Wright John, Yang Allen Y, Ganesh Arvind, Sastry S Shankar, Ma Yi
Coordinated Science Laboratory, University of Illinois at Urbana-Champaign, Urbana, IL 61801, USA.
IEEE Trans Pattern Anal Mach Intell. 2009 Feb;31(2):210-27. doi: 10.1109/TPAMI.2008.79.
We consider the problem of automatically recognizing human faces from frontal views with varying expression and illumination, as well as occlusion and disguise. We cast the recognition problem as one of classifying among multiple linear regression models and argue that new theory from sparse signal representation offers the key to addressing this problem. Based on a sparse representation computed by l{1}-minimization, we propose a general classification algorithm for (image-based) object recognition. This new framework provides new insights into two crucial issues in face recognition: feature extraction and robustness to occlusion. For feature extraction, we show that if sparsity in the recognition problem is properly harnessed, the choice of features is no longer critical. What is critical, however, is whether the number of features is sufficiently large and whether the sparse representation is correctly computed. Unconventional features such as downsampled images and random projections perform just as well as conventional features such as Eigenfaces and Laplacianfaces, as long as the dimension of the feature space surpasses certain threshold, predicted by the theory of sparse representation. This framework can handle errors due to occlusion and corruption uniformly by exploiting the fact that these errors are often sparse with respect to the standard (pixel) basis. The theory of sparse representation helps predict how much occlusion the recognition algorithm can handle and how to choose the training images to maximize robustness to occlusion. We conduct extensive experiments on publicly available databases to verify the efficacy of the proposed algorithm and corroborate the above claims.
我们考虑从具有不同表情、光照以及遮挡和伪装的正面视图中自动识别人脸的问题。我们将识别问题转化为在多个线性回归模型之间进行分类的问题，并认为来自稀疏信号表示的新理论为解决这个问题提供了关键。基于通过l{1}-最小化计算得到的稀疏表示，我们提出了一种用于（基于图像的）目标识别的通用分类算法。这个新框架为面部识别中的两个关键问题提供了新的见解：特征提取和对遮挡的鲁棒性。对于特征提取，我们表明，如果在识别问题中适当地利用稀疏性，特征的选择就不再关键。然而，关键的是特征数量是否足够大以及稀疏表示是否正确计算。只要特征空间的维度超过由稀疏表示理论预测的某个阈值，诸如下采样图像和随机投影等非常规特征与诸如特征脸和拉普拉斯脸等常规特征的表现一样好。通过利用这些误差相对于标准（像素）基通常是稀疏的这一事实，该框架可以统一处理由于遮挡和损坏引起的误差。稀疏表示理论有助于预测识别算法能够处理多少遮挡以及如何选择训练图像以最大化对遮挡的鲁棒性。我们在公开可用的数据库上进行了广泛的实验，以验证所提出算法的有效性并证实上述主张。
