Pengenalan Citra Iris Mata Menggunakan Alihragam Wavelet Daubechies Orde 4
ABSTRACT: Iris is a part of
the circle around the eye pupil. Iris has a very unique pattern, different in
each individual. On this basis the iris can be used as the basis for the
introduction of biometrics. To identify the texture of the iris in an eye
image, method of texture analysis can be used. There are several methods of
texture analysis, one of which is to use a wavelet based on image feature
extraction energy. The analysis uses the energy characteristics contained in
wavelet transform. Based on that reason, in this research an application
program to identify the iris of the eye based on Daubechies order 4 wavelet
transform. Eye image used in this
research was acquired and processed, beginning take on the characteristics and
texture of the iris image which converted into polar form. Then the feature
extraction is done using Daubechies wavelet transform order 4. The
characteristics obtained is in the form of the energy value. The next stage is
the recognition using nearest normalized
Euclidean distance. Tests carried out in the research consist of four types: influence
of sample database, influence of the decomposition level of Daubechies wavelet
transform order 4, influence of different input image formats, and testing on
eye images which are not in database. From the test results, it can be
concluded that the highest recognition rate with the parameters shown in
testing Daubechies wavelet transform order 4 level 4 with two samples iris
image stored is 86.66%. The lowest recognition rate is shown in tests with
Daubechies wavelet transform order 4 level 6 with one sample iris image stored
is 62.5%. Then from the results of testing the influence of different input
image formats, it can be concluded that the samples taken from 40 individuals
which one sample is take for each person, use the format BMP as well as with use JPEG format. Whereas, from
the test result for eye images which are not in database with threshold 0.3559,
of the recognition level is 96%.
Penulis: ANTONIUS DWI
HARTANTO, R. RIZAL ISNANTO, ACHMAD HIDAYATNO
Kode Jurnal: jptlisetrodd100124
