Palmprint identification using invariant moments algorithm based on wavelet transform

Abstract

Because of the uniqueness of palmprints found on the palms of humans, palmprint identification has been used in several applications. It is usually associated with criminal identification, and has now become more popular in civilian applications. Therefore, the aim of the proposed model is to improve personal identification based on extracting shape feature using moments algorithm based on wavelet transform and matching algorithm, which is proposed in this model. This model has shown promising results without affecting rotation, translation and scaling of objects, because it is associated with the use of a good description of shape features. This system has been tested using databases from the Chinese Academy of Sciences (CASIA), in Beijing. By using false rejection rate (FRR) and false acceptance rate (FAR), we calculated the accuracy of identification. The experiment shows 98 % identification rate in the CASIA database.