然后在输入图像人脸初定位的基础上，利用嘴部的主元特征，通过最小剩余误差能量的判决准则实现人脸嘴部区域的自动定位。

For an input image, the mouth region was recognized according to least residual error energy(LREE) criteria after the face region was first located.

youdao

LQR算法是在特定白勺性能指标下，利用最少白勺控制能量，来到达最小白勺状态误差。

LQR algorithm USES the least control energy under certain performance index to achieve the smallest state errors.

youdao