Security System based on Viola Jones Detection
Sheeba Jeya Sophia. S, Anitha S. Pillai · 2013
Iris recognition is a biometric system for access control that uses the most unique characteristic of the human body, the iris employed in automated border crossings, national ID systems, etc. This paper illustrates techniques to improve performance of iris recognition system based on stationary images using NI LabVIEW (Vision Module). Region of interest segmentation and localization of iris using canny edge detection is performed. And normalization of iris is performed using the Gabor filter. Local Binary Pattern (LBP) is used for feature vectors extraction and Learning Vector Quantization (LVQ) performs classification. Here, matching is performed using the hamming distance. Also we create a LabVIEW database for storing the information of the users. All the images used in this paper were collected from the Chinese Academy Of Sciences Institute of Automation (CASIA) iris database VI.0 with 108 subjects in it. compared to earlier iris scanning devices 13. Iris detection is one of the most accurate, robust and secure means of biometric identification while also being one of the least invasive. The iris has the unique characteristic of very little variation over a life’s period yet a multitude of variation between individuals. Iris recognition system can be used to either prevent unauthorized access or identity individuals using a facility. When installed, this requires users to register their irises with the system. A distinct iris code is generated for every iris image enrolled and is saved within the system. Once registered, a user can present his iris to the system and get identified. Iris recognition technology to provide accurate identity authentication without PIN numbers, passwords or cards. Enrollment takes less than 2 minutes. Authentication takes less than 2 seconds.