St.

Thomas’ College of Engineering and Technology

Synopsis on

Retinal blood vessel extraction

Department of Information Technology

By

NAME UNIVERSITY ROLL NO.

PINAKI PAL 12200216033

KAUSTUV NANDY 122002160

Under the guidance of

Dr. RANJIT GHOSH

St. Thomas’ College of Engineering and Technology

Affiliated to MAKAUT

Maulana Abul Kalam Azad University of Technology, West Bengal

Department of Information Technology P a g e 1 | 19

 St. Thomas’ College of Engineering and Technology

St. Thomas’ College of Engineering and Technology

We are submitting the synopsis on Retinal blood vessel extraction as a part of our final year
seventh semester project under the guidance of Dr. Ranjit Ghosh

Pinaki Pal Kaustuv Nandy

Dr. Ranjit Ghosh

Department of Information Technology

Department of Information Technology P a g e 2 | 19

 St. Thomas’ College of Engineering and Technology

St. Thomas’ College of Engineering and Technology

Vision - To promote the advancement of learning in Information Technology through

research oriented dissemination of knowledge which will lead to innovative applications of
information in industry and society.

Mission –

 To incubate students, grow into industry ready professionals, proficient research

scholars and enterprising entrepreneurs.
 To create a learner- centric environment that motivates the students in adopting
emerging technologies of the rapidly changing information society.
 To promote social, environmental and technological responsiveness among the
members of the faculty and students

PEO

Project Mapping with Program Outcomes

PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12

Enter correlation levels 1, 2 or 3 as defined below:

1: Slight (Low) 2: Moderate (Medium) 3: Substantial (High)

Justification :

PSO

Project Mapping with Program Specific Outcomes

PSO1 PSO2 PSO3

Enter correlation levels 1, 2 or 3 as defined below:

1: Slight (Low) 2: Moderate (Medium) 3: Substantial (High)

Department of Information Technology P a g e 3 | 19

 St. Thomas’ College of Engineering and Technology

Index Page

St. Thomas’ College of Engineering and Technology

Table of Contents Page No.

1. Introduction
1.1 Problem Statement
1.2 Problem Definition
1.3 Objective
1.4 Literature Survey / Background Study
1.5 Brief Discussion on Problem (maximum three pages)

2. Concepts and problem analysis (maximum five pages)

3. Conclusion

Annexure : Reference / Bibliography

Department of Information Technology

Department of Information Technology P a g e 4 | 19

 St. Thomas’ College of Engineering and Technology

Retinal blood vessel extraction

1. Introduction
Among the modern health care community, medical imaging has become the most important tool;
this is because of the visual documentation and record storing for the patients and for its ability to
information extraction about many diseases. For retinal image analysis, there are several
applications, such as diabetic retinopathy, where it can be used in addition to their important roles
in some disease detection in early stages [1, 2]. Because of segmentation of retinal image structures
using in modern ophthalmology as a non-invasive diagnosis; it has been a very interested topic. For
retinal diseases such as hypertension, diabetic retinopathy, hemorrhages, macular degeneration,
glaucoma, neovascularization and vein occlusion, working on the optic disc and the retinal blood
vessel morphology is one of the basic indicators for assessing the presence and severity for each of
these diseases. Assessment of the retinal blood vessels diameter and tortuosity or the optic disc
shape manually has many disadvantages such as, time consuming and prone with human error,
especially with complicated vessel structure and a large number of images [3].

Some of diseases listed above such as glaucoma, diabetic retinopathy, and macular degeneration
are very dangerous. If they aren’t detected correctly and in time, they can lead to blindness.
Therefore, an accurate automated segmentation approach for retinal blood vessel and optic disc is
a very important issue in computer aided diagnosis [2]. The automation of segmentation and
investigation of retinal blood vessel features helps ophthalmologist and eye care specialists to carry
out mass vision screening exams for retinal diseases detection in early stages and treatment
evaluation. This could help at prevention and reduction of vision impairments; age related diseases
and many cardiovascular diseases as well as screening cost reduction [4].

1.1. Problem Statement

To automatically extract retinal blood vessel features from fundus image in a fast and efficient
way for ophthalmologic study of different diseases.

