基于加权主动形状建模的人脸特征定位方法

Face Alignment Based on Weighted Active Shape Models

主动形状建模是面部特征定位和人脸识别等模式识别领域中常用的一种方法。然而,由于受到初始情况、光照等诸多因素的影响,主动形状建模经常会陷入最优化过程中的局部最小问题,从而导致其性能下降。该文在传统主动形状模型基础上,提出了一种加权主动形状建模的方法,该方法可以有效地解决上述局部最小问题,并且更好地捕捉局部点的特征信息,从而更精确地进行面部特征定位。最后通过实验验证了上面的结论。

Active Shape Models （ASM） is one of powerful tools for face alignment and face recognition. However, the performance of ASM is often influenced by some factors such as the initial location, illumination and so on, which will frequently lead to the local minima in optimization. This paper proposes a weighted Active Shape Models, in which the more robust local appearance model is constructed with the local information of each landmark fully. Through the improved method the local minima problem can be solved efficiently, extracted the detailed local information of face feature points and localized the points accurately. Experiments verify the above conclusions.