Iris recognition based on singular value decomposition for intrinsic mode and support vector machines
Hui Lv · Journal of Changsha University of Science & Technology · 2008
A new method for iris feature extraction and recognition was proposed in this paper.Firstly,the empirical mode decomposition method is used to decompose the preprocessed iris signal into a number of intrinsic mode function components,from which the initial feature vector matrixes are formed.Secondly,by applying the singular value decomposition technique to the initial vector matrixes,the singular values are obtained.Finally,the singular values serve as the iris feature vectors to be input to the support vector machine and are identified by the output of the classifier.Compared with that of Gabor method,the size of an iris code and the processing time of the feature extraction were significantly reduced.The experiment indicates that the approach could provide a good result for the iris recognition.