1.2. Problem Definition

In this project we have tried to present an automated segmentation approach for retinal blood
vessel extraction. This approach is based on adaptive thresholding method and some
morphological operations. The rest of the report documents the related works done on this field,
their methodologies, and the differences between them, followed by the core concepts of
morphological operations and adaptive thresholding algorithm. After this we have explained
about our approach in a detailed manner with the help of diagrams and flow-chart. The final
section consists of the conclusion and the future scope of this approach

Department of Information Technology P a g e 5 | 19

 St. Thomas’ College of Engineering and Technology

1.3. Objective
This paper proposes a technique to extract blood vessels from a retinal fundus image. From the
input fundus image, the model must be able to extract all the blood vessels using segmentation
and morphological operations. Proposed method is divided into three parts. First, we take the
input and preprocess the input image. Then, the preprocessed image is used to extract the blood
vessels using segmentation algorithm. After this, we use morphological operations as the
postprocessing step to remove the noise and false blood vessels.

1.4. Literature Survey

Many different algorithms were deployed for vessels segmentation, which achieved various
results and performances. Fraz, Rudnicka and Barman [5] introduced supervised method. Dual
Gaussian is used; a collection of second derivative of Gaussian and Gabor filters, feature vector
is generated using some morphological transformation. This feature vector gives information
which helping on handling the normal vessels and the vessels with the central reflex. The
proposed system achieved accuracy, sensitivity and specificity of 0.96, 0.74 and 0.98,
respectively. A supervised method, Yin and Bourennane [6] introduced, they used this method
for vessel segmentation taking into account vessel edge detection on the retinal image. To detect
vessel edge points in this method, they with maximum a posteriori (MAP) as criterion. This
method achieves sensitivity and specificity 0.7248 and 0.9666, respectively on DRIVE.

Another method is morphological processing which consist of techniques [7] dealing with
digital image processing using mathematical morphology by applying some structure element
(SE) to binary images and sometimes to gray-level images. Roychowdhury, Koozekanani and
Parhi developed a novel three-stage blood vessel segmentation algorithm. The first stage is pre-
processing by high-pass filtering then extracting a binary image and another binary image is
reconstructed from morphologically enhanced image for the vessel regions. Next the major
vessels are extracted which is common regions from these two images. Then the second stage,
Gaussian Mixture Model (GMM) classifier is used to classify all pixels in the two binary images
which are remained from previous stage. Set of 8 features are used in GMM which extracted
depending on first and second order gradient images and pixel neighbourhood. Finally, the last
stage, both the vessels and the classified vessel pixels are combined. This method with accuracy
of 0.952 on the DRIVE.

Marin [8] performed a neural network scheme for pixel classification; 7-D vector was
computed. For training and classification, they used multi-layer feed forward neural network.
There are five main layers, the first one is the input layer which consists of seven neurons, and
the second three layers are the hidden layers consisting of fifteen neurons, finally the output
layer which has one neuron. This method has average accuracy, sensitivity and specificity on
the DRIVE database 0.9452, 0.7067 and 0.9801, respectively.

Morphological multi-scale enhancement method is also presented in [9]. For the extraction of
the blood vessels in the angiogram; fuzzy filter and watershed transformation are used. Multi-
scale non-linear morphology opening operators with structuring element which vary in size is
used to estimate the background, and then the background is subtracted from the image to

Department of Information Technology P a g e 6 | 19

 St. Thomas’ College of Engineering and Technology

achieve the contrast normalization. A combined fuzzy morphological operation is applied on

the normalized angiogram with twelve linear structuring elements with nine pixels length; the
structuring element rotated every 150◦ between zero and 180◦. Thresholding the filtered image
to obtain the vessel region, then for approximating the vessels centerlines, thinning operation
is applied. Finally, watershed techniques are applied on vessel centerline to detect the vessel
boundaries.

