基于椭圆傅里叶描述子的遥感图像配准算法

传统的基于点特征的图像配准算法在遥感图像配 准时提取的特征点数量大、分布密,易产生误匹配,导致特 征匹配的效率和精度低。为此,本文利用椭圆傅里叶描述子(EFD)能较好保留 形状信息的特点,提出了一种基于EFD的 图像配准算法,根据匹配的边界对预估变换参数,给出特征搜索范围,从而有效地提 高特征搜索的效率。实 验结果表明,所提出算法能有效抑制误匹配的产生,提升特征匹配的效率,尤其是对于纹理 丰富的大尺寸图像,提 升效果更加明显,验证了本文算法对遥感图像配准的适用性。     

基于粗糙集近似约简和SIFT特征的图像匹配算法

SIFT(Scale Invariant Feature Transform)描述符由于具有尺度、旋转和光照不变等特性在图像匹配领域获得了广泛的应用。但是,SIFT特征点采用128维特征向量表示,当图像特征点较多时,匹配算法所需的存储空间大、匹配时间长,且匹配精度不理想。针对以上问题,本文给出了一种基于Rough-SIFT描述符的图像匹配算法。首先,利用排序法求出图像的稳健特征点,然后为提高后续匹配处理运算效率,将粗糙集约简理论引入到基于SIFT特征的匹配算法中,通过构建一种新的近似约简算法来对稳健特征点的128维特征向量进行降维处理,最后利用约简后的特征点对图像进行匹配。仿真实验表明, 本文方法使得约简后的SIFT特征点更加精确、稳定、可靠,有效减小了匹配算法的存储空间,提高了匹配算法的效率和准确率。      

A novel local octa-pattern feature descriptor for image retrieval

The local tetra patterns (LTrPs) gives four-directional information and ignores the diagonal pixel information, thereby affecting the retrieved image efficiency. In the present work, a novel retrieval approach has been proposed using local octa-patterns (LOcPs) for content-based image indexing and retrieval. The proposed approach encodes the center pixel directional information with its eight adjacent neighbors, from the directions that are computed using the first-order derivatives. Also the nth-order LOcP is computed using \((n-1)\)th-order local direction variations. In addition, the performance of the developed method by combining it with the Gabor transform has been analyzed. The performance of the proposed technique has been compared to existing techniques like LBP, LTP, LDP, and LTrP on Corel-1000 database (DB1) and Describable Textures Dataset (DB2). The performance observed shows that the developed method improves the retrieval parameters from 75.9%/77.13% to 79.4%/81.5% in the form of average precision on DB1/DB2 databases.     

一种新的ISAR距离对齐算法

距离对齐是逆合成孔径雷达(ISAR)成像处理中的或对齐精度不够高,或运算效率过低,无法满足ISAR实时成像的要求.由于距离对齐算法本质上是一种优化方法,基于优化原理,将启发式方法与搜索法相结合,提出了一种新的距离对齐算法.该算法结合使用频域法和累积互相关法,具体分两步实现:首先利用频域法进行粗对齐,然后将第一步得到的结果作为启发式信息进行累积互相关,大大减小了其搜索范围,得到了精确的距离对齐效果.通过将新算法与其他算法的运算量进行分析比较,结果表明该算法运算效率较高.而对实测数据的成像处理结果证明该算法具有良好的对齐精度.这说明新算法在效率和性能上达到了良好的平衡,适合于ISAR实时成像.     

基于透视不变二值特征描述子的图像匹配算法

针对基于局部特征的图像匹配算法普遍存在对透视变换顽健性差的缺点,提出了一种新的二值特征描述子PIBC（perspective invariant binary code）,提高了图像匹配算法的透视变换顽健性。首先,在提取金字塔图像FAST特征点的基础上,利用Harris角点响应值去除非极大值点和边缘响应点;其次,通过模拟相机不同视角成像之间的透视变换,对单个FAST特征点生成不同视角变换下图像的二值描述子,使描述子具备描述不同视角图像中同一特征点的能力。实验结果表明,算法在提高描述子透视不变性的同时时间复杂度与SURF算法近似。     

基于接触式图像传感器的自动光学检测系统研究

为了检测印刷电路板（PCB）通孔的缺陷,提出一种基于接触式图像传感器（CIS）的自动光学检测（AOI）系统。系统采用线性光源从PCB异侧打光的方法来得到均匀的、亮度足够的光线,并使用相关双采样的方式来抑制和消除CIS产生的噪声,在对图像采样、量化后使用特定的补偿因子对CIS上一列光电传感器之间输出值的偏差进行修正。实验表明,本系统工作稳定,成本低廉,能很好地满足工程需求。     

Distributed network platform for automatic optical inspection

Network bandwidth is a bottleneck for multipoint industrial automatic optical inspection. To avoid this constraint, a platform that integrates image acquisition and processing power to allow local processing is proposed. The reduction of network bandwidth requirements is discussed. The performance and feasibility is briefly discussed through preliminary experimental results.     

