Emotion recognition from geometric facial features using self-organizing map
作者：
Highlights：
• We propose an emotion recognition model using system identification.
• Twenty six dimensional geometric feature vector is extracted using three different algorithms.
• Classification using an intermediate Kohonen self-organizing map layer.
• A comparative study with Radial basis function, Multi-layer perceptron and Support vector machine.
• Efficient recognition results with significant increase in average recognition accuracy over radial basis function and multi-layer perceptron. Marginal improvement over support vector machine.
摘要
Highlights•We propose an emotion recognition model using system identification.•Twenty six dimensional geometric feature vector is extracted using three different algorithms.•Classification using an intermediate Kohonen self-organizing map layer.•A comparative study with Radial basis function, Multi-layer perceptron and Support vector machine.•Efficient recognition results with significant increase in average recognition accuracy over radial basis function and multi-layer perceptron. Marginal improvement over support vector machine.
论文关键词：Facial expression analysis,Geometric facial features,Self-organizing map,Features extraction,System identification,Radial basis function,Multi-layer perceptron,Support vector machine
论文评审过程：Received 4 February 2013, Revised 17 July 2013, Accepted 6 October 2013, Available online 19 October 2013.
论文官网地址：https://doi.org/10.1016/j.patcog.2013.10.010
