Downloads: 138
Research Paper | Electronics Communication Engineering | Volume 4 Issue 1, January 2015 | Pages: 1904 - 1908 | India
Iris Recognition using LBP with Classifiers-KNN and NB
Abstract: A biometric system provides special and automatic identification of an individual based on characteristics and unique features showed by individuals. With the need for security system going up, Iris recognition is emerging as one of the important methods of biometrics-based identification system. Our system basically explains the Iris verification that is attempted to implement in MATLAB. Iris recognition is amongst the most robust and accurate biometric technologies supporting databases in excess of millions of peoples. Firstly, preprocessing of iris image includes localization, segmentation and normalization. Canny edge detection is used for region of interest segmentation and localization. For feature extraction Local Binary Pattern (LBP) is used. After feature extraction, Matching is performed by hamming distance. Then, classification is achieved by two different classifiers viz. K-NN and Navie Bayes. The average accuracy of proposed method is which is higher than other conventional methods.
Keywords: Biometrics, iris recognition, Local Binary Pattern LBP, iris feature extraction, matching
How to Cite?: Nivedita S. Sarode, Dr. A.M. Patil, "Iris Recognition using LBP with Classifiers-KNN and NB", Volume 4 Issue 1, January 2015, International Journal of Science and Research (IJSR), Pages: 1904-1908, https://www.ijsr.net/getabstract.php?paperid=SUB15735, DOI: https://dx.doi.org/10.21275/SUB15735