Cancelable Biometric Template Generation using Convolutional Autoencoder
Convolutional autoencoders are a great tool for extracting features from images and compressing them to a lower dimension called latent space. A latent space vector is generated from the input images by extracting the relevant and the most useful features required for approximating the images. In the proposed work, a convolutional autoencoder is used for feature extraction, random noise and random convolution are used for generating cancelable template from these features. This architecture has been trained for palm vein, wrist vein, and palm print images combined from different datasets namely, CASIA, CIEPUT, and PolyU. The proposed method has been experimented and evaluated for various modalities such as palm print, palm vein, and wrist vein. The evaluation of these methods has been done in three different scenarios for addressing different uses and attacks possible.
PDF
