论文标题
orcnet：基于上下文的网络，用于同时分割眼部区域
ORCNet: A context-based network to simultaneously segment the ocular region components
论文作者
论文摘要
准确提取感兴趣区域对于成功的基于眼部区域的生物识别技术至关重要。在这个方向上，我们提出了一种新的基于上下文的分割方法，标题为“眼部区域上下文网络（ORCNET）”，引入了特定的损失函数，即他惩罚上下文损失（PC-loss）。 PC-loss通过使用地面真相和分段蒙版之间的百分比差值来惩罚网络的分割损失。我们通过考虑Biederman的语义关系概念来获得百分比差异，其中我们使用三种上下文（语义，空间和比例）来评估图像中对象的关系。我们的建议在评估的方案中取得了令人鼓舞的结果：虹膜，巩膜和所有（虹膜 +巩膜）细分，对文献基线技术进行了UTPerforment。具有RESNET-152的ORCNET的表现平均优于最佳基线（带有RESNET-152）的基线，分别在F-SCORE，错误率和联盟的交叉路口方面分别为2.27％，28.26％和6.43％。我们还（出于研究目的）为Miche-I数据库提供了3,191个手动标记的面具，作为我们工作的另一个贡献。
Accurate extraction of the Region of Interest is critical for successful ocular region-based biometrics. In this direction, we propose a new context-based segmentation approach, entitled Ocular Region Context Network (ORCNet), introducing a specific loss function, i.e., he Punish Context Loss (PC-Loss). The PC-Loss punishes the segmentation losses of a network by using a percentage difference value between the ground truth and the segmented masks. We obtain the percentage difference by taking into account Biederman's semantic relationship concepts, in which we use three contexts (semantic, spatial, and scale) to evaluate the relationships of the objects in an image. Our proposal achieved promising results in the evaluated scenarios: iris, sclera, and ALL (iris + sclera) segmentations, utperforming the literature baseline techniques. The ORCNet with ResNet-152 outperforms the best baseline (EncNet with ResNet-152) on average by 2.27%, 28.26% and 6.43% in terms of F-Score, Error Rate and Intersection Over Union, respectively. We also provide (for research purposes) 3,191 manually labeled masks for the MICHE-I database, as another contribution of our work.
