ProtoN: Prototype Node Graph Neural Network for Unconstrained Multi-Impression Ear Recognition

2025-08-06

AI Summary

Ear biometrics faces two major challenges: severe scarcity of labeled data and large intra-class variability, rendering existing single-sample feature extraction methods inadequate for learning robust identity representations. To address this, we propose ProtoN—a novel framework that, for the first time, models multiple ear impressions per subject as a graph structure. ProtoN introduces learnable class-specific prototype nodes and designs a dual-path message-passing mechanism coupled with cross-graph prototype alignment to jointly enhance inter-class discriminability and intra-class compactness. The method integrates prototype-based graph neural networks (PGNN), multi-impression graph modeling, cross-graph alignment, and an episode-global hybrid loss function. Evaluated on five benchmark datasets, ProtoN achieves a Rank-1 accuracy of 99.60% and an equal error rate of 0.025%, significantly outperforming state-of-the-art few-shot ear recognition approaches.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Ear biometrics offer a stable and contactless modality for identity recognition, yet their effectiveness remains limited by the scarcity of annotated data and significant intra-class variability. Existing methods typically extract identity features from individual impressions in isolation, restricting their ability to capture consistent and discriminative representations. To overcome these limitations, a few-shot learning framework, ProtoN, is proposed to jointly process multiple impressions of an identity using a graph-based approach. Each impression is represented as a node in a class-specific graph, alongside a learnable prototype node that encodes identity-level information. This graph is processed by a Prototype Graph Neural Network (PGNN) layer, specifically designed to refine both impression and prototype representations through a dual-path message-passing mechanism. To further enhance discriminative power, the PGNN incorporates a cross-graph prototype alignment strategy that improves class separability by enforcing intra-class compactness while maintaining inter-class distinction. Additionally, a hybrid loss function is employed to balance episodic and global classification objectives, thereby improving the overall structure of the embedding space. Extensive experiments on five benchmark ear datasets demonstrate that ProtoN achieves state-of-the-art performance, with Rank-1 identification accuracy of up to 99.60% and an Equal Error Rate (EER) as low as 0.025, showing the effectiveness for few-shot ear recognition under limited data conditions.

Problem

• Addresses ear recognition challenges with limited annotated data
• Improves discriminative feature extraction from multiple ear impressions
• Enhances class separability in few-shot learning scenarios

Innovation

• Graph-based few-shot learning for ear recognition
• Dual-path message-passing Prototype Graph Neural Network
• Cross-graph prototype alignment for class separability