Incorporating Index of Fuzziness and Adaptive Thresholding for Image Segmentation

International Journal of Electrical and Computer Engineering (IJECE)
Vol. 8, No. 4, August 2018, pp. 2406~2418
ISSN: 2088-8708, DOI: 10.11591/ijece.v8i4.pp.2406-2418  2406
Journal homepage: http://iaescore.com/journals/index.php/IJECE
Incorporating Index of Fuzziness and Adaptive Thresholding
for Image Segmentation
Umi Salamah1
, Riyanarto Sarno2
, Agus Zainal Arifin3
, Anto Satriyo Nugroho4
,
Ismail Ekoprayitno Rozi5
, Puji Budi Setia Asih6
1,2,3
Department of Informatics, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia
1
Department of Informatics, Universitas Sebelas Maret, Surakarta, Indonesia
4
Center for Information and Communication Technology Agency for the Assessment and Application of Technology
(PTIK-BPPT), Indonesia
5,6
Eijkman Institute for Molecular Biology, Indonesia
Article Info ABSTRACT
Article history:
Received Jan 8, 2018
Revised Jun 28, 2018
Accepted Jul 10, 2018
Binary Segmentation of an image played an important role in many image
processing application. An image that was having no bimodal (or nearly)
histogram accompanied by low-contrast was still a challenging segmentation
problem to address. In this paper, we proposed a new segmentation strategy
to images with very irregular histogram and had not significant contrast using
index of fuzziness and adaptive thresholding. Index of fuzziness was used to
determine the initial threshold, while adaptive thresholding was used to
refine the coarse segmentation results. The used data were grayscale images
from related papers previously. Moreover, the proposed method would be
tested on the grayscale images of malaria parasite candidates from thickblood
smear that had the same problem with this research. The experimental results
showed that the proposed method achieved higher segmentation accuracy
and lower estimation error than other methods. The method also effective
proven to segment malaria parasite candidates from thickblood smears
image.
Keyword:
Adaptive thresholding
Bimodal
Index of fuzziness
Significant contrast
Very irregular histogram
Copyright © 2018 Institute of Advanced Engineering and Science.
All rights reserved.
Corresponding Author:
Umi Salamah,
Department of Informatics, Institut Teknologi Sepuluh Nopember Surabaya,
Jl. Teknik Kimia, Gedung Teknik Informatika,
Kampus ITS Sukolilo, Surabaya, 60111, Indonesia.
Email: umi14@mhs.if.its.ac.id
1. INTRODUCTION
Image segmentation is a critical process in many image processing applications such as object
detection, shape recognition, and optical character recognition [1]. Segmentation accuracy determines the
success or failure of computerized analysis procedures [2]. Global Thresholding is a popular tool used in
image segmentation [3], because it easy implemented. Optimal condition of image segmentation is obtained
if there is a significant contrast between the object and the background. The condition is characterized by
bimodal formation with a deep valley in image histogram. The valley that separates the two modalities is the
right location of the threshold [2].
The absence of an obvious splitting valley is due to noise and poor illumination, so the segmentation
process becomes not optimal. Some studies based on statistical properties of the image histogram are
addressed to solve the problem. Between-class variance is suggested by Otsu [4] to segment optimally the
object of the image. Inter-class variance and intra-class variance are utilized by Arifin and Asano [5] to
threshold the image by performing hierarchal clustering analysis. However, these methods do not constantly
function well on ill-defined images that are impaired by noise and irregularly illuminated. A Measure of
fuzziness is offered some studies to overcome the problem. Huang and Wang [6] minimize the measure of

