Image restoration of finger-vein networks based on encoder-decoder model

来源 :OptoelectronicsLetters | 被引量 : 0次 | 上传用户:a348329418
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
Finger-vein recognition is widely applied on access control system due to the high user acceptance and convince. Improving the integrity of finger-vein is helpful for increasing the finger-vein recognition accuracy. During the process of finger-vein imaging, foreign objects may be attached on fingers, which directly affects the integrity of finger-vein images. In order to effectively extract finger-vein networks, the integrity of venous networks is still not ideal after preprocessing of finger vein images. In this paper, we propose a novel deep learning based image restoration method to improve the integrity of finger-vein networks. First, a region detecting method based on adaptive threshold is presented to locate the incomplete region. Next, an encoder-decoder model is used to restore the venous networks of the finger-vein images. Then we analyze the restoration results using several different methods. Experimental results show that the proposed method is effective to restore the venous networks of the finger-vein images.
其他文献
Monte Carlo algorithm and Stokes-Mueller formalism are used to simulate the propagation behavior of polarized light in turbid media. The influence of single scattering and multiple scattering on backscattered Mueller matrix in turbid media is discussed. S
利用 532 nm皮秒脉冲激光在金纳米光栅表面诱导表面等离子体激发 CdSe量子点荧光,并测量了 CdSe量子点荧光增强效应。分别采用 AFM刻蚀方法和自组装方法在硅基金膜表面制备了纳米光栅/CdSe量子点的多层薄膜结构。通过调节皮秒脉冲激光的功率,在显微拉曼平台上测量了 CdSe量子点的荧光光谱。结果表明,金纳米光栅 /CdSe量子点结构能够实现量子点远场荧光大幅增强,其最大荧光强度达 7.80倍,并在达到最大强度点开始迅速饱和。该研究结果可广泛应用于光电器件、生物医学检测研究等领域。
为测量透明容器内液体的折射率, 建立了基于容器内表面反射率测量的低相干技术实验系统。系统采用宽带低相干半导体激光光源和改进的迈克尔逊干涉仪, 将装有待测液体的容器放入测量臂光路中, 调节参考臂的光程, 使由容器前壁内表面反射光的光程与来自参考臂反射光的光程相等, 出现干涉现象。捕捉并记录下此干涉信号, 并从中求出容器前壁内表面反射光的强度, 再结合菲涅尔公式及反射率的定义, 即可求出待测液体的折射率, 其测量精度与阿贝折射仪相当。方法能够方便、快捷、准确地测出容器内液体的折射率, 可用于食品、生物医学检验
本文评述了在美国海军研究所化学部进行的激光研究与发展计划。讨论了其对整个激光领域的影响,尤其是在化学激光器、激光过程的动力学和激光促进的化学反应的研究。略述了化学部的激光研究与激光应用的未来方向,描述了正在进行中的或者在计划中的少数几个特殊的实验。
期刊
金刚石中的氮-空位(NV)色心受到越来越多研究学者的青睐, 这种色心在量子信息应用领域具有非常好的自旋和光学性能。为了更好地研究这些性能, 精确探测金刚石中NV色心轴向信息非常必要。介绍了一种利用多束偏振光准确测量两个相邻NV色心组合包含的轴向信息的新方法, 该方法可以探测出在四种可能轴向中, 两个高度重合色心的轴向分布信息。
提出了一种基于非局部均值(NLM)滤波的相干激光雷达距离像去噪方法,结合滤波后的强度像和原始距离像、背景抑制(B-S)后的中值滤波和NLM滤波等图像融合方法,实现B-S和距离反常抑制。对不同载噪比的相干激光雷达多目标仿真图像进行了去噪处理。比较了Lee滤波等方法处理结果。实验结果表明,采用该方法,能够满足距离像背景噪声抑制、目标上距离值正常和边缘保持三方面要求。
Single-shot laser-induced damage threshold (LIDT) measurements of multi-type free-standing ultrathin foils were performed in a vacuum environment for 800 nm laser pulses with durations τ ranging from 50 fs to 200 ps. The results show that the laser damage
In order to research the influence on the beam transmission properties due to the different time intervals in the high-power pulsed transversely excited atmospheric CO2 laser with unstable resonator, the finite element analysis of thermodynamics instantan
The transverse trapping forces on a dielectric sphere located at an oil-water interface are theoretically investigated with the ray-optics model. The transverse trapping forces rely on the internal property of the particle-interface system, and increase w
视网膜血管分割是检测多种眼病的重要手段,在视网膜疾病自动筛查系统中发挥重要作用。针对现存方法对细小血管分割不足且易出现病理误分割的问题,提出了一种基于多尺度注意力解析网络的分割算法。该网络以编码-解码架构为基础,在子模块中引入注意力残差块,加强了特征传播能力,降低了光照不均、对比度低对模型的影响;在编码器和解码器之间增加跳跃连接并去掉传统池化层,以保留足够的血管细节信息;运用并行多分支结构和空间金