what i am...???

Once upon a time, I,
dreamt I was a butterfly,
flittering hither and thither,
to all intents and purposes a butterfly.....
suddenly I awoke......
Now I do not know whether
I was then a man dreaming I was a butterfly,
or
whether I am now a butterfly dreaming I am a man

Saturday, February 21, 2009

projects coorg, srinath


























A list of abstracts of projects which ascent would like to offer as B.Tech Final Year Project or M.Tech Projects

CONTENTS

  1. finger print recognition system with matlab
  2. gps tool box for massistance for deaf and dump, pdaatlab (it is a hardware interfacing included project)
  3. nesting
  4. robot routing with neurofuzzy: miffin
  5. digital water marking for images
  6. vehicle number plate recognition
  7. leukemia detection using image processing
  8. 3 d vision : construction of 3d images from two numbers of 2d images : padmanabh
  9. automated speaker identification using neuro-fuzzy classifier - real time : miffin
  10. virtual keyboard
  11. flexible link modelling
  12. assistance for deaf and dump, pda










1. Automated
Fingerprint Identification System





Existing
security measures rely on knowledge-based approaches like passwords
or token-
based approaches such as swipe cards and passports to
control access to physical and virtual
spaces. Though ubiquitous,
such methods are not very secure. Tokens such as badges
and access
cards may be shared or stolen. Furthermore, they cannot differentiate
between
authorized user and a person having access to the tokens or
passwords.






Biometrics such as fingerprint, face and voice print offers means of
reliable personal
authentication that can address these problems and
is gaining citizen and government acceptance. Fingerprints were one
of the first forms of biometric authentication to be used for
law
enforcement and civilian applications. Contrary to popular belief and
despite decades
of research in fingerprints, reliable fingerprint
recognition is still an open problem. In this
project, we present
three specific contributions to advance the state of the art in this
field.





Reliable
extraction of features from poor quality prints is the most
challenging problem
faced in the area of fingerprint recognition. In
this project, we introduce a new approach for
fingerprint image
enhancement based on Short Time Fourier Transform(STFT) Analysis.
STFT is a well known time-frequency analysis technique to analyze
non-stationary signals.





In
this project, we extend its application to the analysis 2D
fingerprint images. The proposed


analysis
and enhancement algorithm simultaneously estimates several intrinsic
properties
of the fingerprint such as the foreground region mask,
local ridge orientation and local
frequency. Finally the projecty
will conclude with a userfriendly software developed in matlab for
the recognition of fingerprints, comparing it with a database of
fingerprints stored.





2. GPS Tool box for Matlab

    
    The Global Positioning System (GPS) is a burgeoning technology, which
provides unequalled accuracy and flexibility of positioning for
navigation, surveying and GIS data capture. The GPS NAVSTAR (Navigation
Satellite timing and Ranging Global Positioning System) is a
satellite-based navigation, timing and positioning system. The GPS
provides continuous three-dimensional positioning 24 hrs a day
throughout the world. The GPS uses satellites and computers to
compute positions anywhere on earth. The GPS is based on satellite
ranging. That means the position on the earth is determined by
measuring the distance from a group of satellites in space. The basic
principle behind GPS are really simple, even though the system employs
some of the most high-tech equipment ever developed.

    The GPS modules can be purchased from the local market easily. In general a GPS module has a serial port for interfacing with external world. The objective of this project is to develop a set of fuctions for controlling GPS module, fetching data from GPS module and plotting the data obtained. The project includes study of the system in detail, developing the functions in matlab standard format and documentation of the functions developed.




3. A generic approach for nesting of 2-D parts in 2-D sheets using genetic
                       and heuristic algorithms

































    In the present manufacturing scenario, cutting
of twodimensional (2-D) shaped parts from 2-D sheets, with a minimum
wastage of material, is an important task. Thet ask of arranging the
parts on the sheet, known as nesting,is being attempted by several
researchers employing severalmethods and implementing them using
digital computers. While developing the nesting methods for a given
set ofparts and sheets, one should consider certain geometrical and
technical aspects. The geometry of the parts to be cutmay vary from a
simple rectangular shape to a highly irregular one. In the case of
irregular parts, the geometry maycontain a straight line and
curvilinear features. Further, 2-D parts may also contain internal
features (either holes orcutouts) being regular or irregular in
geometry. In a similarmanner, the geometry of the sheet material can
vary fromregular to irregular shapes with or without defective
regions.




