Unconstrained facial expression synthesis and recognition method and system

The invention provides an unconstrained facial expression synthesis and recognition method and system, and the method comprises the steps: an expression synthesis step: capturing an unconstrained style attribute in an unconstrained facial data set image, and achieving the condition mapping from a facial expression image to a group of style conversion images; a content consistency step: when style conversion is performed on the facial expression image, keeping content information in the facial expression image unchanged, and ensuring content consistency; and an expression recognition step: performing expression classification on the generated style conversion image, feeding back loss generated by classification to a generator, and then enabling the generator not to execute blind data enhancement so as to synthesize an image which is more beneficial to improvement of expression recognition performance. 本发明提出了无约束人脸表情合成和识别方法及系统，包括：表情合成步骤：捕捉无约束人脸数据集图像中的无约束风格属性，实现从一个人脸表情图像到一组风格转换图像的条件映射；内容一致性步骤：在对人脸表情图像进行风格转换时，保持人脸