A new automatic alignment technology for single mode fiber-waveguide based on improved genetic algorithm

A novel automatic alignment algorithm of single mode fiber-waveguide based on improved genetic algorithm is proposed. The genetic searching is based on the dynamic crossover operator and the adaptive mutation operator to solve the premature convergence of simple genetic algorithm. The improved genetic algorithm combines with hill-climbing method and pattern searching algorithm, to solve low precision of simple genetic algorithm in later searching. The simulation results indicate that the improved genetic algorithm can rise the alignment precision and reach the coupling loss of 0.01 dB when platform moves near 207 space points averagely.     

光路自动准直中的全自动化控制算法

基于光路准直的基本原理,借助反射镜伺服系统的精密调节和计算机的自动控制,提出了全新的光路自动准直控制算法。在此基础上,建立了光路自动准直单元,编制了控制程序,对光路自动准直算法进行了实验验证。结果表明,采用该算法的光路自动准直单元完全实现了光路的自动准直,具有良好的通用性。提出了几种提高光路自动准直效率的方法。     

Iterative algorithm for automatic alignment by object transformation

Mathematical model for automatic alignment of wafers was derived under the assumption of the ideal condition of alignment marks. Because wafers were fabricated under non-ideal conditions at the factory level, the wafers were difficult to align during the manufacturing process. The errors from the distortion were reduced by repeated application of an ideal alignment sequence algorithm. The alignment algorithm, which was modified to be iterative, is based on the object transformation and is composed of matrix operations like a linear model. The convergence speed of the iteration could be varied by use the convergence constant η. The accuracy of the algorithm was demonstrated by a dicing machine used in an experiment. The alignment was repeated until the error was under the tolerance level of the inspection system. The convergence constant was varied to monitor its effect on iterative alignment speed. The result showed that this iterative algorithm was simple but accurate enough for application at the manufacturing level.     

基于特征的自动图像配准算法

提出了一种基于特征的自动图像配准算法，它利用角点检测和相关运算在给定源图像和目标图像上自动寻找侯选匹配点，利用松驰过程确定对应特征点。算法在大多数情况下能自动完成。从实验结果看，该算法获得了理想的拼合效果。     

基于图像识别的钻头自动跟踪算法

针对当前方法进行钻头自动跟踪过程中,难以对钻头目标模板进行精确描述且运算较为复杂,存在跟踪误差大的问题,提出一种基于图像识别钻头自动跟踪方法。该方法利用双重卷积理论对钻头原图像进行阈值分割,提取钻头运动图像目标,将提取的钻头运动图像目标进行滤波处理,获得钻头图像的归一化中心矩,采用高斯模型对钻头运动图像目标和背景建模,在此基础上将卡尔曼滤波预测估计思想和均值漂移思想相融合,应用于钻头运动图像目标跟踪过程中,由此完成对钻头的自动跟踪。实验结果表明,所提方法能够有效提升钻头运动图像目标的检测精度,且目标跟踪的稳定性较强。     

A novel colour image encryption algorithm based on chaos

In this paper, a novel colour image encryption algorithm based on chaos has been proposed. We use chaotic system to encrypt the R, G, B components of a colour image at the same time and make these three components affect each other. So the correlations between R, G, B components can be reduced and the security of algorithm is increased. Simulation results show that the proposed algorithm can encrypt colour image effectively and resist various typical attacks.     

基于傅里叶梅林预处理的SIFT图像拼接算法

对于图像存在旋转和尺寸缩放而导致的图像拼接质量不理想的问题,提出了基于傅里叶梅林预处理的SIFT图像拼接算法.算法首先利用傅里叶梅林计算图像的计算两幅图像的缩放比例和旋转角度,然后对图像的缩放比例和旋转角度进行调整,最后通过尺度不变特征变换(SIFT)算法进行图像的拼接.实验结果表明,改进的算法匹配的特征点数量增加了1...     

基于Otsu算法的图像阀值自动选取算法研究与应用

针对图像处理在追踪运动物体领域的应用,选择Otsu图像分割算法进行研究分析,给出了该算法的C++程序代码。为验证算法在工程应用领域的有效性和准确性,将其应用到车辆目标检测系统中,该系统以运动目标检测与跟踪为出发点,通过读取视频帧、帧差处理、Otsu分割、形态学处理,连通分量分析进行目标检测,从而实现跟踪汽车运动的目的。最后在Opencv2．4．8和微软VS2010环境下对Otsu算法在该系统的应用进行测试,结果表明,Otsu算法能够快速高效的进行车辆检测及跟踪定位,具有较好的工程应用价值。     

An electron image projector with automatic alignment

An electron image projector for silicon device processing is described which uses an air-cored solenoid and a caesium iodide photocathode. The alignment method is based on the X-rays which are generated when high-voltage electrons strike matter. Phase sensitive detection is used to convert the off balance to a linear signal which is then fed back into analog electronics. Results are presented showing a marker pattern automatically aligned to an accuracy of 0.1 µm.