   In this project, a genetic and heuristic approach is proposed for the nesting of multiple two-dimensional (2-D) shaped parts in multiple 2-D shaped sheets with the aim of minimizing the wastage of the sheet material. The project proposes a new method of representing the sheet and part geometries in discrete form to arrange the parts on the sheet quickly, irrespective of the complexity in the geometry of the sheets and parts. The proposed heuristic approach considers the sheets and parts in a sequential manner and arranges the parts on the sheets using the bottom-left strategy. The genetic algorithm generates the best sequence of the sheets and parts for nesting the parts on multiple sheets, utilizing the sheet material optimally.





4. AUTOMATED OPTIMUM PATH DEVELOPMENT OF MOBILE ROBOT USING GENETIC-NEURO-FUZZY APPROACH
    
    Navigation and obstacle avoidance are very important issues for the successful use of an autonomous mobile robot. When the environment of the robot is obstacle free, the problem becomes less complex. But as the environment becomes complex, motion planning needs much treatment to allow the robot to move between its current and final configurations without any collision within the surrounding environment. The robot path is constrained by the partially-unknown movement of the moving obstacles known as uncluttered environments. Thus to generate collision free path of a car-like robot during its navigation among several moving obstacles it should have proper motion planning as well as obstacle avoidance scheme. This work deals with the determination of time-optimal, collision-free of a mobile robot using Neuro-fuzzy (NN-FLC) approaches. A fuzzy logic controller (FLC) is used to control the robot and the performance of the FLC is improved by using genetic algorithm (GA)-optimized NN-FLC. In the first approach, manually constructed FLC with author defined rules and membership function distributions are developed. In second approach, the rules and membership functions are optimized by using genetic algorithm. In the third approach, Orientation of the robot is also taken in to account for finding the optimal path and the problem of symmetry is solved in this approach. Two more condition variables derive_1 and derive_2 are fed as inputs the neruo-fuzzy network. In the fourth approach, Motion Planning of the mobile robot is developed by considering various dynamic constraints. In all the approaches, Takagi Sugeno method is used and the condition variables are expressed in terms of triangular membership functions. Five layer network is modeled with one hidden layer and learning algorithm (genetic) is used to determine the optimal rules and membership functions so that the robot will navigate in optimal collision-free path.



7. Automated Leukemia Diagnosis with Neurofuzzy Systems










Presently doctors are making decisions about diseases
using biopsy or other medical tests and medical images. Medical
images of cultured tissues are very difficult to manipulate using
naked eye and error probability in decision is very high. More over
two doctors may interpret the same image in two different ways. So we
are trying to realize a system to aid doctors in making decisions
very accurately using computer vision. More than one data mining
technique is used to increase the efficiency of the prediction
algorithm. Fractal analysis, mean and variance in spatial domain as
well as spectral domain are used for data mining. Artificial neural
network and fuzzy logic is used to predict the disease. A self
learning capability is given to the system to increase the accuracy.
Genetic algorithm is used for this purpose. The system is implemented
in MATLAB.



















8. stereo photography





    These
days we think of photographs as two diamensional objects. The reason
is that we always think of photographs on paper. With the advent of
computers and digital cameras, now we have started thinking about and
infact started using digital images. Thesee days we view images in
computer.





    In a
two diamensional photographs a pixel is associated with two
cordingtes x and y ie P(x,y). But in a three dimensional photograph,
a picture has to be associated with three co-ordinates , ie P(x,y,z).
A digital camera is digitising image from a two diamensional sensor
array and hence the normal still camera can not fetch information
about the third dimension (depth).





Humans
have two eyes located side-by-side in the front of their heads. Each
eye takes a view of the same area from a slightly different angle.
The two eye views have plenty in common, but each eye picks up visual
information the other doesn't. Each eye captures its own view and
the two separate images are sent on to the brain for processing. When
the two images arrive simultaneously in the back of the brain, they
are united into one picture. The mind combines the two images by
matching up the similarities and adding in the small differences. The
small differences between the two images add up to a big difference
in the final picture. The combined image is more than the sum of its
parts. It is a three-dimensional stereo picture.





The
objective of this project is to develop and implement an algorithm
which upon receiving two images( steriao images) calculates the
corresponding 3d image. The inputs to the developed program are two
numbes of 2-D images of same scene but from different angles. Let's
say P1(x,y) and P2(x,y). The output is a 3-D image P(x,y,z) and
which can be viewed using a 3-D grph like plot3d in matlab. The
programmig language to be used is matalab.



The
proposed technology can be used in


  1. Robotics:
    Robots can calculate obstacles on its path


  2. Satellite
    imaging: The topology of the earth surface can be calculated from
    two images taken at two different angles by the satellite.


  3. Entertainment:
    3-D photo albums in computer.








No comments:

Post a Comment