Accurate iris segmentation, especially around the iris inner and outer boundaries, is still a formidable challenge. Pixels within these areas are difficult to semantically distinguish since they have similar visual characteristics and close spatial positions. To tackle this problem, the paper proposes an iris segmentation graph neural network (ISeGraph) for accurate segmentation. ISeGraph regards individual pixels as nodes within the graph and constructs self-adaptive edges according to multi-faceted knowledge, including visual similarity, positional correlation, and semantic consistency for feature aggregation. Specifically, visual similarity strengthens the connections between nodes sharing similar visual characteristics, while positional correlation assigns weights according to the spatial distance between nodes. In contrast to the above knowledge, semantic consistency maps nodes into a semantic space and learns pseudo-labels to define relationships based on label consistency. ISeGraph leverages multi-faceted knowledge to generate self-adaptive relationships for accurate iris segmentation. Furthermore, a pixel-wise adaptive normalization module is developed to increase the feature discriminability. It takes informative features in the shallow layer as a reference to improve the segmentation features from a statistical perspective. Experimental results on three iris datasets illustrate that the proposed method achieves superior performance in iris segmentation, increasing the segmentation accuracy in areas near the iris boundaries.

中文翻译：

---

用于虹膜分割的多方面知识驱动图神经网络


准确的虹膜分割，特别是虹膜内部和外部边界周围的分割，仍然是一个艰巨的挑战。这些区域内的像素很难在语义上区分，因为它们具有相似的视觉特征和接近的空间位置。为了解决这个问题，本文提出了一种虹膜分割图神经网络（ISeGraph）来进行精确分割。 ISeGraph将单个像素视为图中的节点，并根据多方面的知识构造自适应边缘，包括视觉相似性、位置相关性和特征聚合的语义一致性。具体来说，视觉相似性加强了具有相似视觉特征的节点之间的连接，而位置相关性根据节点之间的空间距离分配权重。与上述知识相反，语义一致性将节点映射到语义空间并学习伪标签以基于标签一致性来定义关系。 ISeGraph 利用多方面的知识来生成自适应关系，以实现准确的虹膜分割。此外，还开发了逐像素自适应归一化模块以提高特征辨别力。它以浅层的信息特征为参考，从统计角度改进分割特征。在三个虹膜数据集上的实验结果表明，该方法在虹膜分割方面取得了优异的性能，提高了虹膜边界附近区域的分割精度。