The invention discloses a
fingerprint biological
key generation method based on deep neural network coding. According to the method, a classic
fingerprint image processing method and a deep neural
network method are combined, a series of operations of blind alignment, stable
feature extraction, feature sequence stabilization and the like of the
fingerprint image are realized, stable feature components of different samples of the same fingerprint are extracted more accurately, and through layer-by-layer
processing of the deep neural network, the method further stabilizes the fingerprint feature to the feature value, and finally realizes the high-intensity key sequence generation of the normal
fingerprint image through a fingerprint key
fuzzy extractor, and the length of the generated fingerprint biological key can be greater than 512 bits. According to the method, biological feature template information needing to be recorded does not exist, the risk of privacy disclosure is greatly reduced, meanwhile, a user can generate a high-safety secret key without high-intensity memory, the secret key can be used for existing public and private keys, symmetric
encryption and other operations, and the safety and flexibility of fingerprint biological feature use are improved.