Int J Elec & Comp Eng ISSN: 2088-8708 
Incorporating Index of Fuzziness and Adaptive Thresholding …. (Umi Salamah)
2407
fuzziness to threshold the image. Tizhoosh [7] propose ultra fuzziness which is a new fuzzy measure based
on the fuzzy set type II. However, the technique does not constantly function for images with a very irregular
histogram.
This problem get over by Tobias and Seara [8], Lopes et al [2], and Pratamasunu [9] use fuzzy
similarity measure between graylevel that is more compatible with object edges and ambiguity, and it can
prevent in minimum finding problems. The similarity calculation process involves one of the fuzzy measures,
i.e. index of fuzziness (IoF) to determine the appropriate fuzzy region. The result is very satisfying.
However, it does not always work on very irregular histogram images and has not significant contrast. The
segmentation accuracy decrease compared segmented result using the only IoF. This result happens because
sometimes finding the minimum of a function is trapped on local optimal. Therefore, a segmentation strategy
that can handle images that have very irregular histograms and low-contrast is needed. In this paper, we
propose a new segmentation strategy to images with very irregular histogram and have not significant
contrast using IoF and adaptive thresholding. The result will be implemented on candidate parasite
segmentation that most of the images have the same problem with this study.
2. RELATED WORK
2.1. Index of Fuzziness
Index of fuzziness is one type of fuzzy measure. These terms describe the measures of the proximity
of a grey tone image to its two-tone version and also ambiguity in a fuzzy set. The low value indicates the
low ambiguity among the elements. Crossover point modification of will yield in a diversity of these
parameters and so a set of minima is acquired appropriate to the optimum threshold levels [10]. The IoF is
defined [11] as
   AAd
n
AI k
~
,
2
 (1)
where  AAd
~
, denotes the distance between set A and its nearest ordinary set A
~
and n is the number of
elements in A. An ordinary set A
~
nearest to the fuzzy set A is defined as
 
 
 





0.5if1
0.5if0
~
iA
iA
iA
x
x
x


 (2)
Based on the value of k, there are two types of index, i.e. linear and quadratic. Linear IoF may be written as
Equation (6).
    



1
0
~1,min
2 n
g
iAiAA aa
n
 (3)
Meanwhile, Tizhoosh [7] defines a linear IoF,  gX for a M×N image subset A ⊆ X with L graylevel g ∈
[0, L−1], the histogram h(g), and the membership function  gX as follows.
        



1
0
1,min
2 L
g
AAX gggh
MN
g  (4)
2.2. Thresholding Algorithm using Fuzzy Similarity Measure
Lopes et al [2] and Pratamasunu etal. [9] using fuzzy similarity measure to image segmentation. To
calculate it at each histogram level, it is necessary to specify the fuzzy region first. At Lopes et al [2], fuzzy
region boundary search using statistical parameters, P1 and P2. If Bseed is the initial region of black/dark
pixels, Wseed is the initial region of white/bright pixels, and h(xi) shows the number of occurrences at
graylevel, then P1 has gotten from minimal search a function of the number of pixels in the graylevel
intervals [0, 127] dan [128, 255] with Equation (5).

 ISSN: 2088-8708
Int J Elec & Comp Eng, Vol. 8, No. 4, August 2018: 2406-2418
2408
   
 
 


255127
1280
1WseedBseedMinPix
i
ixhP (5)
The value of P1  [0, 1]. Meanwhile, P2 is obtained from Equation (6).
PMIN = P2MN (6)
If the number of pixels including to the graylevel intervals [0,127] or [128, 255] is smaller than a value PMIN,
so the image histogram must be equalized. Based on an experiment using 30 images obtained the value of P1
and P2 is 39,64% and 20%, respectively. At Pratamasunu et al [9], fuzzy region boundary is defined based on
the fuzzy region centre. For the fuzzy region centre VC and number of pixels on graylevel g, h(g), boundaries
of initial seed for dark and bright region, VB, and VW, are defined as
 
 
 
 












