Presentation Attack Detection on Fingerprint Images Using Veins

This work deals with the detection of a presentation attack on a biometric fingerprint sensor capturing an image of a vein. It contains a proposal for a method of detecting a presentation attack on a sensor that uses NIR illumination to highlight a vein in a finger. The method is tested and trained on a dataset containing 294 finger images extracted from 143 pictures of hands. The method is based on extracting textural information from the image and subsequent classification using the SVM classifier. The extraction uses parallel processing and processes features from 294 fingerprint images in 25 minutes on average. Subsequent classification achieves an average detection success rate of 97 %. The work also describes the steps necessary to carry out various types of attacks on a biometric system using the vein system