IRJET- Identifying the Blood Group using Image Processing

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 03 | Mar-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 6.171 | ISO 9001:2008 Certified Journal | Page 2639
Identifying the blood group using Image Processing
Amol Dhande1, Pragati Bhoir2, Varsha Gade3
1,2,3 Computer Engineering, Yadavrao Tasgaonkar Institute of Engineering and Technology, Maharashtra, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Identifying blood group is very important in
emergency cases. The method based on image processing
technology at present is very quick and it has wide uses in
biotechnological field. In this paper, we are proposing the
accurate and fast identification of blood groupbasedonimage
processing technology. Sometimes the human eye may give us
an inaccurate result, but if we detect the blood group using
image processing technology then the small error in the
results which are calculated and given by human is reduced.
Using image processing technology, we can givethebestresult
as this technology is growing faster and faster. This method
can quickly and accurately classify the blood group.
Key Words: ABO blood group, Threshold Segmentation,
HSV, Histogram, Binary image, Clusters, Patch.
1. INTRODUCTION
Blood group identification is the key step to ensure blood
transfusion safety. In the case of emergency blood
transfusion, rapid identification of the type of blood is
essential, directly related to the survival of the patient. The
ABO blood group system is found and identified as the first
human blood group system by Austria Rand Steiner in early
nineteenth Century. Blood groupsare dividedintofourtypes
i.e. A, B, AB and O. ABO blood group detection follows the
agglutination method and then it goes for a machine
recognition. The agglutination reaction means thatoccurred
reaction between the antibody and the antigen, indicating
the presence of the antigen.
1.1 Literature Survey
Mehedi Talukder ,Md Rabiul Islam etc. all in year October
2015 on “Improvement of accuracy of human bloodgroups.”
He has suggested that, the blood group can be detected by
using image processing using plate method. This method
gives the accurate result.
Pravin manikandan, Ravindra G, etc. all in year February
2017 on “Determination and classification of blood type
using image processing techniques.” He has suggested that,
the type of blood group can be detected by using image
processing with method such asthresholding,morphological
processing, quantification, etc. It is effective and efficient
method to detect the agglutination anddeterminestheblood
type of the patient accurately.
Yue fang dong, etc. all in year 2017 on “ABO blood group
determination based on image processing technology.” He
hassuggested that, The blood group can bedetectedbyusing
image processing with method such as measurement of
linear primitives and circular primitives, color information
extraction, object segmentation based on niblack, feature
extraction, etc. A fast, accurate and robust blood group
judgment method is proposed for the rapid and accurate
identification of blood type in the case of emergency
transfusion.
1.2 Comparative Analysis
Table-1: Analysis of previous papers
Title Year
Publishe
d
Techniq-
ue’s Used
Algor
-ithm
Demerits
Improve-
ment of
accuracy
of human
blood
groups.
Oct 2015 Name plate Thre-
sholding
Requires 30
minutes
which is
excessive
especially in
emergency
situation
Determi-
nation and
classifi-
cation of
blood
types
Feb 2017 Morpholo
-gical
process-ing
Quantifi-
cation
More chances
of human
error are
possible only
experts can
tell the blood
type by seeing
at the
agglutina-tion
process.
ABO blood
group
detection
based on
image
process-
ing
techno-
logy
Feb 2017 Feature
extraction
Niblack
segment-
ation, Otsu
algori-thm
Gives accurate
result but time
consuming.
2. EXISTING SYSTEM
In today’sworld, the blood group is identified on the basisof
microscope vision. It may gives wrong result as the human
may be incorrect due to the deficiency in human beings, but
we can reduce this errors by doing the same process on the
basis of image processing at the fast speed without any
wrong interpretation.
3. PROBLEM DEFINITION
1) Improvement of accuracy of human blood group
In this system, it has disadvantage of requiring 30
minutes, which is excessive especially in emergency
situation.

2) Determination and classification of blood type using
image processing
Disadvantage of this system are more chances of human
errors are possible, only experts can tell the blood type by
seeing at the agglutination process.
3) ABO blood group detection based on image processing
technology
In this Paper, method givesaccurate result but it takes more
time to generate the result i.e. finding the blood type on the
basis of image processing techniques used in this project.
We are using some special techniques of image processing
likedetection of background and cluster detection. The final
blood group can be detected on the basis of number of
clusters and feature detection of the image. Due to this, we
get the accurate result without any expert by avoiding
human errors within short period of time. The techniques
used in our projects are morphological processing, finding
the biggest cluster using cluster detection, and background
color detection using HSV luminance method and after this,
we are going to take a decision of cluster or patch to find the
blood group of the image. We also plot the histogram just to
verify the distribution of colors in the image.
4. PROPOSED SYSTEM
The digital images of blood samplesare obtained fromthe
hospital/laboratory consisting of a color image composedof
three samples of blood. These images are processed using
image processing techniques namely feature extraction,
clustering, HSV luminance, etc.
Fig -1: Sample image for further processing
4.1 Resize the Image
In this process, we will resize the image and enhance the
quality of image by converting image into bitmap image.
Bitmap image is the type of memory organization or image
file format used to store digital image.
4.2 HSV Luminance
HSV (Hue, Saturation, and Value) are two alternative
representations of the RGB color model, designed in the
1970s by computer graphics researchers to more closely
align with the way human vision perceives color-making
attributes. In these models, colors of each hue are arranged
in a radial slice, around a central axisof neutral colorswhich
rangesfrom black at the bottom to white at the top. The HSV
representation modelsthe way paints of differentcolorsmix
together, with the saturation dimension resembling various
shades of brightly colored paint, and the value dimension
resembling the mixture of thosepaintswithvaryingamounts
of black or white paint.
Fig -2: Background color detection
4.3 Morphological Operation
Morphology is a tool of extracting image components that
are useful in the representation and description of region
shape, such as boundaries, skeletons, and the convex hull. In
morphological operation, there are two fundamental
operations such asdilation and erosion,intermsoftheunion
of an image with translated shape called a structuring
element. This is a fundamental step in extracting objects
from an image for subsequent analysis. The fundamental
operations in morphological operations can be listed as
4.3.1 Erosion
Erosion is one of the two basic operators in the area of
mathematical morphology. It is typically applied to binary
images, but there are versions that work on grayscale
images. The basic effect of the operator on a binary image is
to erode away the boundariesof regionsofforegroundpixels
(i.e. white pixels, typically). Thus areas of foreground pixels
shrink in size, and holes within those areas become larger.
4.3.2 Dilation
Dilation is the process that grows or thickens the objects in
an image and is known as structuring element. Graphically,
structuring elements can be represented either by a matrix
of 0s and 1s or as a set of foreground pixels.
4.3.3 Smooth Gaussian
The Gaussian smoothing operator is a 2-D convolution
operator that is used to `blur' images and remove detail and
noise. In this sense it is similar to the mean filter, but it uses
a different kernel that represents the shape of a Gaussian
(`bell-shaped') hump.
4.3.4 Threshold Binary
The simplest thresholding methods replace each pixel in an
image with a black pixel if the image intensity Ii,j is less than
some fixed constant T (Ii,j<T), or a white pixel if the image

