Many applications in computer vision can be formulated as a multiple graphmatching problem that finds global correspondences across a bunch of data. Tosolve this problem, matching consistency should be carefully considered withmatching accuracy to prevent conflicts between graph pairs. In this paper, weaim to solve a multiple graph matching problem in complicated environments byusing multiple attributes that are represented in a set of multi-layerstructures. The main contribution of this paper is twofold. First, we formulatethe global correspondence problem of multi-attributed graphs using multiplelayered structures. The formulation is derived by aggregating the multi-layerstructures that describe individual pairwise matching problems respectively.Second, we solve the global correspondence problem by using a novelmulti-attributed multiple graph matching method that is based on themulti-layer random walks framework. The proposed framework contains additionalsynchronization steps to lead random walkers to consistent matching candidates.In our extensive experiments, the proposed method exhibited robust and accurateperformance over the state-of-the-art algorithms.
展开▼