In [10] an approach is presented which is combined unique vessel centerline detection with
morphological bit plane slicing. The first order derivative of a Gaussian filter is used in four
directions to extract the centerlines, and then performing an average derivative and derivative
signs with the extracted centerlines. Mathematical morphology has proven their worth as a
brilliant technique for the blood vessels segmentation in the retina. Morphological
multidirectional top-hat operation is applied on blood vessels gray-scale image with linear
structure element to obtain the orientation map and shape, and then the enhanced vessels are
subject to bit plane slicing. For obtaining the vessel tree, these maps are combined with the
centerlines. This method has average accuracy, sensitivity and specificity on the DRIVE
database 0.943, 0.715, 0.977, respectively.

In [11] fast discrete curvelet transform with multi-structure mathematical morphology is

proposed. For contrast enhancement, FDCT is performed. For detecting the blood vessels
edges, multi-structure morphological transformation is applied. Then morphological opening is
applied on the result image to remove the false edges. Finally, for obtaining the complete final
vascular tree, a connected adaptive component analysis is applied. This method has average
accuracy, sensitivity and specificity on the DRIVE database 0.946, 0.735, 0.979, respectively.

An automated enhancement and segmentation method for blood vessels is presented in [12].
This method decreases the optic disc influence and emphasizes the vessels by applying a
morphological multidirectional top-hat transform with rotating structuring elements to the
background of the retinal image. For producing a vessel response image and the final blood
vessel tree, an improved multi-scale line detector is applied. As line detectors in the multiscale
detector have different line responses, the longer line detectors produce more vessel responses
than the shorter line detectors. To set different weights for different scales, all the responses are
combined by the improved multi-scale detector at different scales. This method has average
accuracy, sensitivity and specificity on the DRIVE database 0.942, 0.735, 0.969, respectively.

Most of these approaches have their advantages and disadvantages, which distinguish it from
other. A complete extraction of the vascular tree in the digital retinal image can be provided
since all the possible vessel pixels have been searched across the whole image. However special
hardware is required to be more suitable for large image dataset for these techniques which are
computationally expensive. In some approaches a significant degradation in the performance is
caused because of noise and lesions so to pick up this noise we perform the enhancement
operation. In our approach we focus on the preprocessing enhancement stage which has a
perfect effect on segmentation step. We use morphological processing to enhance the digital
retinal images to get more accurate results in segmentation process.

Department of Information Technology P a g e 7 | 19

 St. Thomas’ College of Engineering and Technology

1.5. Brief discussion on problem

The method which has been proposed for the extraction of blood vessels, comprise of three
phases: pre-processing, segmentation and post-processing. The green channel of the RGB
image undergo different phases, for the purpose of vessel extraction. The green channel has
most light in it whereas the red and the blue channel suffer from poor illuminance. There are
twice as many green pixels in digital cameras as red or blue pixels, is also the reason why the
green channel will have less noise than the red or the blue channel. The green channel of the
RGB image is then converted into grayscale image. Contrast Limited Adaptive Histogram
Equalization (CLAHE) is applied on the greyscale image to improve the contrast of the image
by limiting the amplification of the image. The median filter is a non-linear digital filtering
technique which is often used to eliminate noise. It is applied on the contrast enhanced image
to eliminate the salt and pepper noise and to smooth the image. Then the image is segmented
using mean-C thresholding. At this stage the output image consists of some non-vessel which
are removed with the help of morphological cleaning operation.

1.5.1. Flow Diagram

Given below is the flow diagram of the model that we have proposed. These are the
sequential steps that we have included to build the model that will extract blood vessel
features from the retinal fundus image.

Fig 1. Flow/Sequence of execution

Department of Information Technology P a g e 8 | 19

 St. Thomas’ College of Engineering and Technology

1.6. Gantt Chart

Fig 2. Gantt chart from September to November’2019

2. Concept and Problem Analysis

In this section of the report we have documented the fundamental concepts regarding the different
steps involved in this model. We have provided the different requirements for this this project be
it mathematical, algorithmic, hardware or software. Furthermore, we have presented the
performance with diagrammatic representation during the different stages of the model.

2.1. Functional Requirement

This sub-section mentions the different functional requirements for the proposed model, this
section details the major functions used in building this model and the dataset used for
validation and testing.

