IEEE Trans Image Process. 2017 May;26(5):2408-2423. doi: 10.1109/TIP.2017.2681841. Epub 2017 Mar 13.
In this paper, we consider the robust face recognition problem via iterative re-constrained group sparse classifier (IRGSC) with adaptive weights learning. Specifically, we propose a group sparse representation classification (GSRC) approach in which weighted features and groups are collaboratively adopted to encode more structure information and discriminative information than other regression based methods. In addition, we derive an efficient algorithm to optimize the proposed objective function, and theoretically prove the convergence. There are several appealing aspects associated with IRGSC. First, adaptively learned weights can be seamlessly incorporated into the GSRC framework. This integrates the locality structure of the data and validity information of the features into l -norm regularization to form a unified formulation. Second, IRGSC is very flexible to different size of training set as well as feature dimension thanks to the l -norm regularization. Third, the derived solution is proved to be a stationary point (globally optimal if p ≥ 1 ). Comprehensive experiments on representative data sets demonstrate that IRGSC is a robust discriminative classifier which significantly improves the performance and efficiency compared with the state-of-the-art methods in dealing with face occlusion, corruption, and illumination changes, and so on.
在本文中，我们通过迭代再约束分组稀疏分类器（IRGSC）和自适应权重学习来研究鲁棒人脸识别问题。具体来说，我们提出了一种分组稀疏表示分类（GSRC）方法，其中加权特征和分组被协同采用，以比其他基于回归的方法编码更多的结构信息和判别信息。此外，我们推导了一种有效的算法来优化所提出的目标函数，并从理论上证明了其收敛性。IRGSC 具有几个吸引人的方面。首先，可以将自适应学习的权重无缝地合并到 GSRC 框架中。这将数据的局部结构和特征的有效性信息集成到 l -范数正则化中，形成一个统一的公式。其次，由于 l -范数正则化，IRGSC 对于不同大小的训练集和特征维度都非常灵活。第三，所得到的解被证明是一个稳定点（如果 p ≥ 1 则是全局最优）。在有代表性的数据集上的综合实验表明，IRGSC 是一种鲁棒的判别分类器，与处理人脸遮挡、损坏和光照变化等问题的最先进方法相比，它显著提高了性能和效率。