 1
1
1
0
0
andV L
Vg
L
Vg
WV
g
V
g
B
C
C
C
C
gh
ghg
V
gh
ghg
(7)
The fuzzy region boundary search process is done along graylevels. The fuzzy regions selected are a region
with the highest IoF. The general algorithm of Pratamasunu etal. [9] proposed method as follows:
Step 1. Compute the image histogram
Step 2. Move B and W throughout graylevels
Step 3. Compute IoF, γ, in each graylevel
Step 4. Determine the centre of fuzzy region, VC = arg max(γ)
Step 5. Compute the boundaries of seed subsets, BV and WV
Step 6. For all graylevels if in fuzzy region calculate   ifB  and   ifW 
Step 7. Threshold the image with T = arg max (   ifB ,   ifW  )
where   
   
 
        








n
g
AAn
g
n
g
i
i
gggghAM
gh
fSMg
fS
1
1
1
2
*and 
2.3. Adaptive thresholding by Anitha et al.
Anitha et al [12] performed a refinement segmentation in mass detection in mammograms based on
Histogram Peak Analysis (HPA) using adaptive window based thresholding approach. The threshold is
computed for each pixel in the region of interest, to recognize if the pixel is suspicious (1) or normal (0) by
setting a small window, W, sized 15×15. This window-based adaptive thresholding is based on the intensity
contrast that marks the intensity divergence between mass and background. To increase the selection of
thresholds for each pixel, I(x, y), the algorithm to refine the result segmentation of a pixel, Bfine(x, y), is
presented as follows.
 
 
  
 
  


 



 


else
yxWyxI
yxB
else
IyxWyxI
yxB
TyxW
mean
fine
meandiff
fine
Cdiff
0
,),1
,
Else
0
,),1
,
Then,If

(8)
where      yxWyxWyxWdiff ,,, minmax  and TC = (Imax + mean of all pixel greater than Imax)/2. δ is a bias
threshold coefﬁcient. It takes values in the range of 0 to 1. The value is set empirically as δ=0.5. Imean and Imax

2409
are the mean and maximum intensity of the image. Wmax(.), Wmin(.), and Wmean(.) are the maximum,
minimum, and mean intensity values in the small window, respectively. The computed threshold for each
pixel makes a reﬁnement segmentation that gives an exact segmentation of the suspicious lesion.
3. RESEARCH METHOD
3.1. Material
Data for this research (original image and ground truth) are provided from grayscale images from
Lopes et al [2], and Pratamasunu et al [9]. Moreover, experiment data are images of malaria parasite
candidate with grayscale JPG format. The data are obtained from Malaria slide of Eijkman Institute for
Molecular Biology. The extraction of the thickblood smear is based on hierarchical classification based on
the morphological characteristics of connected components. The ground truths were built based on Malaria
Diagnosis Guideline by expert instruction.
3.2. Proposed Method
The purpose of this paper is to perform binary segmentation on an image that divides the image into
foreground and background areas. This type segmentation needs well-defined image, i.e. having bimodal (or
nearly) histograms. Very irregular histogram is defined by Tobias and Siera [8] as the cases where the image
histogram may only have local minimum, or even not have any minimum at all. Example of very irregular
histogram is shown as Figure 1c and 1d. The proposed method consists of two main parts, i.e. perform the
initial thresholding on the image using IoF and refinement pixels using Adaptive thresholding.
a b c
d
Figure 1. Modal of histogram image: a. bimodal, b. nearly bimodal, c. unimodal, d. Multimodal
3.2.1 Measurement of Index of Fuzziness
Two memberships are built to calculate the IoF, i.e. dark region (B) and bright region (W) as shown
in Figure 2a. The S and Z functions are used to model dark and bright region, respectively [11]. Formulation
of both functions in (9) and (10).

 ISSN: 2088-8708
2410
   































cx
cxb
ac
ax
bxa
ac
ax
ax
cbaxSxAS
,1
,21
,2
,0
,,; 2
2
 (9)
with initial parameters a and c are taken from the lowest and highest level of the image histogram, while b is
defined as b=(a+c)/2.
     cbaxScbaxZxAZ ,,;1,,;  (10)
In this work, IoF is calculated using Equation (4) for each fuzzy subset region by utilizing the appropriate
fuzzy membership. The formulation of the IoF for each graylevel of dark and light areas respectively such as
Equations (11) and (12).
    