2.1.1. Datasets, comprising both raw fundus images and hand-drawn retinal blood
vessel output image must be created. Different datasets have been used for the
purpose of running tests to determine the values for the thresholding algorithm
and to determine the effectiveness of this proposed method. Here we have used
the DRIVE (Digital Retinal Images for Vessel Extraction) [17] database. It is
available and public database, containing 40 color funds digital images about
population having subjects ranging between 31 and 86 years old. These digital
images were taken by a Canon CR5 non-mydriatic 3CCD camera at 45 field of
view (FOV). Each image is 768 * 584 pixels. The database contains [7] two
main sets, test and training both of each containing 20 digital images. Three
observers, the first and second author and a computer science student manually

Department of Information Technology P a g e 9 | 19

 St. Thomas’ College of Engineering and Technology

segmented a number of images. All observers were trained by an experienced

ophthalmologist (the last author). The first observer segmented 14 images of
the train set while the second observer segmented the other 6 images. The test
set was segmented twice resulting in a set X and Y. Set X was segmented by
both the first and second observer (13 and 7 images respectively) while set Y
was completely segmented by the third observer. The performance of the
vessel segmentation algorithms is measured on the test set. In set X the
observers marked 577,649 pixels as vessel and 3,960,494 as background (12.7
% vessel). In set Y 556,532 pixels are marked as vessel and 3,981,611 as
background (12.3 % vessel).

2.1.2. CLAHE(Contrast limited adaptive histogram equalization), splits the entire

space into a number of tiny sections of identical size and operates on each
region where the contrast of each small region is increased so that the
histogram of the output image corresponds to the histogram indicated by the
distribution parameter. The small neighboring regions are then combined
using bilinear interpolation which suppress the artificially induced limits. Over
noise amplification can be avoided by limiting the contrast of the individual
homogeneous region. Fig. 1 (c) represents the CLAHE enhanced image.
Ordinary AHE (adaptive histogram equalization) tends to overamplify the
contrast in near-constant regions of the image, since the histogram in such
regions is highly concentrated. As a result, AHE may cause noise to be
amplified in near-constant regions. Contrast Limited AHE (CLAHE) is a
variant of adaptive histogram equalization in which the contrast amplification
is limited, so as to reduce this problem of noise amplification.
In CLAHE, the contrast amplification in the vicinity of a given pixel value is
given by the slope of the transformation function. This is proportional to the
slope of the neighbourhood cumulative distribution function (CDF) and
therefore to the value of the histogram at that pixel value. CLAHE limits the
amplification by clipping the histogram at a predefined value before computing
the CDF. This limits the slope of the CDF and therefore of the transformation
function. The value at which the histogram is clipped, the so-called clip limit,
depends on the normalization of the histogram and thereby on the size of the
neighbourhood region. Common values limit the resulting amplification to
between 3 and 4.

Fig. 3. Clipping the peak of the histogram to spread it evenly

It is advantageous not to discard the part of the histogram that exceeds the clip
limit but to redistribute it equally among all histogram bins. The redistribution
will push some bins over the clip limit again (region shaded green in the

Department of Information Technology P a g e 10 | 19

 St. Thomas’ College of Engineering and Technology

figure), resulting in an effective clip limit that is larger than the prescribed limit
and the exact value of which depends on the image. If this is undesirable, the
redistribution procedure can be repeated recursively until the excess is
negligible.

2.1.3. Median Filter, the median filter is a non-linear digital filtering technique,
often used to eliminate noise. This noise reduction is a distinct pretreatment
footstep to upturn the properties of future treatments. The median filter is cast-
off to eradicate salt and pepper noise, to smooth the image. Neighbourhood
averaging can suppress isolated out-of-range noise, but the side effect is that it
also blurs sudden changes such as line features, sharp edges, and other image
details all corresponding to high spatial frequency. The median filter is an
effective method that can, to some extent, distinguish out-of-range isolated
noise from legitimate image features such as edges and lines.

Specifically, the median filter replaces a pixel by the median, instead of the
average, of all pixels in a neighborhood where represents a neighbourhood
defined by the user, centred around location [m,n] in the image.

