Segmentation and Automatic Counting of Red Blood Cells Using Hough Transform

ISSN (ONLINE): 2395-695X
ISSN (PRINT): 2395-695X
International Journal of Advanced Research in Basic Engineering Sciences and Technology (IJARBEST)
Vol. 2, Issue 12, December 2016
V. Antony Asir Daniel et al. © IJARBEST PUBLICATIONS
Segmentation and Automatic Counting of Red Blood
Cells Using Hough Transform
V. Antony Asir Daniel1
, J. Surendiran2
, K. Kalaiselvi3
Assistant Professor, Francis Xavier Engineering College, Tirunelveli 1
Associate Professor, Francis Xavier Engineering College, Tirunelveli 2
PG Scholar, Communication Systems, Francis Xavier Engineering College, Tirunelveli 3
Abstract- Red blood cells are specialized as oxygen carrier RBC plays a crucial role in
medical diagnosis and pathological study. The blood samples are collected using the smear
glass slide. These samples are taken under the test using the image of the blood. Filtering
process are carries out to remove the noise. Morphological operation are applied on the
blood image and using Hough transform method the RBC are counted which is the
effective segmentation process.
Index Terms— RBC, blood samples, segmentation
I. INTRODUCTION
Red blood cells RBC also called erythrocytes, are the most common type of blood cell and
the vertebrate organism’s principal means of delivering oxygen to the body tissues. The
cytoplasm of erythrocytes is rich in hemoglobin, an iron-containing bio molecule that can bind
oxygen and is responsible for the red color of the cells. In humans, mature red blood cells are
flexible and oval biconcave disks. They lack a cell nucleus and most organelles, in order to
accommodate maximum space for hemoglobin. Approximately 2.4 million new erythrocytes are
produced per second.
The cells develop in the bone marrow and circulate for about 100-120 days in the body before
their components are recycled by macrophages. Each circulation takes about 20 seconds. .
Approximately a quarter of the cells in the human body are red blood cells. The red blood cells
are functioned to carry oxygen throughout our body. In health, the red blood cells vary relatively
little in size and shape. In well-spread, dried and stained films the great majority of cells have
round, smooth contours and diameters within the comparatively narrow range of 6.08.5m.
Counting of red blood cells in a blood sample can give the pathologists valuable information
regarding various hematological disorders. In the classical method for diagnosis of red blood
examination in a blood sample, it is counted by manpower; hence it has deficiencies such as poor
reliability, low efficiency and strong subjectivity. The diagnosis is the process of finding out
what kind of disease a certain patient has and those diagnosed must always be accurate. A wrong
diagnosis may lead the situation and condition of a patient become worst and some case, patient
dies due to wrong dosage of drugs given. In order to overcome that weakness, some researchers
33

have done some useful works especially in classifying blood cells from other cells, for example,
classifying white blood cells from other cells such as red blood cells and platelets. Anemia
Sickle-cell Thalassemia Spherocytosis pernicious anemia are the blood diseases
A complete blood count (CBC), also known as full blood count (FBC) or full blood exam
(FBE) or blood panel, is a test panel requested by a doctor or other medical professional that
gives information about the cells in a patient’s blood. A scientist or lab technician performs the
requested testing and provides the requesting medical professional with the results of the CBC.
The cells that circulate in the bloodstream are generally divided into three types: white blood
cells (leukocytes), red blood cells (erythrocytes), and platelets (thrombocytes).
Most of the researchers have concentrated on the classification of white blood cells since
most of the diseases are easy to determine by analyzing the change in white blood cells.
However, by counting the red blood cells, it also provides some information about the abnormal
condition in our body. Analysis of microscopic images is used in many fields of technology and
medicine. In some medical experiments, some drugs, with known effects in red blood cells
membranes, are used to find out their activity.
II. SYSTEM MODEL
A normal blood cell is primarily one of two major particles: a RBC with a normal
Probability Distribution Function (PDF) around 6.08.5 m or a WBC (7-18 m) which includes a
nucleus and cytoplasm is about 1-3 times bigger than normal and mature RBCs. Morphological
closing on the image we have an image with some broken edges and filled cells. We remove the
broken edges from the image so that we are left with the filled cells only.
Fig.1 Smear Glass
34

