基于双重神经网络的图像序列中的Res-RBG面部表情识别
Xiangwei Mou1,2, Yongfu Song1, Xiuping Xie1
1College of Electronic and Information Engineering/Integrated Circuits, Guangxi Normal University, Guilin 541004, China.
Sensors (Basel, Switzerland)
|June 27, 2025
概括
这项研究引入了一种新的双神经网络模型,用于从图像序列中动态地识别面部表情. 该方法显著提高了精度和效率,为先进的智能传感应用铺平了道路.
科学领域:
- 计算机视觉 计算机视觉
- 人工智能的人工智能
- 机器学习 机器学习
背景情况:
- 从静态图像中识别面部表情缺乏时间动态,限制了现实世界的应用.
- 将动态面部表情识别集成到智能传感中是具有挑战性的,因为性能下降.
研究的目的:
- 为图像序列开发一种有效的面部表情识别方法.
- 通过结合时间信息来解决基于静态图像的识别的局限性.
主要方法:
- 提出了一个新的双神经网络模型,将ResNet和剩余的双向GRU (Res-RBG) 融合在一起.
- 评估了基于图像序列的面部表情识别的基准数据集 (CK+和Oulu-CASIA) 的模型.
主要成果:
- 实现了高识别精度:98.10%的CK+和88.64%的奥卢-CASIA.
- 这款车型拥有64.20M的紧参数尺寸.
- 与现有的基于图像序列的方法相比,证明了更高的性能.
结论:
- 拟议的Res-RBG模型有效地捕捉时间动态,以准确识别面部表情.
- 该模型的效率和性能显示出在智能传感应用中部署边缘传感器的巨大潜力.
相关概念视频
Facial Feedback Hypothesis
253
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...
253
Muscles for Facial Expressions
2.8K
The craniofacial muscles are a collection of approximately 20 thin skeletal muscles situated beneath the skin of the face and scalp. These muscles, primarily responsible for the vast array of human facial expressions, originate from the bones or fibrous structures of the skull and extend outwards to connect with the skin. While most skeletal muscles in the body are enveloped in thick fascia, facial muscles generally have a more delicate fascial covering, with the buccinator muscle being a...
2.8K


