发表机构
Halmstad University（哈尔姆斯塔德大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究发现CNNs提取方向特征困难，提出用复杂结构张量作输入，结合小型复杂卷积网络及缩小的CNN规模，在眼周图像数据集实验中，该方法使误识率降低5%-26%，减轻了CNN表示限制，增强了可解释性。
AI 中文摘要
我们的研究表明卷积神经网络（CNNs）难以有效提取方向特征。我们发现，使用包含具有确定性的紧凑方向特征的复杂结构张量作为CNN的输入，与仅使用灰度输入相比，能持续提高识别准确率。实验还表明，由小型复杂卷积网络提供的输入与缩小的CNN规模相结合，优于成熟的主流CNN架构。这表明在CNN中预先使用方向特征，这一在哺乳动物视觉中可见的策略，不仅能减轻其局限性，还能增强其可解释性以及与瘦客户端的相关性。我们使用六种CNN架构，在包含眼周图像的公开数据集（Cross-Eyed和PolyU）上进行了实验，用于在封闭世界和开放世界场景中的生物识别和验证。我们在Cross-Eyed和PolyU数据集上的实验使误识率降低了5%-26%，有力地证明了显式方向先验在开放世界和封闭世界场景中减轻了CNN的表示限制。
英文摘要
Our study provides evidence that CNNs struggle to extract orientation features effectively. We show that using the Complex Structure Tensor, which contains compact orientation features with certainties, as input to CNNs consistently improves identification accuracy compared to grayscale inputs alone. Experiments also demonstrated that our inputs, provided by mini-complex convnets, combined with reduced CNN sizes, outperformed full-fledged, prevailing CNN architectures. This suggests that the upfront use of orientation features in CNNs, a strategy seen in mammalian vision, not only mitigates their limitations but also enhances their explainability and relevance to thin-clients. Experiments were conducted on publicly available datasets comprising periocular images (Cross-Eyed and PolyU) for biometric identification and verification in both Close-World and Open-World Scenarios using six CNN architectures. Our experiments on the Cross-Eyed and PolyU datasets yield a 5-26% reduction in EER, providing strong empirical evidence that explicit orientation priors mitigate CNN representational limits in Open-World and Close-World scenarios.
CommentsarXiv admin note: text overlap with arXiv:2404.15608