1
0
2 L
g
BB ggh
N
 (11)
a. b. c.
Figure 2. Threshold determination process: a. Membership function of dark and bright areas,
b. Calculation process of Index of Fuzziness each graylevel, c. Finding the maximum Index of Fuzziness
    



1
0
2 L
g
WW
ggh
N
 (12)
Multiplication of both indexes determines the total index for each graylevel.
WBT  
(13)
         





1
0
1
0
2
4 L
g
W
L
g
BT gghggh
N
 (14)
The process of calculating IoF from each graylevel position is performed by moving membership functions
(μB and μW) throughout graylevels that are restrained by a point T as shown in Figure 2b. The threshold can
be determined by graylevel with the maximum IoF as shown in Figure 2c. Coarse segmented image, B,
obtained by performing this threshold on the image. Figure 3 is an example of image segmentation result
using IoF based threshold.

2411
Figure 3. Example of result segmentation
3.2.2 Refinement Pixel
Coarse segmentation result from the previous process is compared with ground truth. There are two
types of misclassification, i.e. the background is predicted as the object called false positive (FP) and the
object is predicted as background called false negative (FN). From the data in Figure 4, the threshold
obtained using IoF is 109. The number of FP and FN are 93 and 185, respectively. The distribution of
number of misclassification pixel and the corresponding number of true classified pixel is presented in
Figure 4.
Figure 4. Distribution of number of misclassification pixel
Misclassification occurs in pixels with intensities around the threshold [13]. It happens because
pixels at the same intensity can belong to foreground or background depending on the relation of a pixel to
the surrounding pixels. Such cases often occur in images that have different illumination, noise, or the
condition of some objects have an intensity similar to the background. Therefore, a refinement on these
pixels is needed. The fixed threshold is rather unlikely in this situation, a local threshold is more
appropriately used to suit the varying lighting conditions and changing background [14]-[18].
Refinement of the segmentation results for each pixel, Bfine(x, y), with the intensity around the
threshold is based on local contrast methods that utilize the statistical properties of previous segmentation
results. The refinement operation is performed on some neighbourhood (w×w window). The comparison is
made between the average pixel intensity in the window of an original image (Wmean) and the average pixel
intensity in the foreground region of the initial segmentation results (ROImean) as in Figure 5. The refinement
algorithm for the initial pixel segmentation results,  yxBfine , , as in (16).
 
 


 

else
ROIyxW
yxB meanmean
fine
0
,1
, (16)
Moreover, the refinement algorithm may also use adaptive thresholding (8) proposed by Anitha et al [13]
based on h(T).

 ISSN: 2088-8708
2412
Figure 5. ROI and the histogram
3.2.3 Proposed Thresholding Algorithm
The general algorithm of the proposed method describes as follows.
Step 1. Compute the image histogram
Step 2. Move B and W throughout graylevels
Step 3. Compute IoF, γ, in each graylevel
Step 4. Find T = arg max(γ)
Step 5. Threshold the image with T
Step 6. Find number of pixel at T, h(T)
Step 7. For all pixels that have intensities on interval VC do refinement to the segmentation result in
Step 5. If h(T) is low, then use Equation (8), else use Equation (16).
4. RESULTS AND DISCUSSION
To illustrate the performance, used experiment data are from related research papers, i.e. six images
from Lopez et al [2] and Pratamasunu et al [9] and five noisy images from Pratamasunu et al [9]. Moreover,
the experiment also uses ten parasite candidate images that have been extracted from malaria slide of some
thickblood smear. Comparison method uses Otsu and thresholding method based fuzzy similarity measure.
Some given parameters are as follows. The size of window is 3×3, α=4, and the low limit h(t) is 100.
The performance measure of segmentation uses Accuracy Segmentation (Acc) that measure the ratio of pixels
that truly classified. Acc can be expressed as
%100
)(




