Performance Analysis of Fingerprint and Iris Verification Based On ELM and Genetic Algorithm

In multimodal biometric system, the effective fusion method is necessary for combining information from various modality systems. In this study a new approach to overcome the limitations by using multiple pieces of evidence of the same identity: iris and fingerprint, by combining ELM and Genetic Algorithm. According to ELM theory: “The hidden node / neuron parameters are not only independent of the training data, but also of each other, standard feed forward neural networks with such hidden nodes have universal approximation capability and separation capability. Such hidden nodes and their related mappings are terms ELM random nodes, ELM random neurons or ELM random features.” Genetic algorithms (GAs) operates with a population formed by a set of individuals called chromosomes and every chromosome is constituted by a set of genes. ELM combined with Genetic Algorithm provides better performance as compare to the SVM. It improved the accuracy when compared to SVM.