遗传算法与ICA相结合的多姿态人脸识别算法

为了解决多姿态人脸识别问题，提出了基于独立成分分析（ICA）进行正面人脸合成的新方法。首先利用ICA提取不同姿态人脸的特征子空间，然后利用遗传算法（GA）优化不同姿态的特征子空间，最后利用通过训练得到的姿态转换矩阵得到代表待合成的正面人脸特征系数，并直接进行分类比较。通过实验，验证了新方法对人脸识别率有较大的提高，并进一步简化了识别过程。

Multi-pose face recognition algorithm based on combination of genetic algorithm and ICA

A new frontal face synthesis method based on independent component analysis（ICA） was proposed to deal with the problem of face recognition with pose variations.First,the feature subspaces are formed from different pose images using ICA.Then the feature subspaces are optimized by genetic algorithm（GA）.Finally,the pose image feature coefficient is transformed into its corresponding frontal face image feature coefficient using the transformation matrix predetermined by learning,and we compare the frontal face feature coefficients directly which are obtained by using the transformation matrix with the feature coefficients of the original face images,the recognition rate is improved greatly.