oo
ToTo
FB
FFBB
Acc (17)
where , , and are the foreground and background pixels in the ground truth image and the
segmentation result, respectively. The range of Acc value is [0, 100]. If the Acc value is 100 then the
segmentation result is same with the ground truth image. Six testing images from Lopez et al [2] and
Pratamasunu et al. [9] are used in the first experiment. Segmentation is performed using segmentation
method proposed by Pratamasunu etal. (Fuzzy Similarity Measure, FSM), proposed method (Fuzzy Indexes
and Automatic Thresholding, FIAT), and Otsu Thresholding (Otsu). The result is shown in Figure 6.
The histogram of an original image is presented as Figure 7.
Visually, the result of segmentation using FSM method is almost the same as the proposed method.
Otsu thresholding gets slightly worse results than both. Quantitatively, the segmentation accuracy of such
methods is presented in Table 1. Segmentation accuracy using IoF (Fuzzy Indexes, FI) and segmentation
method that proposed by Lopes etal. without and with histogram equalization (EM1 and EM2) is added in
that table.
There are several analyzes related to the use of compared segmentation method based on Table 1.
Firstly, the use of FI can provide satisfactory accuracy results. It proven from greater than 90% accuracy for
all sample images. Secondly, the use of fuzzy similarity measure-based method, EM2 and FSM, have
improved accuracy and obtained the highest results on images that they have deep valley histograms and
clear objects than the background (Gearwheel, Potatoes, and Stone image). However, the accuracy decrease
compared to segmentation results by FI method on images that have a very irregular histogram and
low-contrast. Finaly, the use of the proposed method, FIAT, can improve overall accuracy compared to FI

2413
and achieves the highest accuracy on images that have very irregular histogram and low-contrast between
object and background.
Figure 6. Result segmentation on Blocks, Gearwheel, Potatoes, Rice, Stone, and Zimba images, respectively
Figure 7. Histogram of first group images
Second experiment uses synthetic reference image from Pratamasunu et al [10]. Four images else
are composed with different graylevel intervals from this reference image. These images are obtained by
adding increasing Gaussian noises as shown in Figure 8. It can be seen that increased noise causes a decrease
in the steepness of the valley formed on the image histogram. Increasing noise decreases the separation
between object and background.
The segmentation performance results of several methods to this data are shown in Table 2.
Segmentation accuracy with FSM is outstanding when the image histogram has a clear separation between
objects and backgrounds marked by deep valley on the histogram as shown in Figure 8d and 8e. Meanwhile,
the proposed method is outstanding in the opposite condition. Based on the average accuracy of the five
images,the proposed method is outstanding than FSM and Otsu.

 ISSN: 2088-8708
2414
Figure 8. Synthetic reference image: a. The original image, b. Ground truth, c. Histogram of the original
image, d–g. Histogram of original image that give Gaussian Distribution noises g(0.01, 0.01), g(0.05, 0.05),
g(0.10, 0.10), and g(0.15, 0.15), respectively
Table 2. Segmentation Accuracy from Second Group Sample
No Image
Acc (%)
FSM FIAT Otsu
1 Original 100 100 100
2 Original+ g(0.01, 0.01) 99.99 99.96 99.89
3 Original+ g(0.05, 0.05) 99.64 99.56 99.04
4 Original+ g(0.10, 0.10) 88.49 90.25 82.97
5 Original+ g(0.15, 0.15) 84.91 85.05 76.46
Average 94.61 94.96 91.67
Figure 9 shows graphs of the IoF for each graylevel from the five images in the second experiment.
It can be seen that the addition of noise to the original image causes the IoF graph change, but the graylevel
position with maximum value does not have much effect since it does not move much from the position
without noise. It shows that the use of IoF to determine the threshold is robust to noise. Refinement pixel-
pixel on segmentation results around the threshold of the noisy image to be the right choice to improve the
accuracy of segmentation results.
Figure 9. Index of Fuzziness Graph from images of the second experiment
In the third experiment, we used grayscale images of parasite candidate from thickblood smear as
shown Figure 10. A malaria parasite is characterized by a nucleus with attached cytoplasm [19]. The
presence of the cytoplasm is important for distinguishing a parasite's nucleus from an object whose shape and
size resemble parasite's nucleus [20], [21]. The size of each file is 140×140 pixels that derived from 16 times

