Image Matching System using GeoSpatial and CBIR: A Java Implementation

Desklib provides past papers and solved assignments for students. This project details a Java-based image matching system.

ABSTRACT
“Image matching using Geo Spatial” Project is a Java-based project which helps the user to find
a matching image of our subject image. This technology is designed to help law enforcement
agencies so that they can find a match of any felons from their database. This will reduce the
effort by a significant amount and can increase the productivity of any agency that uses it. If a
database consists of several thousand images then this software can show the matching results in
just a few seconds.
INTRODUCTION
Every day the average person with a computer faces a growing flow of multimedia
information, particularly via the Internet. But this ocean of information would be useless
without the ability to manipulate, classify, archive and access them quickly and selectively.
The problems with text-based access to images have prompted increasing interest in the
development of image-based solutions. This is more often referred to as Content-Based Image
Retrieval (CBIR). Content-Based Image Retrieval relies on the characterization of primitive
features such as color, shape, and texture that can be automatically extracted from the images
themselves.
MOTIVATION
To help law enforcement agencies I got motivated to design an image matching system which
can reduce efforts of the officers so that more time can be invested to prevent the crime from
happening. This will also get a very precise result so that there is no confusion after when the
result is shown.
SYSTEM STRUCTURES
Hardware requirements for the system: Hard disk: 80 GB RAM: 512 Mb or more, Processor:
Intel i3 4th generation.
Software requirements for the system: Language used: Advanced Java (Java Swing) and for
front-end NetBeans 8.0, Java Applets.
FUNCTIONS
a. The system will help the user to find a very precise match of the image which is our
input.
b. We can easily add more images in our database so that search precision can improve.
c. Using CBIR we can find the closest looking image to our searched image.
USER REQUIREMENTS
The user will only need all three java files, Java development kit installed on a Windows 7 or
higher system.

ADDITIONAL FEATURES
a. This system can also help hospitals to people which are not yet identify by running CBIR
through all available databases. Shopping malls can use this technology to see if there is
anything suspicious about any customer.
b. The details of a person’s identify over the time so that the system can still find perfect
match if the photograph in the database is few years old. We can widen the histogram
value so that match can find of an old image.
INHERENT COMPLEXITIES AND CHALLENGES
To manage all the images in the database and make the system easy to use, the system must have
interactive GUI so that every functionality can be accessed by just click of a button. Challenges
occurred like sometime the image may have low tone or has a very high histogram value and
then we cannot find a match for that image so the matching image and the images in the database
must be of good quality.
PROJECT PLAN
S.NO Activity Date range Activity
1. Week 1- Week 2 Research about CSIR and
Geo- Spatial
2. Week 3- Week 4 Collecting resources and
practical study of the
application
3. Week 5- Week 7 Project Implementation and
Testing
CONCLUSION
In this application, we have learned about Image matching using Geo-Spatial and it can use in
various sectors like law enforcement, hospitals, shopping malls, etc.
REFERENCES
 Carswell, J., Wilson, D. and Bertolotto, M., 2019. Digital Image Similarity for Geo-
spatial Knowledge Management. [online] Semanticscholar.org. Available at:
<https://www.semanticscholar.org/paper/Digital-Image-Similarity-for-Geo-spatial-
Knowledge-Carswell-Wilson/9097ecdb58d04d26905bfe21986b545e3e883704>
[Accessed 7 Mar. 2019].