International Journal of Advances in Engineering, 2015, 1(8), 622 - 625
ISSN: 2394-9260 (printed version); ISSN: 2394-9279 (online version); url:http://www.ijae.in
RESEARCH ARTICLE
Detection and Counting of Red Blood Cells using Hough Transform
Technique
Karthikeyan. K and K. Brharama Neelima
Department of Electronics and Telecommunication, Bharath University, India
[email protected]
Received 16 July 2015 / Accepted 17 August 2015
Abstract— Counting of red blood cells (RBC) in blood cell images is very important to detect as well as to follow the process of
treatment of many diseases like anemia, leukemia etc. To accurately identify fetal RBCs from maternal RBCs, multiple features
including cell size, roundness, gradient, and saturation difference between cell and whole slide are used in supervised learning to
generate feature vectors, to tackle cell color, shape, and contrast variations. A large number of medical images in digital format are
generated by hospitals and medical institutions every day. Consequently, how to make use of this huge amount of images effectively
becomes a challenging problem. In the field of biomedicine, because of cell’s complex nature, it still remains a challenging task to
segment cells from its background and count them automatically Content-based image indexing and retrieval has been an important
research area in computer science for the last few decades. Many digital images are being captured and stored such as medical
images, architectural, advertising, design and fashion images, etc. As a result large image databases are being created and being used
in many applications. In this work, the focus of our study is on medical images However, locating, identifying and counting of red
blood cells manually are tedious and time-consuming that could be simplified by means of automatic analysis, in which segmentation
is a crucial step. In this paper, we present an approach to automatic segmentation and counting of red blood cells in microscopic
blood cell images using Hough Transform.
Keywords : Image Processing , Detection, Red Blood Cell, Counting, Hough Transform.
I. INTRODUCTION
The blood consists of a suspension of special cells in a liquid called plasma.Blood consists of 55 % plasma, and 45 % by
cells called formed elements. The blood performs a lot of important functions. By means of the hemoglobincontained in the
erythrocytes, it carries oxygen to the tissues and collects the carbondioxide (CO2). It also conveys nutritive substances (e.g.
amino acids, sugars,mineral salts). Any problem to the physiological system directly affects the bloodcomponents. The
analysis of individual blood components gives a valuableinformation about the status of the physiological system and helps
in diagnosis ofvarious disorders. The erythrocytes are the most numerous blood cells in the human body, and it also called
redblood cells. The red blood is a blood that functioned as carry oxygen throughout our body. An RBC count is a blood test
performed by a healthcare practitioner at your doctor’s office. Blood will be drawn from a vein. The blood sample will be
sent to a laboratory for analysis. The analysis will do with the help of some chemicals manually and it takes minimum of 2
days to identify the result. The patients have to wait until the result came and has to visit the doctor again. In the proposed
system, the RBC is counted automatically using image processing technique. Consumes less time. Result will be produced
at the spot itself. Low cost of implementation, Based on the count diseases can be easily identified.
Figure.1 Illustration view of Blood Cell
623
Int. J. Adv. Eng., 2015, 1(8), 622-625
II. WORKING FUNCTION OF PROPOSED SYSTEM
The blood sample is placed below the camera; the light is placed under the sample. To loosen the blood sample density, the
liquid is mixed with the blood and then placed under the camera. The image is captured by the camera and it is send as
input to the matlab process. The RBC cells are segmented separately using the Hough transform algorithm. The features of
the sample are extracted and the RBCs are found based on the features. The total number of RBCs is counted and according
to the value, the disease is identified.
Figure.2 Proposed System
Detection and Counting of Fetal RBC through Hough Transform : To count the total number of red blood cells in a
microscopic image of bloodsmear using matlab. To detect and count the number of abnormal cells in the given
microscopicimage of blood smear using matlab.
Figure.3 Input images
The red blood cells are also more or less similar to the circular objects seen in the figure . When it is possible to detect those
circular objects, it is also possible to detect the red blood cells. Once detection is complete ,the number of cells can be
counted easily. This function has the ability to detect even the overlapped cells. while browsing the image processing
toolbox in matlab an example called “Identifying Round Objects” can be observed. This particular example explained steps
involved in detecting round objects in an image based on form factor. It perfectly detected round objects in the following
image. The form factor for a perfectly round object is one. For all objects it is less than or greater than one.
