The field of biometric recognition is moving towards more accurate and robust methods for identifying individuals. Recent research has focused on exploring new modalities, such as ear and iris recognition, and improving the performance of existing methods, such as gender classification. The use of deep learning techniques, such as convolutional neural networks (CNNs) and graph neural networks, has been shown to be effective in extracting features from biometric data. Additionally, the incorporation of symmetry information, such as bilateral ear symmetry and chirality, has been found to improve the accuracy of biometric recognition systems. Notable papers in this area include: ProtoN, which proposes a graph-based approach for ear recognition, achieving state-of-the-art performance on several benchmark datasets. Symmetry Understanding of 3D Shapes via Chirality Disentanglement, which introduces a method for extracting chirality-aware features from 3D shapes, demonstrating its effectiveness in various downstream tasks.