应用多种深度学习架构用于基于面部表情的情绪分类
Cheng Qian1, João Alexandre Lobo Marques2, Auzuir Ripardo de Alexandria3
1Institute of Data Engineering and Science, University of Saint Joseph, Macau SAR, China.
Sensors (Basel, Switzerland)
|March 17, 2025
概括
这项研究评估了面部表情识别 (FER) 的十种深度学习模型. EfficientNet V2和ResNet50实现了最高精度,平衡了情绪检测的性能和效率.
科学领域:
- 计算机科学 计算机科学
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 面部表情识别 (FER) 对于理解人类情绪至关重要.
- 应用范围涵盖大数据分析,医疗保健,安全和用户体验.
- 深度学习模型为FER任务提供了高级功能.
研究的目的:
- 综合评估FER的十个最先进的深度学习模型.
- 根据准确性,训练时间和文件大小分析模型性能.
- 为特定的FER应用要求确定最佳架构.
主要方法:
- 使用FER2013数据集进行面部表情识别.
- 评估了十个深度学习模型:VGG16,VGG19,ResNet50,ResNet101,DenseNet,googLeNet V1,MobileNet V1,EfficientNet V2,ShuffleNet V2和RepVGG. 在这些模型中,深度学习模型包括VGG16,VGG19,ResNet50,ResNet101,DenseNet,GoogleLeNet V1,MobileNet V1,EfficientNet V2,ShuffleNet V2和RepVGG.
- 评估关键性能指标,包括测试准确性,训练时间和重量文件大小.
主要成果:
- 效率网V2和ResNet50表现出卓越的性能,具有高精度和稳定的收.
- 虽然DenseNet,GoogLeNet V1和RepVGG表现出强的结果,但最初的收速度较慢.
- 轻量级模型 (MobileNet V1,ShuffleNet V2) 提供了计算效率,但对具有挑战性的情绪的准确性较低.
结论:
- 在FER模型中,计算效率和预测准确性之间存在关键的权衡.
- 对于FER的模型选择应与特定的应用需求和约束保持一致.
- 这项研究通过详细介绍模型性能和权衡来推动FER的深度学习.
更多相关视频
05:51Exploring the Use of Isolated Expressions and Film Clips to Evaluate Emotion Recognition by People with Traumatic Brain Injury
Published on: May 15, 2016
8.9K
06:19Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
Published on: August 16, 2024
355
相关概念视频
01:24Facial Feedback Hypothesis
107
Charles Darwin proposed that facial expressions are an evolutionary adaptation for communication. He argued that these expressions are not influenced by culture but are universal across species. For example, a snarling expression with exposed teeth signals a threat in many animals, including humans. Darwin also suggested that displaying an emotion can intensify the feeling. Smiling, for example, could enhance one's sense of happiness. This idea laid the foundation for understanding the role...
107
01:26Emotional Expression
133
Emotional expression encompasses how individuals convey their emotions through verbal communication and non-verbal cues. These non-verbal actions include facial expressions, body language, and physical gestures, such as frowning or smiling. Among these, facial expressions play a crucial role in emotional expression and are understood universally, indicating a biological basis for how humans communicate emotions.
Universal Facial Expressions
Psychologist Paul Ekman identified seven basic...
Universal Facial Expressions
Psychologist Paul Ekman identified seven basic...
133