Evaluating software-based fingerprint liveness detection using Convolutional Networks and Local Binary Patterns
This work addresses the need for reliable fingerprint liveness detection to enhance security in biometric systems, but it is incremental as it builds on existing datasets and methods.
The paper tackled the problem of spoof fingerprint detection in biometric authentication by evaluating two feature extraction techniques, Convolutional Networks with random weights and Local Binary Patterns, combined with an SVM classifier, achieving a 95.2% correct classification rate and a 35% improvement in test error over prior results.
With the growing use of biometric authentication systems in the past years, spoof fingerprint detection has become increasingly important. In this work, we implement and evaluate two different feature extraction techniques for software-based fingerprint liveness detection: Convolutional Networks with random weights and Local Binary Patterns. Both techniques were used in conjunction with a Support Vector Machine (SVM) classifier. Dataset Augmentation was used to increase classifier's performance and a variety of preprocessing operations were tested, such as frequency filtering, contrast equalization, and region of interest filtering. The experiments were made on the datasets used in The Liveness Detection Competition of years 2009, 2011 and 2013, which comprise almost 50,000 real and fake fingerprints' images. Our best method achieves an overall rate of 95.2% of correctly classified samples - an improvement of 35% in test error when compared with the best previously published results.