基于压缩感知与结构自相似性的遥感图像超分辨率方法

本文提出了一种基于压缩感知、结构自相似性和字典学习的遥感图像超分辨率方法,其基本思路是建立能够稀疏表示原始高分辨率图像块的字典。实现超分辨率所必需的附加信息来源于遥感图像中广泛存在的自相似结构,该信息可在压缩感知框架下通过字典学习而得到。这里,本文采用K-SVD方法构建字典、并采用OMP方法获取用于稀疏表达的相关系数。与现有基于样本的超分辨率方法的最大不同在于,本文方法仅使用了低分辨率图像及其插值图像,而不需要使用其它高分辨率图像。另外,为了评价方法的效果,本文还引入了一个衡量图像结构自相似性程度的新型指标SSSIM。对比实验结果表明,本文方法具有更好的超分辨率重构效果和运算效率,并且SSSIM指标与超分辨率重构效果具有较强的相关性。      

一种基于多字典学习的图像分割模糊方法

本文提出一种基于多字典学习的图像分割模糊模型和算法.在模型中,结合多字典学习和模糊方法,考虑了分割区域内部的一致性和边界的正则性：一方面使用区域块均值和带有类标的结构字典重构图像块,利用重构误差和l2正则能量共同度量分割区域内部的一致性,该度量能够刻画图像不同区域的灰度信息和纹理模式;另一方面采用小波系数稀疏正则保持分割区域边界的几何结构.基于交替方向乘子法和字典学习方法给出新模型的快速求解算法.在该算法中,除了小波阈值,每一步都是显示表达式,因此简单易用.一系列实验结果验证了本文算法的有效性.     

Fast Super‐Resolution Algorithm Based on Dictionary Size Reduction Using k‐Means Clustering

This paper proposes a computationally efficient learning‐based super‐resolution algorithm using k‐means clustering. Conventional learning‐based super‐resolution requires a huge dictionary for reliable performance, which brings about a tremendous memory cost as well as a burdensome matching computation. In order to overcome this problem, the proposed algorithm significantly reduces the size of the trained dictionary by properly clustering similar patches at the learning phase. Experimental results show that the proposed algorithm provides superior visual quality to the conventional algorithms, while needing much less computational complexity.     

某型电子信息系统模块级故障诊断技术研究

针对电子信息系统结构复杂、难于建立精确数学模型等特点，以某型电子信息系统为例，采用故障字典和BP神经网络相结合的方法，利用Multisim软件进行电路仿真。再由实测样本数据对BP神经网络进行训练，完成对网络各参数的设置。仿真结果表明，该方法可以较好地将故障定位到元器件，同时可为其他电子信息系统模块级故障诊断技术研究提供借鉴。     

基于文本理解的自动文摘系统研究与实现

本系统模拟人的理解、知识获取认知过程，利用全信息词典有效地组织语言学知识。背景知识和领域知识，利用部分分析器算法，实现语法语义语用分析一体化，从文本中提取重要信息，将任一篇文章转换为计算机内的一个信息提取框架实体．根据填充情况，由文摘生成器产生合适的文摘．目前已实现计算机病毒领域文章的自动文摘，验证了文摘模型的可行性和有效性．文摘系统模型与领域无关．     

一种新的数据持久层设计方法与实现

针对目前数据库模型改动将导致业务层和数据库层的大量数据修改的不足这一问题,提出建立新的框架即双重数据持久层框架的设计方法,该方法联合运用iBATIS数据持久层框架和数据字典技术来实现.当数据库模型需要变更时,可较方便地通过操作数据字典,来实现对数据持久层和数据库模型的同步维护,较大程度提高了工作效率,可移植性增强.     

移动基站电费管控措施探讨

从分析移动基站电费现状入手,深入研究了转供电改造模型的建立,通过对直供电改造中基站耗电量、电费单价、改造投资金额与投资回收年限关系的分析,提出直供电改造投资模型字典,可作为基站转供电改造选择依据,并对管理节能及电费管控的相关内容进行了深入研究。     

Extended linear regression for undersampled face recognition

Linear Regression Classification (LRC) is a newly-appeared pattern recognition method, which formulates the recognition problem in terms of class-specific linear regression with sufficient training samples per class. In this paper, we extend LRC via intraclass variant dictionary and SVD to undersampled face recognition where there are very few, or even only one, training sample per class. Intraclass variant dictionary is adopted in undersampled situation to represent the possible variation between the training and testing samples. Three types of methods, quasi-inverse, ridge regularization and Singular Value Decomposition (SVD), are designed to solve low-rank problem of data matrix. Then the whole algorithm, named Extended LRC (ELRC), is presented for face recognition via intraclass variant dictionary and SVD. The experimental results on three well-known face databases show that the proposed ELRC has better generalization ability and is more robust to classification than many state-of-the-art methods in undersampled situation.     

A realistic defect oriented testability methodology for analog circuits

Owing to the non-binary nature of their operation, analog circuits are influenced by process defects in a different manner compared to digital circuits. This calls for a careful investigation into the occurrence of defects in analog circuits, their modeling related aspects and their detection strategies. In this article, we demonstrate with the help of a real CMOS circuit that simple test stimuli, like DC, transient and AC, can detect most of the modeled process defects. Silicon devices tested with the proposed test methodology demonstrate the effectiveness of the method. Subsequently, the proposed test method is implemented in production test environment along with the conventional test for a comparative study. This test methodology is structured and simpler, therefore results in substantial test cost reduction.