Dynamic Graph Representation for Occlusion Handling in Biometrics
Dynamic Graph Representation for Occlusion Handling in Biometrics
复制标题
DOI：
10.1609/aaai.v34i07.6869
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Min Ren;Yunlong Wang;Zhenan Sun;T. Tan
中科院分区：
文献类型：
--
作者：
Min Ren;Yunlong Wang;Zhenan Sun;T. Tan
由于各种遮挡的不利影响，卷积神经网络（cnn）在生物特征识别中的泛化能力大大下降。为此，我们提出了一种新的统一框架，结合cnn和图形模型的优点来学习生物识别中遮挡问题的动态图表示，称为动态图表示（DGR）。通过图形生成器重新构建特定区域的卷积特征，建立生物特征空间部分之间的联系，并基于这些节点表示构建特征图。Feature Graphs的每个节点对应输入图像的一个特定部分，边缘表示部分之间的空间关系。通过分析节点之间的相似性，该框架能够自适应地去除代表被遮挡部分的节点。在动态图匹配中，我们提出了一种新的策略来测量节点和相邻矩阵的距离。因此，该方法比基于cnn的方法更具说服力，因为动态图方法对生物特征决策的推断更具说明性和合理性。虹膜和人脸实验验证了该框架的优越性，与基线方法相比，该框架大大提高了遮挡生物特征识别的准确性。
The generalization ability of Convolutional neural networks (CNNs) for biometrics drops greatly due to the adverse effects of various occlusions. To this end, we propose a novel unified framework integrated the merits of both CNNs and graphical models to learn dynamic graph representations for occlusion problems in biometrics, called Dynamic Graph Representation (DGR). Convolutional features onto certain regions are re-crafted by a graph generator to establish the connections among the spatial parts of biometrics and build Feature Graphs based on these node representations. Each node of Feature Graphs corresponds to a specific part of the input image and the edges express the spatial relationships between parts. By analyzing the similarities between the nodes, the framework is able to adaptively remove the nodes representing the occluded parts. During dynamic graph matching, we propose a novel strategy to measure the distances of both nodes and adjacent matrixes. In this way, the proposed method is more convincing than CNNs-based methods because the dynamic graph method implies a more illustrative and reasonable inference of the biometrics decision. Experiments conducted on iris and face demonstrate the superiority of the proposed framework, which boosts the accuracy of occluded biometrics recognition by a large margin comparing with baseline methods.