GRM($m$): An Efficient Face Recognition Descriptor

This paper presents GRM (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m$</tex-math></inline-formula>), a Gabor wavelet-based face recognition descriptor tailored to tackle the challenges posed by limited-sample conditions in computer vision tasks. Traditional deep learning models, such as ResNet and Transformer architectures, often struggle to generalize with sparse training data, particularly for near-frontal face images. To overcome this limitation, we propose a novel representation framework that leverages Gaussian Riemannian Manifolds (GRM) to capture both geometric structures and statistical dependencies of facial features. The GRM (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m$</tex-math></inline-formula>) descriptor encodes multi-scale local features into a Riemannian manifold space, enhancing the discriminative capability of face representations even with minimal samples. Combined with deep neural networks, GRM (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m$</tex-math></inline-formula>) efficiently fuses handcrafted geometric features with high-level semantic embeddings, significantly improving recognition accuracy. Extensive experiments on benchmark datasets demonstrate that GRM (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m$</tex-math></inline-formula>) outperforms state-of-the-art methods in few-shot learning scenarios, especially under challenging variations in expression, lighting, and accessories. The proposed approach provides a robust and scalable solution for real-world face recognition applications with constrained training samples.