Scholarlink

Facial Expression Recognition (FER) has experienced significant advancements recently, driven by breakthroughs in machine learning, image processing, and cognitive sciences. This study aims to enhance the precision and effectiveness of FER by delving into the intricacies of facial movement features within static images. Our innovative approach utilizes patch-based Gabor features to automatically capture these nuances, providing a comprehensive understanding of static and dynamic characteristics crucial for robust FER. Notably, our results showcase exceptional performance, with VGG16 achieving an outstanding accuracy of 99.28% in the Emotion Detection Dataset. These findings validate the efficacy of our proposed methodology and emphasize the potential of integrating dynamic facial movement features for superior emotion recognition.

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

Mapping Facial Emotions Through Deep Neural Networks

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Satyam Kumar,
  • Lakshya Sharma,
  • Puneet Mittal,
  • Purusharth Agarwal

摘要

Facial Expression Recognition (FER) has experienced significant advancements recently, driven by breakthroughs in machine learning, image processing, and cognitive sciences. This study aims to enhance the precision and effectiveness of FER by delving into the intricacies of facial movement features within static images. Our innovative approach utilizes patch-based Gabor features to automatically capture these nuances, providing a comprehensive understanding of static and dynamic characteristics crucial for robust FER. Notably, our results showcase exceptional performance, with VGG16 achieving an outstanding accuracy of 99.28% in the Emotion Detection Dataset. These findings validate the efficacy of our proposed methodology and emphasize the potential of integrating dynamic facial movement features for superior emotion recognition.