Fingerprint access control recognition technology

1. The detection of the earliest fingerprint identification system and the detection of criminal suspects by the police has a history of more than 30 years. This has laid a good technical foundation for the research and practice of fingerprint identification. In particular, the current fingerprint identification system has reached the stage of convenient operation, accurate and reliable, and moderate price, and is gradually applied to the civilian market.

2. Fingerprint matching algorithm (including fingerprint image processing, special positive extraction, comparison and matching)

In fingerprint matching algorithm, there are mainly two concepts, verification and identification; verification is what we often say 1:1 algorithm, identification is 1:N algorithm. At the same time, there are two important parameters misrecognition rate and refusal rate for fingerprint matching algorithm.

2.1 Verification

Verification is the one-to-one matching of fingerprints collected from a site with a registered fingerprint to identify the identity. As a prerequisite for verification, his or her fingerprint must already be registered in the fingerprint database. Fingerprints are stored in a compressed format and are associated with their name or their identification (ID, PIN). Then in the comparison scene, first verify its identity, and then use the fingerprint of the system and fingerprint collected on the spot to prove its identity is legitimate. The verification actually answers the question: "Is he the person he claimed to be?" This is a method that is used more often in applications.

2.2 Identification

The identification is to compare the fingerprints collected in the scene with the fingerprints in the fingerprint data, and find the fingerprint matching the live fingerprints. This is also called "one-to-many matching." Validation is in fact answering the question: "Who is he?" Identification is mainly used in the traditional field of criminal fingerprint matching. The fingerprint of an unidentified person is compared with the fingerprint of the person who has the criminal record in the fingerprint database to determine whether the person has ever had a criminal record.

2.3 Misrecognition rate and refusal rate

Since the computer processes the fingerprint, it only involves some limited information of the fingerprint, and the matching algorithm is not an exact match, and the result cannot be guaranteed to be 100% accurate. An important measure of the specific application of the fingerprinting system is the recognition rate. It consists of two parts, the FRR and the FAR. We can adjust these two values ​​for different purposes. FRR and FAR are inversely proportional. Express this number with 0-1.0 or percentage.