2.1.4. Adaptive Gaussian Thresholding, the black-and-white image is generated

from grayscale image by setting the pixels to white whose value is beyond a
certain threshold, setting the other pixels to black. Here, adaptive gaussian
thresholding technique is taken where a threshold is calculated for each pixel
in the image based on some local statistics such as mean, median of the
neighborhood pixels and threshold is updated each time. The main advantage
of this thresholding method is that it is applicable in case of badly illuminated
images [20]. In adaptive gaussian thresholding (where C is a constant), for
extraction of blood vessels the pixels lies in a uniform neighborhood are set to
background value. The adaptive gaussian thresholding can be carried out as
follows:

a. A mean filter of window size N × N is selected.

b. The enhanced image is convolved with the weighted mean.
c. A difference image is obtained by subtracting the convolved image from
enhanced image.
d. The difference image is thresholded with the constant value C.
e. The complement of the thresholded image is calculated.

Two experiments are conducted to determine the values of constant C and

window size. This has been discussed under section 2.2.

Department of Information Technology P a g e 11 | 19

 St. Thomas’ College of Engineering and Technology

2.1.5. Morphological Operations, Mathematical morphology extracts components

of image which are useful for representing and describing the region shape
such as boundaries, skeletons and the convex hull. Mathematical morphology
is considered as powerful tool which solving many problems in image
processing and computer vision. Erosion, dilation, closing and top- hat
transformation are the basic morphological operations which are used to detect,
modify and manipulate the features presented in the image based on their
shapes [13]. Mathematical morphology is a series of morphological algebraic
arithmetic operators. Structuring element (SE) is applied by morphological
operators typically to binary images and sometimes can be extended to gray-
level images. Selecting the proper structure element for our application; its
shape and size is an important step in Strengthening or weakening the results.
A structuring element can be any size and take any shape and has origin point.
Expanding the objects by a specific structuring element is called dilation,
filling holes, and connecting the disjoint regions, dilation of image A by
structuring element B is denoted by A ^ B. The structuring element B is
positioned with its origin at (x, y) and the new pixel value is determined using
rule 1:

or in set language as shown in rule 2:

In contrast the erosion operation which shrinks the objects by a structuring

element, erosion of image A by structuring element B is denoted by A (-) B .
The structuring element B is positioned with its origin at (x, y) and the new
pixel value is determined using in rule 3:

Other morphological operations can be applied by performing a series of

erosions and dilations, these operations called compound operations, the most
widely used of these compound operations are opening and closing.
The opening of image A by structuring element B is denoted by A*B is simply
erosion followed by dilation as shown in rule 5 and rule 6.

Department of Information Technology P a g e 12 | 19

 St. Thomas’ College of Engineering and Technology

2.2. Experiments
In this section we have mentioned the different experiments we have conducted in order to
determine the value of the window size and the bias value (C) for the thresholding algorithm.
The window size and the bias value determines how well the retinal fundus image will be
thresholded.

Experiment 1: To determine the value of C

In the first experiment, for selection of C, a series of values from 0.03 to 0.05
with a variation of 0.002 are taken. For every value of C, accuracy is calculated
and plotted against different values of C. This is shown in Fig. 2. From the
graph, it can be observed that the accuracy value increases till the value of
C = 0.042 and then begins to decrease. Therefore, in order to get a better result
with maximum accuracy, the optimum value of C is taken as
0.042. Fig. 4 depicts the output images with different values of C.
From Fig. 3 (a), it can observed that at C = 0.03 the output image includes
vessels with unwanted spurious noise. At C = 0.042 the output image extract
vessels with maximum accuracies 0.9629 as shown in Fig. 3 (b). For higher
value of C = 0.05 less vessels are identified which is shown in Fig. 3 (c).

Fig. 4. Variation of accuracy with respect to constant (C)

Fig. 5. Segmented image at different values of C (a) C = 0.03, (b) C = 0.042

and (c) C = 0.05.