INPUT IMAGE
PRE
PROCESSING
FILTER
EDGE DETECTION
MORPHOLOGICAL
OPERATIIONS
RBC COUNT
III. PROPOSED METHOD
Now the actual size extraction algorithm starts. some cells whose edge is not completely detected
are left out. This happens because the imfill function fills the regions which are bounded
completely, without a gap of even a single pixel. To count such cells we apply the Circular
Hough transform on the edges of the remaining cells.A single blood smear image can be
processed multiple times for various detections of blood components unlike an original blood
sample. the aim of this project and related work is to automate the process of red blood cell
counting, develop and validate the necessary image processing steps to quantify and count
peripheral blood particles on blood smear slides, ease the working of the pathologist, to help the
doctor make a better diagnosis.
Hough Transform Method
The Hough transform is a feature extraction technique used in image analysis, computer
vision, and digital image processing. The purpose of the technique is to find imperfect instances
of objects within a certain class of shapes by a voting procedure. Mitigate problems posed by
different conditions such as noisy and degraded images, differing blood staining techniques,
various types of microscope illumination, overlapping and adjacent cells, to get an efficient
result,
to get an accurate result to find reasons that are not completely clear, a greater number of
errors tends to occur at the boundaries of the input domain rather than in the ”center.”.
Fig 2.Flow chart for counting red blood cells
35

Circle Detection Process
The process of identifying possible circular objects in Hough space is relatively simple,
First we create our accumulator space which is made up of a cell for each pixel, initially Each of
these will be set to 0. For each (edge point in image( i, j): Search for the local maxima cells,
these are any cells whose value is greater than every other cell in its neighborhood. These cells
are the one with the highest probability of being the location of the circle(s) we are trying to
locate.
The problems we will know the radius of the circle we are trying to locate beforehand,
however if this is not the case we can use a 3 dimensional accumulator space, this is much more
computationally expensive. This method can also detect circles that are partially outside of the
accumulator space if enough of its area is still present within it. The Hough transform can be
used to determine the parameters of a circle when a number of points that fall on the perimeter
are known.
IV. RESULT AND DISCUSSION
The counting and detection of red blood cells are done here by using Hough transform
method by Matlab program. A count for the WBC can also be conducted after thorough research.
Further, classification of the different types of WBC present in the blood can be done by using
various image processing techniques. Using the morphology various diseases that affect the
shape and size of the cells can be detected by examining the cells for the particular variation. For
example, certain red blood cells of a patient affected by anemia turn to sickle shape. On
examining the blood smear of a patient suspected of anemia, the sickle shaped cells can be
detected by edge detection techniques and then be counted. The RBC count only helps in partial
diagnosis of blood, the counting of white blood cells will improve it further.
Applications
It is applicable for Pregnancy tests Dengue fever tests Anemia Differential counts.
Advantages
More effective than manual count Reliable and reproducible. Efficient and cost effective
(it can sample 120-150 samples per hour).Easy to distinguish tiny clumps of platelets and
36

nucleated red blood cells. The automated hematology analyzers also may produce cell counts
which are falsely increased or decreased.
Limitations
Large or unidentifiable atypical cells, toxic immature neutrophils, and markedly
reactive lymphocytes can also be misclassified. Reactive lymphocytes can also be misclassified
Here are the outputs which show the segmented image which are undergone for the RBC
COUNT
Fig 3. Gray Scale Image
Fig 4. Dilated Gradient Mask
37

Fig 5. Cleared boarder image
Fig 6. Isolated red blood cells
Fig 7. Outlined original image
38

