Analyzing people’s unique physical and behavioral characteristics is the essence of the science of biometrics. Over the last two decades, we have witnessed an exponential growth of research interests in this domain, through which biometrics has surged from interesting and conventional pattern recognition applications, to deep learning-based mainstream research topics. Three major reasons account for this, first, the technological progress of the sensors that capture biometric signals, second, the significant increase in machines' computing power, and third, the democratization of deep learning paradigms.
In this article collection, we are focusing on deep learning and biometric research topics that continue to be challenging, including evaluating new biometric techniques, remarkably improving the performance of existing ones, and ensuring the scalability of biometric systems to handle the ever-increasing amount of biometric data. In fact, biometric systems follow a typical pipeline that is composed of separate acquisition, preprocessing, feature extraction and classification. Deep learning as a data-driven representation learning approach has been shown to be a promising alternative to conventional data-agnostic and handcrafted pre-processing and feature extraction for biometric systems.
Combining deep learning models with biological visual perception, many biologically plausible approaches to deep learning have been proposed for review. Including research on a single deep learning model including CNN, RNN, AE, GAN, GNN, and reinforcement learning models, the recent approaches of visual perception computational models oriented deep learning, showing its advantage and its progressive impact on artificial intelligence.
Topics include but are not restricted to the following:
• AI-Based Biometric Applications
• Identity, Expression, Gender and Age Recognition
• Vision and Perception
• Deep Learning Techniques and Intelligent Systems for analyzing biometric data, such as CNN, RNN, transfer learning with convolutional neural networks, GAN, GNN, and reinforcement learning models for face recognition, gender and ethnicity classification, etc.
• Behavioral Analysis and Information Inference
• Activity, Action and Posture Recognition
• Biometric systems for information assurance
• Privacy, Security and Access Control
Keywords:
biometrics, deep learning, generative adversarial networks, convolutional neural networks, recurrent neural networks, identity recognition, gender classification, privacy
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
Analyzing people’s unique physical and behavioral characteristics is the essence of the science of biometrics. Over the last two decades, we have witnessed an exponential growth of research interests in this domain, through which biometrics has surged from interesting and conventional pattern recognition applications, to deep learning-based mainstream research topics. Three major reasons account for this, first, the technological progress of the sensors that capture biometric signals, second, the significant increase in machines' computing power, and third, the democratization of deep learning paradigms.
In this article collection, we are focusing on deep learning and biometric research topics that continue to be challenging, including evaluating new biometric techniques, remarkably improving the performance of existing ones, and ensuring the scalability of biometric systems to handle the ever-increasing amount of biometric data. In fact, biometric systems follow a typical pipeline that is composed of separate acquisition, preprocessing, feature extraction and classification. Deep learning as a data-driven representation learning approach has been shown to be a promising alternative to conventional data-agnostic and handcrafted pre-processing and feature extraction for biometric systems.
Combining deep learning models with biological visual perception, many biologically plausible approaches to deep learning have been proposed for review. Including research on a single deep learning model including CNN, RNN, AE, GAN, GNN, and reinforcement learning models, the recent approaches of visual perception computational models oriented deep learning, showing its advantage and its progressive impact on artificial intelligence.
Topics include but are not restricted to the following:
• AI-Based Biometric Applications
• Identity, Expression, Gender and Age Recognition
• Vision and Perception
• Deep Learning Techniques and Intelligent Systems for analyzing biometric data, such as CNN, RNN, transfer learning with convolutional neural networks, GAN, GNN, and reinforcement learning models for face recognition, gender and ethnicity classification, etc.
• Behavioral Analysis and Information Inference
• Activity, Action and Posture Recognition
• Biometric systems for information assurance
• Privacy, Security and Access Control
Keywords:
biometrics, deep learning, generative adversarial networks, convolutional neural networks, recurrent neural networks, identity recognition, gender classification, privacy
Important Note:
All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.