# 人脸对齐--Face Alignment by Explicit Shape Regression

Face Alignment by Explicit Shape Regression CVPR2012 https://github.com/soundsilence/FaceAlignment

1 Introduction A face shape S 由 N 个facial landmarks 组成。face alignment 的目标就是 估计一个 shape S 使其与 true shape S^ 尽可能的接近。也就是人脸特征点的估计位置 和真值位置尽可能的接近。数学语言描述就是最小化

Regression-based methods learn a regression function that directly maps image appearance to the target output 基于回归的方法有的使用了 parametric model，This is indirect and sub-optimal because smaller parameter errors are not necessarily equivalent to smaller alignment errors。 有的方法对每个 individual landmarks 学习一个回归器，但是 because only local image patches are used in training and appearance correlation between landmarks is not exploited, such learned regressors are usually weak and cannot handle large pose variation and partial occlusion

using a fixed shape model in an iterative alignment process (as most methods do)may also be suboptimal

the early regressors handle large shape variations and guarantee robustness, while the later regressors handle small shape variations and ensure accuracy. Thus, the shape constraint is adaptively enforced from coarse to fine, in an automatic manner.

To our knowledge, adapting such shape model flexibility is rarely exploited in the literature.

Our regressor realizes the shape constraint in an non-parametric manner: the regressed shape is always a linear combination of all training shapes

using features across the image for all landmarks is more discriminative than using only local patches for individual landmarks

2 Face Alignment by Shape Regression 这里我们使用 boosted regression [9, 8] to combine T weak regressors (R1 ,…Rt ,…,RT ) in an additive manner

that the regressor Rt depends on both image I and previous estimated shape S(t−1)

key difference is that the shape-indexed image features are fixed in the second level, i.e., they are indexed only relative to S t−1 and no longer change when those r’s are learnt This is important, as each r is rather weak and allowing feature indexing to change frequently is unstable.

2.2. Primitive regressor We use a fern as our primitive regressor r

2.3. Shape-indexed (image) features For efficient regression, we use simple pixel-difference features, i.e., the intensity difference of two pixels in the image 为了快速回归计算，我们使用像素差值特征

A pixel is indexed relative to the currently estimated shape rather than the original image coordinates

In this work, we suggest to index a pixel by its local coordinates (δx,δy) with respect to its nearest landmark. As Figure 2 shows, such indexing holds invariance against the variations mentioned above and make the algorithm robust.

2.4. Correlation-based feature selection 一共有 P*P 个 pixel-difference features 产生，对每个fern regressor 如何选出 F 个好的特征了？

11

0 条评论

• ### 人脸对齐--One Millisecond Face Alignment with an Ensemble of Regression Trees

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.n...

• ### 人群密度估计--CrowdNet: A Deep Convolutional Network for Dense Crowd Counting

CrowdNet: A Deep Convolutional Network for Dense Crowd Counting published in ...

• ### 目标检测--Accurate Single Stage Detector Using Recurrent Rolling Convolution

Accurate Single Stage Detector Using Recurrent Rolling Convolution CVPR 2017 ...

• ### Tutorial: How to "live stream" a media file

I have tried a while to setup a free (open source etc.) live streaming solution...

仔细一看，已经提示我们的context.xml中没有配置权限，此时我们只需要用最高效的解决办法就是

• ### 基于双眼视觉的高精度无人机目标定位系统（CS CV）

在工作过程中，无人驾驶车辆常常需要高精度地定位目标。在无人材料搬运车间中，无人车辆需要对工件进行高精度的姿态估计以准确地抓住工件。在此背景下，本文提出了一种基于...

• ### Finding the closest objects in the feature space在特征空间中找到最接近的对象

Sometimes, the easiest thing to do is to just find the distance between two obje...

• ### 卡内基梅隆大学全校最受欢迎的Python课主讲Prof Kosbie给学生的一些实用性建议

I base the talk not on morals, but simply on patterns among the hundreds of CMU ...

• ### 在python中如何比较两个float

前几天跟同事聊起来，在计算机内部float比较是很坑爹的事情。比方说,0.1+0.2得到的结果竟然不是0.3?

• ### 【量化精品】通过LSTM神经网络进行时序预测针对股票市场（附Python源码）

阅读原文 Neural Networks these days are the “go to” thing when talking about new fad...