DIAGNOSIS OF WATERBORNE MICROBES IN DRINKABLE WATER BY

EMPLOYING IMAGE PROCESSING

Dr.A.GOMATHI AND M.JEEVA

1. Objectives of the Proposal

 Detection and identification of micro-organism oocysts, based on Machine Vision

technology applied to drinking water.
 New concept of detection uses image processing which allows detailed
inspection of parasite morphology to nanometer dimensions making the
detection more reliable than existing manual methods.
 The evaluation and impact of new technologies in machine vision has opened up
new possibilities in application to medical and biological engineering.
 The Machine Vision System has been designed and implemented to simplify and
improve the detection and analysis procedures required by these directives.

2. Critical Review of Status Identifying Gaps

5.1 National Status Review:

 Krishnan M, Sumrithra MG. 2013. A Novel Algorithm for Detecting Bacterial Leaf Scorch
(BLS) of Shade Trees Using Image Processing . In proceeding of IEEE 11th Malaysia
International Conference on Communications . IEEE, Kuala Lumpur, 474-478.
DOI:10.1109/MICC.2013.6805876.
 Kurniawati NN, Abdullah SNHS, Abdullah S, Abdullah S. 2009a. Investigation on image
processing techniques for diagnosing paddy diseases. In proceeding of 2009
International conference on soft computing and pattern recognition . IEEE, Malacca, 272-
277. DOI: 10.1109/SoCPaR.2009.62.

5.2 International Status Review

[1] Al Bashish D, Braik M, Bani-Ahmad S. 2010. A framework for detection and
classification of plant leaf and stem diseases . In proceeding of 2010 International
conference on signal and image processing . IEEE, Chennai, 113-118. DOI:
10.1109/ICSIP.2010.5697452.

[2] Anthonys G, Wickramarachchi N. 2009. An image recognition system for crop

disease identification of paddy fields in Sri Lanka. In Proceeding of 2009 International
Conference on Industrial and Information Systems (ICIIS) . IEEE, Sri Lanka, 403-407.
DOI:10.1109/ICIINFS.2009.5429828.

[3] Arivazhagan S, Shebiah R.N, Ananthi S, Varthini SV. 2013. Detection of unhealthy
region of plant leaves and classification of plant leaf diseases using texture features.
Agric Eng Int: CIGR Journal Vol. 15(1), 211-217.

[4] Asfarian A, Herdiyeni Y, Rauf A, Mutaqin KM. 2013. Paddy Diseases Identification
with Texture Analysis using Fractal Descriptors Based on Fourier Spectrum. In
proceeding of International Conference on Computer, Control, Informatics and Its
Applications. IEEE, Jakarta, 77-81, DOI: 10.1109/IC3INA.2013.6819152.

[5] Camargo A, Smith JS. 2009a. An image-processing based algorithm to automatically

identify plant disease visual symptoms. Biosyst Eng 102(1), 9-21. DOI:
10.1016/j.biosystemseng.2008.09.030.

[6] Camargo A, Smith JS. 2009b. Image pattern classification for the identification of
disease causing agents in plants. Comput Electron Agric, Vol. 66(2009), 121-125.
DOI:10.1016/j.compag.2009.01.003.

[7] Du CJ, Sun DW. 2004. Recent developments in the applications of image processing
techniques for food quality evaluation. Trends in Food Science & Technology, Vol
15(2014), 230–249. DOI: 10.1016/j.tifs.2003.10.006.

6. Novelty / uniqueness of the Proposal

 Large micro-organisms can be filtered with relatively ease, others can be
neutralised by chemical treatment. The main problem of drinking water is infection with
smaller micro-organisms that are difficult to eliminate due to their size. A precise
method to diagonise different microbes present in potable water has been
implemented. The Machine Vision System presented here has been designed and
implemented to simplify and improve the detection and analysis procedures required by
the SOP in term of laboratory and analytical procedures

7. Outline of the Project

Micro-organisms exiting in water have tremendously varied forms and
sizes. They can be classified in groups according to their size: There is a Ciliate group
which is relative large, over 100 um, and then the Flagellates generally less than 100
um followed by the Desmids and Diatoms which can be less than 60 um. Also there are
some Algae group with dimension from about 20 to 80 um. According to the type of
micro-organism found in drinking water it is possible to find: Worms The eggs and
larvae of various intestinal worms found in man and warm-blooded animals pollute the
water at times. They do not generally cause widespread infection for several reasons:
they are relatively few in number and are so large they can be filtered out of water with
comparative ease.
The spread of image processing’s applications in the different fields
indicate only 4.2% dedicated to medical and biological engineering .
The main reason for this low number of applications is the fact that the
living cells’ size and shape usually change and even their colour vary sometimes during
their life cycle. Also in terms of automatic classification the amount of artificial
intelligence embedded in these applications is relative complex and high. The
application of image processing to detection of Micro-organisms in water present the
problems associated with the physical variance of living cells and requires the
development of specialized algorithms.
This method is very unreliable due to the fact that under DIC microscopy
the contrast between the object of interest and the background is minimal; therefore
objects are very difficult to distinguish by a human operator. Also under DIC microscopy
it is impossible to see the nucleus inside sporozoites; hence sporozoites detection is
based only on the shape deformation of the of the external oocyst wall – a very
subjective process.