Department of Information Technology P a g e 13 | 19

 St. Thomas’ College of Engineering and Technology

Experiment 2: To determine the value of window size

In the second experiment, by increasing the window sizes, the unnecessary

black pixels are removed from the image background in a better way with
filling out characters and vice versa. For selection of window size different
sizes from 3 × 3 to 19 × 19 are taken and calculated the accuracies. The
accuracy starts increasing from window size 3 × 3 to 13 × 13 and after 13 × 13
it starts decreasing. So, as at window size 13 × 13 maximum accuracy is
obtained, the optimum window size is considered as 13 × 13. The variation of
accuracy with respect to different window sizes is shown in Fig. 4.

Fig. 6. Variation of accuracy with respect to window size (W)

2.3. Performance

We have not yet performed this step; we are yet to validate the efficiency and accuracy of
this approach. Efficiency or accuracy of the model for each analysis method is analysed
by error rate. This error rate is defined by the terms normal and abnormal right and normal
and abnormal wrong as follows:
1) Abnormal Right (AR): The test gives positive result if extracted vessel is present.
2) Normal Right (NR): The test gives negative result if extracted vessel is absent.
3) Normal Wrong (NW): The test gives positive, but blood vessel is absent.
4) Abnormal Wrong (AW): The test gives negative, but blood vessel is present.
Sensitivity, specificity and accuracy are used to describe the clinical efficiency of the
proposed model.

These are the output of the different stages of the model that we have implemented so far:
A) Raw input fundus image

Department of Information Technology P a g e 14 | 19

 St. Thomas’ College of Engineering and Technology

B) Pre-processed image
C) Thresholded image
D) Post-processed image

Fig. 7. Raw fundus image; Input to the model; stage A (Ordered by: L-R, Top-Bottom)

Department of Information Technology P a g e 15 | 19

 St. Thomas’ College of Engineering and Technology

Fig. 8. Pre-processed image; stage B (Ordered by: L-R, Top-Bottom)

Fig. 9. Thresholded output containing noise; stage C (Ordered by: L-R, Top-Bottom)

Department of Information Technology P a g e 16 | 19

 St. Thomas’ College of Engineering and Technology

Fig. 10. Final image after applying morphological cleaning operations; Output of the model; stage D
(Ordered by: L-R, Top-Bottom)

2.4. Platform Used

This project has been implemented using open source software and libraries, here we have
used Python for the scripting and libraries such as OpenCV, pandas, Scikit, matplotlib etc.
The model can be run in any machine containing Python 3.5 or above interpreter and the
above-mentioned libraries.

Hardware specification:
 x64 architecture
 Windows 10
 8 GB RAM

3. Conclusion
In this paper, we have proposed a method based on local adaptive thresholding for extraction of
retinal vessels. The main contribution of the paper is the application of mean-C thresholding for
retinal blood vessels extraction. This automated method can segment retinal blood vessels
effectively. At the same time, the proposed method is very time efficient as it can complete the
process within a very small execution time. Together the efficacy and strength with its easiness

Department of Information Technology P a g e 17 | 19

 St. Thomas’ College of Engineering and Technology

and fast employment make the offered method a pertinent implementation for being unified into a
comprehensive pre-screening scheme for early identification of ophthalmological disorders.

Although further scope is there to improve the output by tuning the morphological operations for
noise removal of the thresholded output. The performance evaluation is yet to be done.

4. Future Scope
In this project we can improve the blood vessel detection by improving the output. The main
problem in the current state of this project is that the thresholded output produces a very good
blood vessel extract but with a lot of false positives. Thus, by improving the post-processing stage
of the model we can provide a cleaner and more accurate output. The morphological cleaning
operation can further be improved to give a better output.

