检索结果-内蒙古大学图书馆

Iris super-resolution using CNNs: is photo-realism important to iris recognition?

IET BIOMETRICS 2019年第1期8卷 69-78页

作者： Ribeiro, Eduardo Uhl, Andreas Alonso-Fernandez, Fernando Univ Salzburg Dept Comp Sci Jakob Haringer Str 2 A-5020 Salzburg Austria Fed Univ Tocantins Dept Comp Sci 109 NorteAv NS 15ALC 14 Palmas Brazil Halmstad Univ CAISR IS Lab Box 823 SE-30118 Halmstad Sweden

The use of low-resolution images adopting more relaxed acquisition conditions such as mobile phones and surveillance videos is becoming increasingly common in iris recognition nowadays. Concurrently, a great variety of single image super-resolution techniques are emerging, especially with the use of convolutional neural networks (CNNs). The main objective of these methods is to try to recover finer texture details generating more photo-realistic images based on the optimisation of an objective function depending basically on the CNN architecture and training approach. In this work, the authors explore single image super-resolution using CNNs for iris recognition. For this, they test different CNN architectures and use different training databases, validating their approach on a database of 1.872 near infrared iris images and on a mobile phone image database. They also use quality assessment, visual results and recognition experiments to verify if the photo-realism provided by the CNNs which have already proven to be effective for natural images can reflect in a better recognition rate for iris recognition. The results show that using deeper architectures trained with texture databases that provide a balance between edge preservation and the smoothness of the method can lead to good results in the iris recognition process.

关键词： edge preservation low-resolution images convolutional neural networks quality assessment Video signal processing feedforward neural nets Image recognition image resolution visual databases CNN architectures photo-realism iris recognition process near infrared iris images texture recovery realistic images texture databases training databases natural images Computer vision and image processing techniques feature extraction single image super-resolution techniques edge detection photorealistic image generation image texture surveillance videos mobile phone image database iris super-resolution Neural computing techniques objective function optimisation video signal processing iris recognition

来源：评论

学校读者我要写书评

暂无评论

Selective finite-states model predictive control of grid interfaced three-level neutral point clamped photovoltaic inverter for inherent capacitor voltage balancing

引用

IET POWER ELECTRONICS 2018年第13期11卷 2072-2080页

作者： Bonala, Anil Kumar Sandepudi, Srinivasa Rao Muddineni, Vishnu Prasad Natl Inst Technol Warangal Dept Elect Engn Hanamkonda 506004 Telangana India

A selective finite states model predictive control is proposed for a grid interfaced three-level neutral point clamped solar photovoltaic inverter. The proposed control approach eliminates the weighting factor selection for dc-link capacitor voltage balancing and reduces the computational burden for real-time implementation. The switching states required for the prediction and objective function optimisation are selected based on the position of reference voltage vector in the space vector plane, inverter current directions and the charge status of the dc-link capacitors. As a result, the selection of optimal switching state is fast, easy to implement and eliminates the selection of weighting factor for capacitor voltage balancing. The feasibility of the proposed control approach is verified through simulation and laboratory-scale experimentation. The results confirm that the proposed method attains the inherent dc-link capacitor voltage balance and also retains the dynamic and steady-state current tracking in comparison with the classical finite control-set model predictive control.

关键词： power grids invertors electric current control predictive control PWM invertors power capacitors voltage control power generation control photovoltaic power systems three-level neutral point inherent capacitor voltage balancing selective finite states model predictive control solar photovoltaic inverter control approach weighting factor selection dc-link capacitor voltage balancing switching states prediction objective function optimisation reference voltage vector space vector plane dc-link capacitors optimal switching state dc-link capacitor voltage balance dynamic state current tracking steady-state current tracking classical finite control-set model predictive control finite-states model predictive control

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient power allocation algorithm in cognitive radio networks

引用

IET COMMUNICATIONS 2016年第17期10卷 2445-2451页

作者： Zhou, Mingyue Zhao, Xiaohui Changchun Univ Technol Coll Comp Sci & Engn Changchun Peoples R China Jilin Univ Coll Commun Engn Changchun Peoples R China

Most of traditional power allocation algorithms are often based on maximum capacity technology (MCT) in cognitive radio networks (CRNs) at the expense of higher energy consumption. The optimisation of energy efficiency power allocation schemes are important performance in green communication. This study investigates the energy efficient power allocation for orthogonal frequency division multiplexing based CRNs in underlay mode. The authors' scheme is obtained by optimising an objective function consisting of the users' performance degradation and the network interference, in the same time to track time-varying target of signal to inference plus noise ratio (SINR) under maximum transmit power for each cognitive user and interference power constraint from primary user. A convex optimisation problem is formulated where the tradeoff between energy consumption and transmission capacity is considered, and a distributed algorithm is developed to solve this problem. Simulation results show that the authors' proposed algorithm can guarantee an acceptable target SINR for all cognitive users and significantly improves energy efficiency compared with throughput per Joule and MCT schemes. Furthermore, the proposed algorithm with the introduced appropriate weight parameters can get higher transmission capacity.

关键词： cognitive radio radio networks energy conservation energy consumption telecommunication power management convex programming radiofrequency interference environmental factors distributed algorithms target tracking OFDM modulation distributed algorithm transmission capacity convex optimisation problem primary user interference power constraint cognitive user maximum transmit power SINR signal to inference plus noise ratio time-varying target tracking network interference performance degradation objective function optimisation underlay mode orthogonal frequency division multiplexing green communication energy consumption CRN cognitive radio networks energy-efficient power allocation algorithm

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：