8. Expected scientific output/outcome of the project

The excellent contrast between the objects of interest and background
provided by this method make thresholding and binarisation possible using a simple
clustering, with little noise presented in the binary image. Noise clean-up is performed,
followed by objects reconstruction. Then Danielsson Circle detection is employed to
perform potential oocyst detection, Danielsson circle detection algorithm is able to
detect circular objects touching each-other. The circles with corresponding
Cryptosporidium size are defined as suspicious objects detected and their position is
recorded for further analysis. In the image processing for this Micro-organism our
system have the advantage over human operator in determining accurately small
dimensions and morphology using separation of red and green plane form a colour
frame. In our laboratory test results, detection using this algorithm was 100%
successful.

9. Methodology
The Machine Vision approach presented in this work can perform
automated analysis to determine whether or not Micro-organism oocysts are present in
treated water supply. The system can reliable determine the presence of micro-
organisms and enable the sample to be accurately and efficiently reviewed by an
operator if required.
The novel approach of detection proposed here allows a reliable
detection of waterborne micro-organism with substantial reduction in process time and
cost than the current methods in use and permit the assessment of large quantity of
water quality.
 The implemented algorithms accommodate feature such as micro-
organism size, shape, nucleons number, DAPI internal staining and typical or atypical
FITC staining. The application example presented in this paper provides a reliable
detection of FITC stained Cryptosporidium with Epi-illumination fluorescence
microscopy.

10. Work Plan 1-3 3-6 6-9 9-12 12-15 15-18 18-2121-24 24-27 27-30 30-33 33-36

Sl Activity/Mileston 1st year 2nd year 3rd year

no. e 1-6 7 - 12 13 - 18 19 - 24 25 - 30 31 - 36
A1 Literature Survey

A2 Staff Recruitment

A3 Computer
Upgradation
A4 Mathematical model
and Simulation of
Various Systems
A5 Design and
implementation of
the power
Requirement from
solar panel
A6 Design and
implementation of
Turbofan- Wind
turbine
A7 Design and
implementation of
Power electronic
systems
A8 Fabrication

A9 Testing and results

A1 Report Preparation
0

11.Suggested Plan of action for utilization of research outcomes

 Modules Description
Research Work related to Detect micro-
Module I organism oocytes in drinkable water

Analyzing Various microbes with data set

Module II

Research Work about Feature Extraction and

Module III
Classification
Research Work about the Machine vision
Module IV
technology
Module V Analyzing the algorithm

Module VI Project Implementation with software

12. Names of 5 Experts/Agencies/ Institutions working in the similar area

(i) Dr. G.R.K.PRASAD
Assistant Professor / ECE
KL University
E-Mail: ramguda1978@gmail.com

(ii) Dr. R. P. Ramkumar,

Professor / ECE,
Mallareddy engineering college(Autonomus)
E-Mail: ramkumarrp@mrec.ac.in

(iii) Dr.S.Gopinath
Associate Professor/ECE
Karpagam Institute of Technology
Coimbatore
E-mail: gopi.vasudev@gmail.com

(iv) Dr.P.Venkatachalam, Ph.D.,

 Professor & Head,
Department of Agriculture Engineering,
Agricultural College and Research Institute,
Madurai – 625 104.
Mobile: 91 - 9442961793, E-Mail: pvenkat55@yahoo.co.uk
(v) K L Solar Company Pvt Ltd – Coimbatore

(vi) Green Wind and Solar Powertech- Pvt Ltd - Coimbatore

13. Any other information relevant to the Project proposal/ execution of the
project
The Advanced Analysis algorithm is a feature extraction algorithm,
extracting relevant information under FITC and DAPI filters at 1000x total
magnification, for each potential Cryptosporidium oocyst tagged by the Detection
Algorithm. These parameters are stored together with the images acquired for each
potential Cryptosporidium oocyst for each mode
The reliability of the system is dependent on the quality of the acquired
images. Therefore algorithms have been developed to assure the proper quality: Auto-
focus and Flat Field Correction.

14. Facilities & Infrastructure already available to the PI(s) at their institute
for implementing the project.

S.N Equipment Name For which purpose it would be

o utilized in current project
1. R&D Lab For simulation & Implementation
2. Transportation For equipment purchase and
 installation
3. Water & Electricity Available
4. Administrative & Secretarial For financial support
Support
5. Standby power supply Available
6. Department & Main Library facilities To refer books, journals,
magazines and research articles
7. Laboratory Space & Furniture For doing research experiments

8. Air Conditioned room for Available

equipment
9. Digital Storage Oscilloscope For analysing the output signals
10. Converter Module For testing
11. Computing Module For testing
12. Signal/ Image processing lab For diagonising the oocytes in
water
13. Microcontroller For generating pulses