Multi-modal biometrics and Emerging Biometrics -- A Novel Dual-modal Biometric Recognition Method Based on Weighted Joint Sparse Representation Classification -- Personal Identification with Exploiting Competitive Tasks in EEG Signals -- A Systematical Solution for Face De-identification -- Skeleton-Based Action Recognition with Improved Graph Convolution Network -- End-to-end Finger Trimodal Features Fusion and Recognition Model Based on CNN -- Mouse Dynamics Based Bot Detection Using Sequence Learning -- A New Age-groups Classifying Method for Irrawaddy Dolphin -- Auricular Point Localization Oriented Region Segmentation for Human Ear -- Portrait Thangka Image Retrieval via Figure Re-dentification -- To See Facial Expressions Through Occlusions via Adversarial Disentangled Features Learning with 3D Supervision -- Automatically Distinguishing Adult from Young Giant Pandas Based on Their Call -- Alzheimer's Disease Prediction via the Association of Single Nucleotide Polymorphism with BrainRegions -- A Deep Attention Transformer Network for Pain Estimation with Facial Expression Video -- Cognitive Analysis of EEG Signals Induced by Visual Stimulation of Facial Emotion -- 3D Context-Aware PIFu for Clothed Human Reconstruction -- Facial Expression Synthesis with Synchronous Editing of Face Organs -- Multi-lingual Hybrid Handwritten Signature Recognition Based on Deep Residual Attention Network -- Traumatic Brain Injury Images Classification Method Based on Deep Learning -- Palatal Rugae Recognition via 2D Fractional Fourier Transform -- Hand Biometrics -- Fusion of Partition Local Binary Patterns and Convolutional Neural Networks for Dorsal Hand Vein Recognition -- Pose-Specific 3D Fingerprint Unfolding -- Finger Vein Recognition Using A Shallow Convolutional Neural Network -- Finger Crystal Feature Recognition Based on Graph Convolutional Network -- Signatured Fingermark Recognition Based on Deep Residual Network -- Dorsal Hand Vein Recognition Based on Transfer Learning with Fusion of LBP Feature -- An Improved Finger Vein Recognition Model with A Residual Attention Mechanism -- A Lightweight CNN using HSIC Fine-tuning for Fingerprint Liveness Detection -- An Efficient Joint Bayesian Model with Soft Biometric Traits for Finger Vein Recognition -- A Novel Local Binary Operator Based on Discretization for Finger Vein Recognition -- A Generalized Graph Features Fusion Framework for Finger Biometric Recognition -- A STN-based Self-supervised Network for Dense Fingerprint Registration -- An Arcloss-based and Openset-test-oriented Finger Vein Recognition System -- Different Dimension Issues in Deep Feature Space for Finger-vein Recognition -- Facial Biometrics -- Holistic Co-occurrence Prior for High-density Face Detection -- Iris Normalization Beyond Appr-circular Parameter Estimation -- Non-Segmentation and Deep-Learning Frameworks for Iris Recognition -- Incomplete Texture Repair of Iris Based on Generative Adversarial Networks -- Deepfakes Detection Technology Basedon Multi Scale Fusion -- Balance Training for Anchor-free Face Detection -- One-Class Face Anti-spoofing Based on Attention Auto-encoder -- Full Quaternion Matrix and Random Projection for Bimodal Face Template Protection -- Kinship Verification via Reference List Comparison -- Face Attribute Estimation with HMAX-GCNet Model -- Wavelet-based Face Inpainting with Channel Relation Attention -- Monocular 3D Target Detection Based on Cross-modal and Mass Perceived Loss -- Low-quality 3D Face Recognition with Soft Thresholding -- Research on Face Degraded Image Generation Algorithm for Practical Application Scenes -- Embedding Fast Temporal Information Model to Improve Face Anti-spoofing -- Speech Biometrics -- Jointing Multi-task Learning and Gradient Reversal Layer for Far-field Speaker Verification -- Attention Network with GMM Based Feature for ASV Spoofing Detection -- Cross-corpus Speech Emotion Recognition Based on Sparse Subspace Transfer Learning -- Channel Enhanced Temporal-Shift Module for Efficient Lipreading -- Explore the Use of Self-supervised Pre-trained Acoustic Features on Disguised Speech Detection.

The LNCS volume 12878 constitutes the proceedings of the 15th Chinese Conference on Biometric Recognition, held in Shanghai, China, in September 2021. The 53 papers presented in this book were carefully reviewed and selected from 72 submissions. The papers cover a wide range of topics such as multi-modal biometrics and emerging biometrics; hand biometrics; facial biometrics; and speech biometrics.