Fig 8. Histogram graph
V. CONCLUSION
As a conclusion, this research successfully uses various image processing techniques
for Red Blood Cell Estimation. It utilizes morphological approaches for segmentation, extraction
and estimation in order to solve problem in image processing of the red blood cells. The results
of the image act as an accurate outcome of determining the number of red blood cells by using
Hough transform technique. It proposes an image processing system that uses MATLAB
software for blood cell counting.
In future the count for the WBC can also be conducted after thorough research. Further,
classification of the different types of WBC present in the blood can be done by using various
image processing techniques. Using the morphology various diseases that affect the shape and
size of the cells can be detected by examining the cells for the particular variation. For example,
certain red blood cells of a patient affected by anemia turn to sickle shape. On examining the
blood smear of a patient suspected of anemia, the sickle shaped cells can be detected by edge
detection techniques and then be counted. The RBC count only helps in partial diagnosis of
blood the counting of white blood cells will improve it further.
REFERENCES
[1] Red Blood Cells Estimation Using Hough Transform Technique”, Signal Image Processing; Nasrul
Humaimi Mahmood and Muhammad Asraf Mansor, An International Journal (SIPIJ Vol.3,) No 2 April
2012.
[2] ”Counting of RBCs and WBCs in noisy normal blood smear microscopic images”; M.Habibzadeh, A.
Krzyak, T.Fevens, A.Sadr,Proc. of SPIE Vol. 7963 79633I-1, 05 July 2011.
[3] ”Automated Red Blood Cell Counting”;Alaa Hamouda, Ahmed Y. Khedr, and Rabie
A.Ramadan,INTERNATIONAL JOURNAL OF COMPUTING SCIENCE, VOL. 1, NO. 2, FEBRUARY,
2012.
39

[4] ”Automated morphological processing for counting the number of red blood cell”; AMT Nasution, EK
Suryaningtyas,Proceeding of the 2008 International Joint Conference in Engineering IJSE2008, Jakarta,
Indonesia, August
[5] ”A Comparison of Binarization Methods for Historical Archive Documents”;J. He, Q.D. M. Do, A. C.
Downton and J. H. Kim,Proceedings of the 2005 Eight International Conference on Document Analysis
and Recognition (ICDAR05).
[6] ”Adaptive Binarization Method for Document Image Analysis”,AlSharafMeng-Ling Feng and Yap-Peng
Tan, 2004 IEEE International Conference on Multimedia and Expo (ICME).
[7] ”Red Blood Cell Segmentation Using Masking and Watershed Algorithm”, J.M. Sharif, M. F. Miswan, M.
A. Ngadi, Md Sah Hj Salam,A Preliminary Study, 2012 International Conference on Biomedical
Engineering (ICoBE), Penang, Malaysia, 27-28 February2012
[8] ”Study and Comparison of Various Image Edge Detection Techniques”,Raman Maini Dr. Himanshu
Aggarwal,A Preliminary Study,International Journal of Image Processing(IJIP), Volume (3) : Issue (1).
[9] ”Computerized Haematology Counter”, International Journal of Medical and Clinical Research ISSN:
0976-5530 E-ISSN: 0976-5549, Volume 3, Issue 6, 2012, pp.-190-194.
[10]”Cell Splitting with High Degree of Overlapping in Peripheral Blood Smear”,Ngoc-Tung Nguyen, Anh-
Duc Duong, and Hai-Quan Vu,International Journal of Computer Theory and Engineering, Vol. 3, No. 3,
June 2011.
[11]”Digital Image Processing”,R.G. Gonzalez,2nd Edition, Prentice Hall, 2002[12] ”Getting Started With
MATLAB”,Rudra Pratap, Oxford University Press.Rizvi
40

Segmentation and Automatic Counting of Red Blood Cells Using Hough Transform

More Related Content

Viewers also liked (13)

Similar to Segmentation and Automatic Counting of Red Blood Cells Using Hough Transform (20)

More from IJARBEST JOURNAL (20)

Recently uploaded (20)

Segmentation and Automatic Counting of Red Blood Cells Using Hough Transform