The palmprint recognition method based on the SMA-ConvNeXt model

Abstract Palmprint recognition technology has been widely applied in the field of security authentication. However, complex lighting conditions and diverse non-contact hand postures pose significant challenges to the accuracy and stability of recognition. To address the challenges of complex lighting conditions and the diversity of non-contact gestures in recognition, we propose a palmprint recognition method based on the SMA-ConvNeXt model. Firstly, we introduce an efficient gated self-attention mechanism, which enables dynamic weighting between global features and local details, effectively alleviating the feature deviation caused by different hand postures. In addition, we design an adaptive channel enhancement module, while dynamically adjusting channel weights, the key channel information is enhanced, effectively addressing the problem of channel feature collapse under complex lighting conditions. Finally, we propose a multi-scale hybrid encoder to tackle detail loss and blurring issues under complex lighting conditions, significantly improving texture recognition performance. Experimental results demonstrate that our proposed model outperforms the original model by more than 2% in accuracy and reduces the equal error rate by over 50% on four widely used palmprint datasets, providing valuable insights for the relevant field.