42 / 45
(a) Previous (b) Proposed
(c) Previous
(d) Proposed
Figure 6. Performance comparison in Cataract Region Extraction
5. CONCLUSION
Like human, dogs also develop cataracts with age among many other causes. It can cause blurred
vision and eventually entire lens diffusely can become cloudy, and all functional vision may be lost.

 ISSN: 2088-8708
672
However, since the patient is a dog who has very limited capability of complaining its abnormalities to
human, we need a pre-diagnostic tool for the pet owners who have limited knowledge of animal diseases.
In this paper, we propose a computer vision based software to extract canine cataract from digital
camera photographs automatically. This effort has been done by our team for many years with different
technical algorithms involved [6], [11], [12].
Intelligent control of FCM clusters in quantization and careful trapezoid type membership functions
used in fuzzy stretching are keys of successful result in this experiment.
Since this pre-diagnostic function for knowledge-limited pet owners without professional equipment
does not have to meet the rigorous standard in accuracy, the proposed method is verified as effective for
casual pet dog owners to see if the dig has cataract problem as early as possible. We expect that similar
vision based methodology can be applied to extract glaucoma and give pre-diagnosis of abnormality as soon
as possible.
REFERENCES
[1] V. N. Patil, et al., “Extra Capsular Cararact Surgery in canine - A Pictorial View,” International Journal of
Veterinary Science & Research, vol. 1, no. 1, pp.1-6, 2014.
[2] M. G. Davidson and S. R. Nelms, “Diseases of the canine lens and cataract formation”. In: Veterinary
Ophthalmology, 4th edn. (ed. Gelatt KN) Ames, Blackwell Publishing, pp. 859–887, 2007.
[3] S. J. Yoo, “An Outline about a Canine Cataract,” The Journal of Veterinary Science, vol. 40, no. 8, pp. 708-716,
2004.
[4] P. D. S. Raghuvanshi and S. K. Maiti, “Canine cataracts and its management: An overview,” Journal of Animal
Research, vol. 3, no. 1, pp.17-26, 2013.
[5] T. L. McCalla, “Cataract in dogs: Animal eye care LLC,” Bellingham, http://www.waltham.com, (2005).
[6] K.B. Kim, “Extraction of Canine Cataract Object for Developing Handy Pre-diagnostic Tool with Fuzzy Stretching
and ART2 Learning,” International Journal of Fuzzy Logic and Intelligent Systems, vol. 16, no. 1, pp. 21-26, 2016.
[7] M. Dar, et al., "B-scan ultrasonography of ocular abnormalities: a review of 182 dogs," Iranian Journal of
Veterinary Research, vol. 15, no. 2, pp. 122-126, 2014.
[8] M. J. Lizak, et al., “Quantitation of galactosemic cataracts in dogs using magnetization transfer contrast-enhanced
magnetic resonance imaging,” Investigative Ophthalmology and Visual Science, vol. 37, pp. 2219-2227, 1996.
[9] M. A. Abd-Elhamid, et al., “Endoscopic evaluation for the anterior and posterior segment of the eye: A new and
useful technique for diagnosis of glaucoma in dogs,” Life Science Journal, vol. 11, no. 11, 2014.
[10] G. Swati and A. M. Karandikar. "Diagnosis of Diabetic Retinopathy using Machine Learning." Journal of Research
and Development, 2015.
[11] K. B. Kim, et al., “Machine Intelligence can guide Pet Dog Health Pre-Diagnosis for Casual Owner: A Neural
Network Approach,” International Journal of Bio-Science and Bio-Technology, vol. 6, no. 2, pp. 83-90, 2014.
[12] M. S. Kim, et al., “Cannie Cataract Extraction and Analysis from Pet Image by Using FCM Algorithm,” Proc. of
spring Conference of KIICE, vol. 20, no. 1, pp. 94-96, May 2016.
[13] K. B. Kim and D. H. Song, “A Trapezoid Type Fuzzy Stretching for Automatic Subsurface Damage Detection
among Spectacle Lens Products,” In 2016 INTERNATIONAL CONFERENCE on Future information and
Communication Engineering (ICFICE 2016), vol. 8, no. 1, pp. 197-200, June 2016.
BIOGRAPHIES OF AUTHORS
Kwang Baek Kim received his M.S. and Ph.D. degrees from the Department of Computer Science,
Pusan National University, Busan, Korea, in 1993 and 1999, respectively. From 1997 to the present,
he is a professor at the Department of Computer Engineering, Silla University, Korea. He is
currently an associate editor for Journal of Intelligence and Information Systems and The Open
Computer Science Journal (USA). His research interests include fuzzy neural network and
applications, bioinformatics, and image processing.
Doo Heon Song received a B.S. degree in Statistics & Computer Science from Seoul National
University and M.S. degree Computer Science from the Korea Advanced Institute of Science and
Technology in 1983. He received his Ph.D. Certificate in Computer Science from the University of
California in 1994. Form 1983-1986, he was a research scientist at the Korea Institute of Science and
Technology. He has been a professor at the Department of Computer Games, Yong-in Songdam
College, Korea, since 1997. His research interests include ITS, machine learning, artificial
intelligence, medical image processing, cognitive, and game intelligence.

Intelligent Automatic Extraction of Canine Cataract Object with Dynamic Controlled Fuzzy C-Means based Quantization

More Related Content

What's hot (19)

Similar to Intelligent Automatic Extraction of Canine Cataract Object with Dynamic Controlled Fuzzy C-Means based Quantization (20)

More from IJECEIAES (20)

Recently uploaded (20)

Intelligent Automatic Extraction of Canine Cataract Object with Dynamic Controlled Fuzzy C-Means based Quantization