5. Bibliography

[1] R. Udayakumar,V. Khanaa,T. Saravanan and G. Saritha,“Retinal Image Analysis Using

Curvelet Transform and Multistructure Elements Morphology by Reconstruction”, Middle-
East Journal of Scientific Research, vol. 12,no.12, PP. 1668-1671, (2013).
[2] Y.Yang,S. Huang and N.RAO,“An automatic hybrid method for retinal blood vessel
extraction”, International Journal of Applied Mathematics and Computer Science, vol. 18,no.3,
PP. 399-407, (2008).
[3] A. Salazar-Gonzalez, D.l Kaba, Y. Li and X. Liu, “Segmen- tation of Blood Vessels and Optic
Disc in Retinal Images,” in IEEE Journal of Biomedical and Health Informatics, pp. 2168-2194,
(2014).
[4] M. M. Fraz, P. Remagnino and A. Hoppe et al, “Blood vessel segmentation methodologies in
retinal imagesa survey,” in Computer Methods and Programs in Biomedicine,vol. 108 pp. 407433,
(2012).
[5] M. Moazam Fraz, Alicja R. Rudnicka,Christopher G. Owen and Sarah A. Barman,
“Delineation of blood vessels in pediatric retinal images using decision trees-based ensemble
classification, ” in International journal of computer assisted radiology and surgery, pp. 1-17,
(2013).
[6] Y. Yin, M. Adel, and S. Bourennane, “Automatic Segmen- tation and Measurement of
Vasculature in Retinal Fundus Images Using Probabilistic Formulation,” in Computational and
mathematical methods in medicinel,Hindawi Publishing Corporation Computational and
Mathematical Methods in Medicine ,vol.2013, pp. 16, (2013).
[7] S. Roychowdhury, D. D. Koozekanani , Keshab K and Parhi, “Blood Vessel Segmentation of
Fundus Images by Major Vessel Extraction and Sub-Image Classification, ” in Biomed- ical and
Health Informatics, IEEE Journal, pp. 2168-2194, (2014).
[8] D. Marn, A. Aquino*, M. Emilio Gegndez-Arias and J. Manuel Bravo, “A new supervised
method for blood vessel segmentation in retinal images by using gray-level and mo- ment
invariants-based features, ” in Medical Imaging, IEEE Transactions onl,vol.30,no.1, pp. 146-158,
(2011).

Department of Information Technology P a g e 18 | 19

 St. Thomas’ College of Engineering and Technology

[9] K. Sun, Z. Chen, S. Jiang, and Y. Wang, “Morphological multiscale enhancement, fuzzy filter
and watershed for vascu- lar tree extraction in angiogram,” Journal of medical systems,” in Journal
of medical systems, vol.35, pp. 811-824, (2011).
[10] M.S. Miri and A. Mahloojifar, “An approach to localize the retinal blood vessels using bit
planes and center- line detection,” in Computer methods and programs in biomedicine, vol.108,
pp. 600-616, (2012).
[11] M.M. Fraz et al., “Retinal image analysis using curvelet transform and multistructure
elements morphology by recon- struction,” in Biomedical Engineering, IEEE Transactions on,
vol.58, pp. 1183-1192, (2011).
[12] Y. Hou, “Automatic Segmentation of Retinal Blood Vessels Based on Improved Multiscale
Line Detection,” in Journal of Computing Science and Engineering, vol.8, pp. 119-128, (2014).
[13] Mukhopadhyay, Susanta and Chanda, Bhabatosh, “Multiscale morphological segmentation
of gray-scale images,” Image Processing, IEEE Transactions on, vol. 12, no. 5, pp. ,533- 549
(2003).
[14] M.M. Fraz, P. Remagnino, A. Hoppea, B. Uyyanonvarab, A.R. Rudnicka ,C.G. Owen,
S.A. Barman, “Blood vessel segmentation methodologies in retinal images–A survey, ”
Computer methods and programs in biomedicine, vol. 108, no. 1, pp. 407-433, (2012).
[15] S.Tatiraju,A. Mehta “Image Segmentation using k-means clustering, EM and Normalized
Cuts, ” in Department of EECS, vol. 1, pp. 17, (2008).
[16] Chinki Chandhok,Soni Chaturvedi andA.A Khurshid, “An Approach to Image Segmentation
using K-means Clustering Algorithm, ” in International Journal of Information Tech- nology
(IJIT),vol. 1, (2012).
[17] M. Niemeijer, J.J. Staal, B.v. Ginneken, M. Loog, M.D. Abramoff, DRIVE: digital retinal
images for vessel extrac- tion, http://www.isi.uu.nl/Research/Databases/DRIVE, accessed (2014).

Department of Information Technology P a g e 19 | 19