intensity is greater than that constant. In the example image
on the right, this results in the dark tree becoming
completely black, and the white snow becoming completely
white.
4.3.5 Blob Detection
4.3.5.1 Finding a counter
In this method, the blob in the image is detected using blob
detection methods like Counter detection in image
processing.
4.3.5.2 Classification between Cluster and Patch
In this method, we classify the cluster and patch to identify
the blood group by determining the area of a cluster.
Fig -3: Detection of Cluster OR Patch
4.4 Histogram
Histogram is a graph of number of pixelsversustheQuantity
of pixels. The color histogram can be built for any kind of
color space, although the term is more often used for three-
dimensional spaces like RGB or HSV. For monochromatic
images, the term intensity histogram may be used instead.
For multi-spectral images, where each pixel is represented
by an arbitrary number of measurements (for example,
beyond the three measurements in RGB), the color
histogram is N-dimensional, with N being the number of
measurements taken. Each measurement has its own
wavelength range of the light spectrum, some of which may
be outside the visible spectrum.
fig -4: Histogram
5. IMPLEMENTATION DETAILS
The system is developed in Visual studio using the
techniques of image processing and opencv methods. The
user interface is developed using opencv and the
implementation of identification of the blood group is
processed using image processing techniques.
6. RESULT ANALYSIS
We first detect the background color using Imageprocessing
technique like HSV luminance plane to detect background
color. Range to detect cluster or patch on the basis of area of
the agglutination of the blood. Range to detect cluster or
patch is between 0 to 255 of HSV Luminance plane method
and it should be as follows:
Table-2: To detect Cluster or patch
0 255
50 255
0 230
The final result is calculated on the basis of combination of
cluster and patch of the given three images which is as
follows:
Table-3: Identification of blood group on the basis of
combination of cluster and patch of three images
Combination of cluster
and patch
Result as a blood group
C P C A
P C C B
C C C AB
P P P O
7. CONCLUSIONS
A fast, accurate and robust blood group judgment method is
proposed for the rapid and accurate identification of blood
types in the case of emergency transfusion.
A large number of experiments show that this method can
quickly and accurately identify whether the serum and
antibody agglutination reaction, and then get blood type
determination, to meet the needs of automated rapid blood
type analyser.
REFERENCES
[1] ABO Blood Group Detection Based on Image Processing
Technology Vue-fang Dong' Suzhou Institute of
Biomedical Engineering and Technology Chinese
Academy of Sciences Su Zhou, China. /international
conference of IEEE 2017.

[2] Stainsby D, Jones H, Asher D, et al. Serious hazards of
transfusion: a decade of hemovigilance in the UK.[J].
Transfusion Medicine Reviews, 2006, 20(4):273-282.
[3] Patton C 1. Handbook of automated analysis,continuous
flow techniques : by William A. Coakley, Marcel Dekker
Inc. 1981. SFr 55.00 (xii + 144 pages) ISBN 0 8247 1392
3[J]. Trac Trends in Analytical Chemistry, 1983,
2(4):Xlll-XlV.
[4] Brown, Barry, Hicks, et al. Blood Policy and
Technology[J]. 1985.
[5] Sturgeon P. Automation: its introduction to the field of
blood group serology.[J]. Immunohematology, 2001,
17(4):100-5.
[6] Wittmann G, Frank J, Schramm W, et al. Automation and
Data Processing with the Immucor Galileo Jf5 System in
a University Blood Bank[J]. Transfusion Medicine &
Hemotherapy, 2007, 34(5):347-352.
[7] Shin S Y, Kwon K C, Koo S H, et al. Evaluation of two
automated instruments for pre-transfusion testing:
AutoVue Innova and Techno TwinStation.[J]. Korean
Journal of Laboratory Medicine, 2008, 28(3):214-220
[8] Dada A, Beck D, Schmitz G. Automation and Data
Processing in Blood Banking Using the Ortho AutoVue
Jf5 Innova System[J]. Transfusion Medicine &
Hemotherapy, 2007, 34(5):341-346.

IRJET- Identifying the Blood Group using Image Processing

More Related Content

What's hot (20)

Similar to IRJET- Identifying the Blood Group using Image Processing (20)

More from IRJET Journal (20)

Recently uploaded (20)

IRJET- Identifying the Blood Group using Image Processing