Analysis of Tradeoffs among Verification Accuracy, Memory Consumption, and Execution Time in the GH-Based Fuzzy Fingerprint Vault

The fuzzy fingerprint vault solution has been proposed as a way to protect the registered fingerprint template, and the geometric hashing solution has been applied to implement it. Although this Geometric Hashing-based fuzzy fingerprint vault solution can solve the auto-alignment problem and provide higher security, it requires more memory space due to the large size of the hash table. To solve this problem, we make the GH-based fuzzy fingerprint vault to be configurable, and study the tradeoffs among the verification accuracy, the memory consumption, and the execution time of it. The experimental results show that the configurable approach can either maximize the verification accuracy or minimize the memory consumption and/or the execution time by setting a performance parameter properly.