Abstract
Although face recognition systems have wide application, they are vulnerable to presentation attack samples (fake samples). Therefore, a presentation attack detection (PAD) method is required to enhance the security level of face recognition systems. Most of the previously proposed PAD methods for face recognition systems have focused on using handcrafted image features, which are designed by expert knowledge of designers, such as Gabor filter, local binary pattern (LBP), local ternary pattern (LTP), and histogram of oriented gradients (HOG). As a result, the extracted features reflect limited aspects of the problem, yielding a detection accuracy that is low and varies with the characteristics of presentation attack face images. The deep learning method has been developed in the computer vision research community, which is proven to be suitable for automatically training a feature extractor that can be used to enhance the ability of handcrafted features. To overcome the limitations of previously proposed PAD methods, we propose a new PAD method that uses a combination of deep and handcrafted features extracted from the images by visible-light camera sensor. Our proposed method uses the convolutional neural network (CNN) method to extract deep image features and the multi-level local binary pattern (MLBP) method to extract skin detail features from face images to discriminate the real and presentation attack face images. By combining the two types of image features, we form a new type of image features, called hybrid features, which has stronger discrimination ability than single image features. Finally, we use the support vector machine (SVM) method to classify the image features into real or presentation attack class. Our experimental results indicate that our proposed method outperforms previous PAD methods by yielding the smallest error rates on the same image databases.
Highlights
Nowadays, biometric recognition systems are widely used in various application systems because they are hard to steal, have high recognition accuracy, and are convenient for users [1,2].Such a recognition method is based on the difference in specific physical or behavioral characteristics among people
To overcome the above limitations of previous research on the presentation attack detection (PAD) problem for a face recognition system, we propose a new PAD method based on hybrid features that combines information from both handcrafted and deep learning features
We measure the detection accuracy of the PAD method in both cases of with and without applying PCA for feature selection to validate the efficiency of the PCA method for feature dimensionality reduction
Summary
Biometric recognition systems are widely used in various application systems because they are hard to steal, have high recognition accuracy, and are convenient for users [1,2] Such a recognition method is based on the difference in specific physical or behavioral characteristics among people. Along with face and fingerprint, several biometric features, such as veins (blood vessels) [3,4], iris [2,5], palm-print [4,6,7], and ear [7,8], have been used in recognition applications These previous studies have shown that biometric systems are more suitable in terms of enhancing recognition accuracy and user convenience as compared to traditional recognition methods, such as token-based methods (using keys and cards) or knowledge-based methods (using username and passwords).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
