Compositional Dictionaries for Domain Adaptive Face Recognition
Compositional Dictionaries for Domain Adaptive Face Recognition
复制标题
DOI：
10.1109/tip.2015.2479456
复制
发表时间：
2013-08
影响因子：
10.6
通讯作者：
Qiang Qiu;R. Chellappa
中科院分区：
文献类型：
--
作者：
Qiang Qiu;R. Chellappa
我们提出了一种字典学习方法来补偿由于视点、光照、分辨率等变化而引起的人脸变换。我们方法的核心思想是强制域不变稀疏编码，即，在不同的域中设计相同人脸的一致稀疏表示。以这种方式，在由正面人脸组成的源域中的稀疏代码上训练的分类器可以应用于目标域（由不同姿势、照明条件等的人脸组成），而不会损失太多的识别精度。该方法是首先学习域基字典，然后使用基字典上的稀疏表示来描述每个域移位（身份、姿态和照明）。适应于每个域的字典被表示为基字典的稀疏线性组合。在人脸识别的背景下，与建议的组合字典的方法，人脸图像可以被分解成稀疏表示为一个给定的主题，姿势和照明。这种方法有三个优点。首先，所提取的对象的稀疏表示跨域是一致的，并且使得能够进行姿势和照明不敏感的人脸识别。其次，姿态和照明的稀疏表示可以随后用于估计面部图像的姿态和照明条件。最后，通过组成主题和不同领域的稀疏表示，我们还可以执行姿势对齐和照明归一化。使用两个公开的人脸数据集进行了大量的实验，以证明所提出的方法的人脸识别的有效性。
We present a dictionary learning approach to compensate for the transformation of faces due to the changes in view point, illumination, resolution, and so on. The key idea of our approach is to force domain-invariant sparse coding, i.e., designing a consistent sparse representation of the same face in different domains. In this way, the classifiers trained on the sparse codes in the source domain consisting of frontal faces can be applied to the target domain (consisting of faces in different poses, illumination conditions, and so on) without much loss in recognition accuracy. The approach is to first learn a domain base dictionary, and then describe each domain shift (identity, pose, and illumination) using a sparse representation over the base dictionary. The dictionary adapted to each domain is expressed as the sparse linear combinations of the base dictionary. In the context of face recognition, with the proposed compositional dictionary approach, a face image can be decomposed into sparse representations for a given subject, pose, and illumination. This approach has three advantages. First, the extracted sparse representation for a subject is consistent across domains, and enables pose and illumination insensitive face recognition. Second, sparse representations for pose and illumination can be subsequently used to estimate the pose and illumination condition of a face image. Last, by composing sparse representations for the subject and the different domains, we can also perform pose alignment and illumination normalization. Extensive experiments using two public face data sets are presented to demonstrate the effectiveness of the proposed approach for face recognition.