Scholarlink

<p>Face recognition technology has advanced significantly with deep learning, particularly through convolutional neural networks and models like VGG-Face, FaceNet, and ResNet. These systems, combined with loss functions such as ArcFace, have significantly improved human face recognition accuracy by extracting high-dimensional features. However, applying these human-centric algorithms to cat face recognition poses unique challenges due to differences in facial structure, feature distribution, and data availability. Additionally, variations in posture, fur texture, and limited distinguishing features can reduce recognition accuracy. In this study, we propose an adaptive method specifically designed for cat face recognition. We introduce an adaptive self-learning smoothing mask that enhances low-frequency signal retention and augments high-frequency features, focusing on fine-grained textures and subtle facial variations. This approach improves the model’s ability to identify key facial regions, addressing the challenges of feature overlap and data sparsity. Experimental results demonstrate that our method enhances the recognition performance of cat faces, achieving an accuracy of 92.74% on the test set, providing a more accurate and robust solution compared to traditional face recognition models. This work contributes to the development of more effective animal face recognition systems with potential applications in pet identification, behavioral monitoring, and environmental tracking. All our code and datasets are publicly available through <a href="https://github.com/qxzheng/CatFace.">https://github.com/qxzheng/CatFace.</a></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Adaptive fourier-enhanced vision transformer with self-learning smoothing masks for accurate cat face recognition

  • 期刊论文

  • 发表日期：

    2025年8月29日

查看全文
  • Qingxiao Zheng,
  • Taiyong Li

摘要

Face recognition technology has advanced significantly with deep learning, particularly through convolutional neural networks and models like VGG-Face, FaceNet, and ResNet. These systems, combined with loss functions such as ArcFace, have significantly improved human face recognition accuracy by extracting high-dimensional features. However, applying these human-centric algorithms to cat face recognition poses unique challenges due to differences in facial structure, feature distribution, and data availability. Additionally, variations in posture, fur texture, and limited distinguishing features can reduce recognition accuracy. In this study, we propose an adaptive method specifically designed for cat face recognition. We introduce an adaptive self-learning smoothing mask that enhances low-frequency signal retention and augments high-frequency features, focusing on fine-grained textures and subtle facial variations. This approach improves the model’s ability to identify key facial regions, addressing the challenges of feature overlap and data sparsity. Experimental results demonstrate that our method enhances the recognition performance of cat faces, achieving an accuracy of 92.74% on the test set, providing a more accurate and robust solution compared to traditional face recognition models. This work contributes to the development of more effective animal face recognition systems with potential applications in pet identification, behavioral monitoring, and environmental tracking. All our code and datasets are publicly available through https://github.com/qxzheng/CatFace.