The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SIGNAL PROCESSING
Transactions ID Number: 32-202
Full Name: Hamed Ranjzad
Position: Student
Age: ON
Sex: Male
Address: Iran-miyaneh-shahid mottahari street-bamshad alley-postal code 5313756675
Country: IRAN
Tel: 0984232232335
Tel prefix:
Fax:
E-mail address: hamedranjzad@gmail.com
Other E-mails: hamedranjzad@yahoo.com
Title of the Paper: Designing a New System of Iris Recognition
Authors as they appear in the Paper: Hamed Ranjzad, Hossein Ebrahimnezhad
Email addresses of all the authors: hamedranjzad@gmail.com
Number of paper pages: 16
Abstract: using recognitions systems based on biometric is increasing every day. Among biometric recognition systems, iris recognition is more noticeable due to its high accuracy. In security systems for more accuracy of iris recognition processes, colored images with high resolution and limited to inside of eye are highly favored. In these systems, matching error is of utmost importance. In this paper a new recognition system is proposed for this kind of images. The iris recognition operation is done in four steps: 1-Segmentation 2-Normalization 3-Feature extraction 4-Matching. For the Segmentation Operation a novel combinational method using RANSAC algorithm and nonlinear least squares is proposed. The advantage of using this method is due to its less sensitivity to texture variations of iris and eyelid effects. For the normalization operation an independent method of iris boundaries shapes is used. For feature extraction a new adaptive filter is designed. This filter repr!
esents the texture features of iris more accurately. The scope and directions of this filter changes depending on situation and texture variations around each pixel. For more accuracy also texture features are extracted by using geometrical properties of iris texture lines. To overcome resistance of these geometrical features against undesired factors such as rotation and displacement of pupil, these features are extracted locally and relatively. Finally extracted feature by some methods of texture analysis are combined. In order to reduce the lengths of feature vectors, PCA is imposed locally on them. For matching operation a new approach is proposed as well. The simulation results represent the better performance of our new designed system with reduced matching error rate tending to zero.
Keywords: Iris recognition system, Nonlinear-Least square algorithm, RANSAC, Adaptive filter, Geometrical properties of texture lines, locally PCA
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 80.191.209.14
