Scholarlink

<p>Music has consistently been recognized for its emotional value and unique capacity to improve mood. Because of the fast-paced nature of today’s world and rising stress levels, music has become a vital part of people’s daily lives to relax. By creating playlists based on user emotions, the proposed work improves the listening experience. Face recognition, feature extraction, mood detection, and music recommendation are the four main steps in the process. A personalized playlist based on the detected emotion reflects the user’s preferred songs and current mood. The recommended playlist is shown on the right side of the video frame, while the user’s emotion will be identified through real-time video recording. This method combines real-time emotion detection with music recommendation using Haar cascade with frontal face and eye classifier to provide tailored user experiences, efficient stress relief, and an improved listening experience.</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

Curating Emotion-Based Music Playlists with CNN and Haar Cascade for Facial and Eye Detection

  • 期刊论文

  • 发表日期：

    2025年6月3日

查看全文
  • D. S. Sahana,
  • Sneha Sureddy,
  • K. Geetha,
  • J. A. Madhurya

摘要

Music has consistently been recognized for its emotional value and unique capacity to improve mood. Because of the fast-paced nature of today’s world and rising stress levels, music has become a vital part of people’s daily lives to relax. By creating playlists based on user emotions, the proposed work improves the listening experience. Face recognition, feature extraction, mood detection, and music recommendation are the four main steps in the process. A personalized playlist based on the detected emotion reflects the user’s preferred songs and current mood. The recommended playlist is shown on the right side of the video frame, while the user’s emotion will be identified through real-time video recording. This method combines real-time emotion detection with music recommendation using Haar cascade with frontal face and eye classifier to provide tailored user experiences, efficient stress relief, and an improved listening experience.