Eigenspace-Based Face Hashing

We present a novel approach to generating cryptographic keys from biometrics. In our approach, the PCA coefficients of a face image are discretised using a bit-extraction method to n bits. We compare performance results obtained with and without the discretisation procedure applied to several PCA-based methods (including PCA, PCA with weighing coefficients, PCA on Wavelet Subband, and LDA) on a combined face image database. Results show that the discretisation step consistently increases the performance.