Abstract:
This research paper deals with the implementation of iris recognition using Integro
differential method and wavelets on iris images. The proposed system contains three
parts i.e. preprocessing, feature extraction and matching. The preprocessing part further
contains pupil localization, iris localization and normalization processes. First the centre
coordinates and pupil is calculated. In the next phase iris area is calculated using Integro
differential method and ellipse as the contour model i.e. the parameter form of ellipse is
used. Then the iris area is converted to normalized template. After that feature extraction
process takes over in which the rows of input normalized template are taken as signals
and then these are convolved with the gabor filter or wavelets. The output of this process
is encoded in the form of feature template. Then this feature template of the input iris
image is stored in the database. When the iris identification is required then the input
image is compared with the feature templates that are stored in database using hamming
distance which gives the ratio that describes the no of pixels that are different in both
templates.
The proposed algorithm was tested on CASIA database. The empirical results provide the
accuracy of 96% with time delay of 0.066134 sec per image. The comparison of the
proposed technique with other well known techniques is provided in the thesis both with
respect to time and performance in the form of graphs. It is evident from the comparison
that the proposed technique performs better not only with respect to accuracy but time
also. The robustness and time efficiency of the proposed algorithm makes it perfect
candidate for real time applications.
