基于随机森林的连续情感识别和跟踪算法

A Continuous Emotion Recognition and Tracking Algorithm Based on Random Forest

现有的大多数情感识别算法在进行连续情感识别时稳健性较差,影响了识别的精度。为此,提出一种基于随机森林的连续情感识别和跟踪算法,可持续识别出人脸在正常交流过程中的各种情感。在训练阶段,首先重建输入图像的三维脸部模型。并通过图像融合来构建连续情感表示(CEP)和用户无关情感表示(UIEP)。然后,由三维脸部形态、CEP图像及其情感值构成增强型训练集,并利用该训练集来构建随机森林。在情感估计阶段,随机森林同时进行两种回归操作:一种是针对三维脸部表情的跟踪;一种是针对当前情感的识别。当前时间步骤的CEP图像和之前时间步骤的三维脸部形态作为输入,计算当前时间步骤的情感值和三维脸部形态作为输出。当随机森林没有合适的输出时,利用UIEP图像进行复原优化,获得经过复原的三维脸部形态和情感。仿真实验结果表明,所提算法的性能优于当前大多数情感识别算法,实时连续情感识别时的皮尔逊相关系数也较高。

Most of the existing emotion recognition algorithms have poor robustness in continuous emotion recognition,which affects the accuracy of recognition.A continuous emotion recognition and tracking algorithm based on random forest is proposed,which can recognize the emotion of human face in the process of normal communication.During training period,the 3D facial model of input images is firstly restored.Then continuous emotion presentation(CEP)and the user-independent emotion presentation(UIEP)are constructed by image fusion.The 3D facial shapes,CEP images together with their emotion values constitute an augmented training set with which the random forest is constructed.In emotion estimation period,two regressions are taken in the random forest simultaneously:one is for tracking the 3D facial expression,the other is for recognizing the current emotion.The CEP image of current time step and 3D facial shape of previous time step are taken as the inputs,then the affective value and 3D facial shape of current time step are calculated as outputs.When there are no acceptable outputs of random forest,the recovery operation is taken with the help of UIEP images to achieve recovered 3D facial shape and emotion.Simulation results show that the performance of the proposed algorithm is better than most current emotion recognition algorithms,and the Pearson s correlation coefficient is also higher in real-time continuous emotion recognition.