2415
bicubic magnification from an extraction of malaria parasite candidate 35×35 pixels. Most of these images
have a very irregular histogram and low-contrast. This can be seen from the image histograms in Figure 11b.
a b
Figure 10. Malaria parasite candidate: a. RGB images, b. Grayscale image
Most of the segmentation results with the FSM method are under segmentation as shown in
Figure 11d, so the resulting object is smaller than the ground truth. Even some images lose cytoplasm
(3rd, 6th, and 8th candidate). This condition is opposite with result segmentation using Otsu method that
over-segmentation as shown in Figure 11f. Results segmentation of the proposed method as shown in
Figure 11e are more similar to the groundtruth than two other methods for almost any image. Different
results are shown on the 5th and 6th candidate images. Both images have a bimodal (or nearly) histogram
with a deep valley between them. Accuracy segmentation 5th parasite candidate image using FSM method is
higher than others. It has a clear distinction between objects and background. Meanwhile, in the 6th
candidate image, the object is clearly visible although the contrast is not too high, the background conditions
are homogeneous. For this image, the Otsu method produces segmentation results that are more similar to
ground truth.
a b c d e f
Figure 11. Result segmentation of parasite candidate: a. The original image, b. Histogram image,
c. Groundtruth, d-f. Result segmentation of FSM, proposed method, and Otsu, respectively
Beside accuracy segmentation, we define performance that measures the distance between the ideal threshold
(TIdeal), i.e. the optimal threshold performed manually based on visual inspection and threshold generated by
the segmentation method (TComp) called Estimation Error (EE). Smaller the value of EE means the better the
segmentation results. The formulation of EE as defined in Equation (18).

 ISSN: 2088-8708
2416
%100
255
T-T CompIdeal
EE (18)
Performance of segmentation methods on the parasite candidates quantitatively is shown in Table 3.
The results show that the proposed method can produce the closest threshold to the ideal threshold.
Moreover, it has the highest accuracy and lowest estimation errors in most of the images. By results of the
previous visual analysis, FSM excels quantitatively at the fifth candidate, while Otsu excels at the 6th
candidate. This result shows that the proposed method is properly implemented in parasite candidate images.
Table 3. Performance of segmentation methods from Third Group Sample
Image
Threshold Estimation Error (%) Acc (%)
Ideal FSM FIAT Otsu FSM FIAT Otsu FSM FIAT Otsu
Candidate 1 75 47 82 108 10.98 2.75 12.94 95.68 97.92 91.07
Candidate 2 130 81 124 139 19.22 2.35 3.53 88.66 97.63 97.08
Candidate 3 80 63 87 112 6.67 2.75 12.55 95.49 98.55 91.75
Candidate 4 70 108 66 98 14.9 1.57 10.98 84.1 89.73 85.87
Candidate 5 125 106 171 159 7.45 18.04 13.33 96.87 92.32 94.08
Candidate 6 120 39 75 122 31.76 17.65 0.78 91.94 94.14 98.05
Candidate 7 130 171 145 104 16.08 5.88 10.20 91.31 91.33 45.7
Candidate 8 137 156 141 129 7.45 1.57 3.14 88.73 93.25 89.41
Candidate 9 117 123 118 104 2.35 0.39 5.10 96.94 98.19 95.63
Candidate 10 125 147 126 124 8.63 0.39 0.39 92.41 92.52 92.51
Average 12.55 5.33 7.29 92.21 94.56 88.12
Based on the experimental results of the three datasets above, it can be concluded that the proposed method is
suitable for use on binary segmentation of images that have very irregular histogram and low-contrast.
The use of the method on multi thresholding cases will be further research.
5. CONCLUSION
A new strategy to overcome segmentation problem on images that have a very irregular histogram
and not significant contrast is presented in this paper. The strategy is incorporating IoF and adaptive
thresholding. Initial threshold is obtained by finding graylevel with the maximum IoF. Furthermore,
segmentation is performed on the image with the initial threshold so that the coarse segmented are obtained.
Better segmentation results are obtained from implemented local thresholding based on an adaptive window.
Experimental results show that the proposed segmentation method gives improved accuracy than any other
methods. Meanwhile, fuzzy similarity measure based segmentation method is more suitable to be used on
images that have a deep valley on the histogram and significant contrast. In the future, the criterion or size of
the irregularity of the histogram needs to be mathematically defined so that the exact method can be
determined for different image conditions.
ACKNOWLEDGEMENTS
This research was supported by Ministry of Research, Technology and Higher Education of the
Republic of Indonesia under Grant PDD 2017 with contract number is 873/UN27.21/PP/2017. We are
grateful to Mr Pratamasunu and Eijkman Institute for Molecular Biology Indonesia for preparing the
materials for this research and giving access to the datasets. We are also grateful to Mr Pratamasunu for the
supports of comparison program for this research.
REFERENCES
[1] Weszka JS. A survey of threshold selection techniques. Computer Graphics and Image Processing. 1978; 7(2):
259–265.
[2] Lopes NV, Mogadouro PA, Bustince H, Melo-pinto P. Automatic Histogram Threshold Using Fuzzy Measures.
IEEE Transactions On Image Processing. 2010; 19(1): 199–204.

