Constrained Design of Deep Iris Networks
Constrained Design of Deep Iris Networks
复制标题
DOI：
10.1109/tip.2020.2999211
复制
发表时间：
2019-05
影响因子：
10.6
通讯作者：
Kien Nguyen;C. Fookes;S. Sridharan
中科院分区：
文献类型：
--
作者：
Kien Nguyen;C. Fookes;S. Sridharan
尽管与传统技术相比，最近的深度神经网络有望提供更准确、更高效的虹膜识别，但经典IrisCode的一些重要属性几乎无法通过当前的深度虹膜网络实现：模型的紧凑性和少量计算操作（FLOP）。本文将虹膜网络设计过程转化为一个约束优化问题，将模型大小和计算量作为学习准则。一方面，这使我们能够完全自动化的网络设计过程，以搜索最佳的虹膜网络架构，具有最高的识别精度，仅限于计算和模型紧凑性约束。另一方面，它使我们能够研究经典的IrisCode和最近的深度虹膜网络的最优性。它还使我们能够学习最佳的虹膜网络，并以更少的计算和内存需求展示最先进的性能。
Despite the promise of recent deep neural networks to provide more accurate and efficient iris recognition compared to traditional techniques, there are vital properties of the classic IrisCode which are almost unable to be achieved with current deep iris networks: the compactness of model and the small number of computing operations (FLOPs). This paper casts the iris network design process as a constrained optimization problem which takes model size and computation into account as learning criteria. On one hand, this allows us to fully automate the network design process to search for the optimal iris network architecture with the highest recognition accuracy confined to the computation and model compactness constraints. On the other hand, it allows us to investigate the optimality of the classic IrisCode and recent deep iris networks. It also enables us to learn an optimal iris network and demonstrate state-of-the-art performance with less computation and memory requirements.