# A Dynamic Multi-Scale Convolution Model for Face Recognition Using Event-Related Potentials

## TL;DR

This paper introduces a new model for face recognition using brain signals, which improves accuracy and provides insights into how the brain processes familiar and unfamiliar faces.

## Contribution

A novel Dynamic Multi-Scale Convolution model is proposed for ERP-based face recognition, achieving superior performance with dynamic filter generation.

## Key findings

- The model achieved a balanced accuracy rate of 93.20% and an F1 score of 88.54%.
- It outperformed state-of-the-art models in cross-subject face recognition tasks.
- The model provides data-driven insights into ERP components related to face recognition.

## Abstract

With the development of data mining technology, the analysis of event-related potential (ERP) data has evolved from statistical analysis of time-domain features to data-driven techniques based on supervised and unsupervised learning. However, there are still many challenges in understanding the relationship between ERP components and the representation of familiar and unfamiliar faces. To address this, this paper proposes a model based on Dynamic Multi-Scale Convolution for group recognition of familiar and unfamiliar faces. This approach uses generated weight masks for cross-subject familiar/unfamiliar face recognition using a multi-scale model. The model employs a variable-length filter generator to dynamically determine the optimal filter length for time-series samples, thereby capturing features at different time scales. Comparative experiments are conducted to evaluate the model’s performance against SOTA models. The results demonstrate that our model achieves impressive outcomes, with a balanced accuracy rate of 93.20% and an F1 score of 88.54%, outperforming the methods used for comparison. The ERP data extracted from different time regions in the model can also provide data-driven technical support for research based on the representation of different ERP components.