The application of fingerprint identification has a long history. In about 6000 years BC, fingerprint had been used to identify persons in China and Syria. With the price of the fingerprint sensor and the fingerprint recognition system lower, the fingerprint identification is more common used.

　　A fingerprint is the pattern of ridges and furrows on the surface of a fingertip. Each individual has unique fingerprints. The uniqueness of a fingerprint is exclusively determined by the local ridge characteristics and their relationships. A total of one hundred and fifty different local ridge characteristics, call minutiae details, have been identified. These local ridge characteristics are not evenly distributed. Most of them depend heavily on the impression conditions and quality of fingerprints and are rarely observed in fingerprints. The two most prominent ridge characteristics, call minutiae, are ridge ending and ridge bifurcation.
         Automatic fingerprint identification systems (AFIS) have been widely used. An AFIS consists of two phases: off-line and on-line. In the off-line phase, a fingerprint is acquired, enhanced using different algorithms, where after features of the fingerprint are extracted and stored in a database as a template. In the on-line phase, a fingerprint is acquired, enhanced and features of the fingerprint are extracted, fed to a matching model and matched against template models in the database.

Figure 2. Flowchart of AFIS　　

　　Among all the biometric techniques, fingerprint-based identification is the most common used method which has been successfully used in numerous applications. Comparing to other biometric techniques, the advantages of fingerprint-based identification are as following:
(1) The minutiae details of individual ridges and furrows are permanent and unchanging.
(2) The fingerprint is easily to capture using the fingerprint sensor.
(3) Most people have ten fingers, and fingerprint for every finger is different. So it can be used to form
      multiple passwords to improve the security of the systems.
(4) The template used in the fingerprint identification is not original fingerprint image, so it can protect       the privacy of individual. And generally the size of the template is smaller than original image, so it       can reduce the requirement of the memory and alleviate the burden of networks.

　　Biometrics Research Group of Institute of Automation, Chinese Academy of Science and FINGERPASS group have done much research on the novel technology of fingerprint Recognition and have done lots of work in the wonderful application of fingerprint Identification. During the passed 7 years, FINGERPASS has participated in many momentous projects such as National Science Foundation projects, National 863 Foundation projects and CAS Study Abroad Foundation projects. By this time FINGERPASS has issued 5 monographs, has published about 40 papers on the important conferences and magazines and now has 6 patents, 2 registered soft wares. What's more, the fingerprint recognition algorithms got a good result in the second Fingerprint International Competition (FVC2002), the algorithms achieved the seventh place and got the first place among domestic competitors. The average error rates are below 1.1%. FINGERPASS has developed the fingerprint identification module based DSP and some fingerprints application software