2417
[3] Sezgin M, Sankur B. Survey over image thresholding techniques and quantitative performance evaluation.
Journal of Electronic Imaging. 2004; 13(1): 146–165.
[4] Otsu N. A threshold selection method from gray-level histograms. IEEE Transaction on System, Man, and
Cybernetics. 1979; 9: 62–66.
[5] Arifin AZ, Asano A. Image segmentation by histogram thresholding using hierarchical cluster analysis. Pattern
Recognition Letters. 2006.
[6] Huang LK, Wang MJJ. Image Thresholding by Minimizing The Measure of Fuzziness. Pattern Recognition.
1995; 28(1): 41–51.
[7] Tizhoosh HR. Image thresholding using type II fuzzy sets. Pattern Recognition. 2005; 38: 2363–2372.
[8] Tobias OJ, Seara R. Image Segmentation by Histogram Thresholding Using Fuzzy Sets. IEEE Transactions On
Image Processing. 2000; 11(12): 1457–1465.
[9] Pratamasunu GQO, Arifin AZ, Navastara DA, Wijaya AY, Khotimah WN. Image Thresholding Based on Index
of Fuzziness and Fuzzy Similarity Measure. IEEE 8th International Workshop on Computational Intelligence and
Applications. Hiroshima, Japan. 2015.
[10] Pal SK, King RA, Hashim AA. Automatic grey level thresholding through index of fuzziness and entropy.
Pattern Recognition Letters. 1983; 1( 3): 141–146.
[11] Bustince H, Herrera F, and Montero J. Fuzzy Sets and Their Extensions: Representation, Aggregation and
Models. Springer, 2008.
[12] Anitha J, Peter JD, and Alex SI. A dual stage adaptive thresholding (DuSAT) for automatic mass detection in
mammograms. Computer Methods and Programs in Biomedicine. 2017; 138: 93–104.
[13] Jamal I, Akram MU, Tariq A. Retinal Image Preprocessing: Background and Noise Segmentation.
TELKOMNIKA. 2012; 10( 3): 537–544.
[14] Zhang W, Dou J. A Fast Thresholding Technique in Image Binarization for Embedded System. TELKOMNIKA
Indonesian Journal of Electrical Engineering. 2014; 12(1): 592–598.
[15] Singh OI, James O, Sinam T, Singh TR. Local Contrast and Mean based Thresholding Technique in Image
Binarization. International Journal of Computer Applications. 2012; 51(6): 5–10.
[16] Hore S, et al. An Integrated Interactive Technique for Image Segmentation using Stack based Seeded Region
Growing and Thresholding. International Journal of Electrical and Computer Engineering. 2016; 6(6): 2773–
2780.
[17] Yazid H, Arof H. Gradient based adaptive thresholding. Journal of Visual Communication and Image
Representation. 2013; 24(7): 926–936.
[18] Singh TR, Roy S, Singh OI, Sinam T, Singh KM. A New Local Adaptive Thresholding Technique in
Binarization. International Journal of Computer Science Issues. 2011; 8(6): 271–277.
[19] WHO, Basic Malaria Microscopy, 2nd ed. Switzerland: WHO Press, 2010.
[20] Salamah U, et al. Enhancement of Low Quality Thickblood Smear Microscopic Images of Malaria Patients using
Contrast and Edge Corrections. International Conference on Knowledge Creation and Intelligent Computing
(KCIC). Menado, Indonesia. 2016; 219–225.
[21] Abidin SR, Salamah U, Nugroho AS. Segmentation of Malaria Parasite Candidates from Thick Blood Smear
Microphotographs Image Using Active Contour Without Edge. International Conference on Biomedical
Engineering (IBIOMED). Yogyakarta, Indonesia. 2016; 78–83.
BIBLIOGRAPHY OF AUTHORS
Umi Salamah received her Master degree in 2002 and she is currently a Ph.D. student in the
Department of Computer Science at the Institut Teknologi Sepuluh Nopember Surabaya,
Indonesia. Her research interests include image processing and pattern recognition in
computer aided diagnosis for malaria from thick blood smears microphotograph
Riyanarto Sarno received his M.Sc and Ph.D in Computer Science from the University of
Brunswick Canada in 1988 and 1992. His research includes Internet of Things, Enterprise
Computing, Information Management, Intelligent Systems and Smart Grids

