Discrete cosine transform: algorithms, advantages, applications
Discrete cosine transform: algorithms, advantages, applications
Digital image processing (2nd ed.)
Digital image processing (2nd ed.)
A comparison of fast inverse discrete cosine transform algorithms
Multimedia Systems - Special issue on video compression
Image Representation Using 2D Gabor Wavelets
IEEE Transactions on Pattern Analysis and Machine Intelligence
High Confidence Visual Recognition of Persons by a Test of Statistical Independence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Location of the Pupil-Iris Border in Slit-Lamp Images of the Cornea
ICIAP '99 Proceedings of the 10th International Conference on Image Analysis and Processing
Personal Identification Based on Iris Texture Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Computers
UBIRIS: a noisy iris image database
ICIAP'05 Proceedings of the 13th international conference on Image Analysis and Processing
Integer DCTs and fast algorithms
IEEE Transactions on Signal Processing
| Hi-index | 0.00 |
Iris recognition is a method of biometric authentication which uses pattern recognition techniques. Biometrics refers to the automatic recognition of individuals based on their physiological and behavioral characteristics [1]. A behavioral characteristic is more a reflection of an individual's psychological makeup like signature; speech patterns etc. whereas a physiological characteristic is relatively stable physical characteristic like face, fingerprints, gait, palm print and iris patterns etc. variation in physical characteristics is smaller than a behavioral characteristic. In this paper, we investigate a novel method for iris recognition using one dimensional Discrete Sine Transform (DST) as a means of feature extraction for later classification. The DST of a series of averaged patches are taken from normalized iris images and a small subset of coefficients is used to form feature vectors. Classification is carried out using neural network. The feature extraction capabilities of the DST are optimized on the two largest publicly available iris image data sets, 2,156 images of 308 eyes from the CASIA database and 2,955 images of 150 eyes from the Bath database.