Figure.4 Output images -1
624
Int. J. Adv. Eng., 2015, 1(8), 622-625
Figure.5 Output images -2
Having successfully isolated the red blood cells we have applied a counter that has counted the number of rbcs in the image
field . However, blood count in medical terms means the number of blood cells (rbc or wbc or platelets) in a cubic
millimeter of blood volume. Hence we have deduced a formula to calculate the number of red blood cells per cumm based
on the number of cells in the area of the given image of the blood sample. We have assumed that the thickness of the blood
sample film is 0.1 mm which is the standard medical practice. This allows for an overlapping of maximum two layers in
thickness which is the common trend in the images provided. This formula requires an input for providing the
magnification factor which is the magnification level under the microscope at which the image has been taken. We have
taken 2 blood cell images for our study. Each of the images are pre-processed by the above mentioned techniques. Finally
the number of red blood cells were identified and counted in each of these images using Hough Transform. The results of
our study have been discussed in Table - 1 along with the different parameters used for each of the images.
III. RESULTS
Comparison of the Result between the proposed method and the manual method: It is observed that the results obtained by
the proposed method offer a good conformity with the manual counting method. In our method, we have left out the cells
that are not totally in the image field. However, in a real blood test where blood count is done manually, the practice is to
count the cells on two adjacent edges of the image field and take each cell as one irrespective of how much of it is in the
image field. It is assumed that two opposite sides have same number of such cells. As this edge correction has not been
considered, in each of the samples the count values by the proposed method are slightly less than the count values obtained
manually. The software must be modified to count those rbcs to obtain more accurate result.
Table. I proposed method vs manual method
Image
Sample
1
2
Interate
Count
83
56
Blood Counted
Manualy
84
56
Fetal RBC count
Manually
2
49
Fetal Counted
Methodically by System
2
47
The results are presented and the graphical user interface (GUI) is developed to provide userfriendly for analysis. This GUI
was developed using GUIDE (Graphical User Interface Development Environment) which is one of the tools that have
been provided in the MATLAB
.
Figure.6 Final result
625
Int. J. Adv. Eng., 2015, 1(8), 622-625
CONCLUSION
As a conclusion, this research successfully utilizes morphological approached for segmentation,extraction and estimation in
order to solve problem in image processing of the red blood cells. The results of the image can be used as good input in
determining the number of red blood cellsby using Hough transform technique. By using the MATLAB, all the
importance’s aspects like correct algorithm and system has been successfully produced. With correct algorithm, the red
blood cells can be detected and segmented as well as estimated the number of the red blood cells. Through system created
using MATLAB, it also enable the study of the morphological features of the red blood cells image, thus, can determine
whether the person is normal or otherwise by referring amount of red blood cells in human blood. This technique does not
involve too much looping process when develops the MATLAB source code program. One of the issues that need to be
considered to improve this study is to reduce the time taken by the user determine the red blood cells parameters.
ACKNOWLEDGEMENT
I would like to thank esteem Bharath University-R&D Students Potential Division of Electronics and Telecommunication
Engineering Research lab mentor Dr. M. Poonavaika and Director of Computing and Communicatiion Network Research
lab
REFERENCES
1.
2.
3.
4.
5.
Heidi Berge, Dale Taylor, Sriram Krishnan, and Tania S. Douglas. Improved Red Blood Cell Counting in thin Blood Smears. Proceedings of
ISBI, 2011. pp.204-207.
Ramin Soltanzadeh. “Classification of Three Types of Red Blood Cells in Peripheral Blood Smear Based on Morphology. Proceedings of
ICSP, 2010.
O. Barinova, V.Lempitsky and P. Kohli, : On the detection of multiple object instances using Hough Transforms , CVPR, (2010).
K. R. Zalik and B. Zalik, “Validity index for clusters of different sizes and densities,” Pattern Recognit. Lett., vol. 32, no. 2, pp. 221–234, Jan.
2011.
Karthikeyan K, Pankaj Kumar , Mrs.K. Brharama Neelima on Counting and detection of fetel RBC using Hough Transform Technique(2015)