 ISSN: 2088-8708
2418
Agus Zainal Arifin received his Master degree in Computer Science University of Indonesia in
2001 and Dr. degree in Information Engineering from Hiroshima University, Japan in 2007.
His research interests included Pattern Recognition, Image Processing, Computer vision, and
Computational intelligent
Anto Satriyo Nugroho received his M.Eng. and Dr.Eng. degrees in Electrical and Computer
Engineering from Nagoya Institute of Technology of Japan, in 2000 and 2003 respectively.
His research interests included Pattern Recognition & Image processing with applied field of
interests on Biometrics & Computer aided diagnosis for Malaria status identification from
blood smears microphotograph. Currently, he is the President of Indonesian Association for
Pattern Recognition (INAPR), elected in 2017
Ismail Ekoprayitno Rozi received his Master degree in Bioengineering from Nagaoka
University of Technology in 1995. Now he is working as senior researcher in bioinformatics
unit and IT officer of Eijkman Institute for Molecular Biology. He is interested in computer
aided diagnosis for malaria from blood smears
Puji Budi Setia Asih earned her doctoral degree in 2010 from University of Indonesia. Now
she is currently the head of Malaria and vector resistance Department at the Eijkman Institute
for Molecular Biology. She has involved in several research projects such as molecular
mechanisms underlying Plasmodium resistance to anti malarial drugs and anti malarial drug
discovery through medicinal plants.

Incorporating Index of Fuzziness and Adaptive Thresholding for Image Segmentation

More Related Content

What's hot (19)

Similar to Incorporating Index of Fuzziness and Adaptive Thresholding for Image Segmentation (20)

More from IJECEIAES (20)

Recently uploaded (20)

Incorporating Index of Fuzziness and Adaptive Thresholding for Image Segmentation