Study Of Invariant Features In Palmprint Identification System

The technology of palmprint recognition is one of the most important research focuses in the field of Biometrics identification technologies, which develops rapidly in these years. The uniqueness and the invariance for a lifetime of the technology of palmprint recognition is as good as the technology of fingerprint recognition. Besides of this, palmprint recognition possesses a lot of irreplaceable advantages, such as high accuracy, short recognition time and inexpensive price, etc. These advantages make the technology of palmprint recognition not only an important supplement to the current biometric identification technologies, but also a significant biometric technology itself. It is believable that the technology of palmprint recognition will have a very wide range of potential applications.Through the study and research to the development history and current research to this subject, we know that this technology is still in a stage of rapid development, especially in the field of the invariant features of palmprint recognitions. A great deal of effort, research work, innovation and experiment are needed to this subject. On the base of the main technologies in this field, we mainly focused on the technology of the invariant features extraction of palmprint recognition. A new method based on the Maximum Effective Circle (MEC) is presented using the characteristic of the palmprint that the uniqueness and the invariance to the rotation can be obtained by obtain the datum point. Experiment result shows that the new method has a stable localization performance to the different samples of the same individual. The validity has also been demonstrated and the result shows that this method has a good invariability toward rotation, translation and scaling. Finally, a experiment system is developed to show the results of every step of the method as well as the method as a whole.