Localized Radon transform-based detection of ship wakes in SARimages

Presents a Radon transform-based approach to the detection of ship wakes in synthetic aperture radar (SAR) images. The key element of this technique is a localization of the Radon transform, whereby the intensity integration is performed over short line segments rather than across the entire image. A linear feature detection algorithm, which utilizes this localized Radon transform, is then developed. In this algorithm, referred to as the feature space line detector algorithm, the transform space is subjected to processing which serves to isolate and locate the response of linear features and suppresses the response of false alarms. This algorithm is tested on both synthetic images corrupted by various levels of Weibull multiplicative noise and on actual SAR images of ship wakes. The results of this testing demonstrate the algorithm's robustness in the presence of noise, as well as its ability to detect and localize linear features that are significantly shorter than the image dimensions     

On-board selection of relevant images: an application to linearfeature recognition

We propose an on-board selection scheme for aerial and space images, based on linear feature detection in a feature hyperspace. The detection task is performed by means of the Radon transform (RT) and the wavelet transform; a fast algorithm for the RT computation is described, and counteractions against the discretization errors are proposed. A new, wavelet-based algorithm is introduced, which performs a fine analysis of the waveforms of the RT peaks, yielding a possibly error-free detection in images corrupted by a high level of noise. A technique, based on the feature hyperspace, is proposed, able to significantly exploit all the available pieces of information on these peaks. Results of the tests on synthetic and real images are reported, which show that this method achieves satisfactory results, making the detection task highly reliable in the presence of both noise and clutter.     

An efficient Fourier method for 3-D radon inversion in exactcone-beam CT reconstruction

The radial derivative of the three-dimensional (3-D) radon transform of an object is an important intermediate result in many analytically exact cone-beam reconstruction algorithms. The authors briefly review Grangeat's (1991) approach for calculating radon derivative data from cone-beam projections and then present a new, efficient method for 3-D radon inversion, i.e., reconstruction of the image from the radial derivative of the 3-D radon transform, called direct Fourier inversion (DFI). The method is based directly on the 3-D Fourier slice theorem. From the 3-D radon derivative data, which is assumed to be sampled on a spherical grid, the 3-D Fourier transform of the object is calculated by performing fast Fourier transforms (FFTs) along radial lines in the radon space. Then, an interpolation is performed from the spherical to a Cartesian grid using a 3-D gridding step in the frequency domain. Finally, this 3-D Fourier transform is transformed back to the spatial domain via 3-D inverse FFT. The algorithm is computationally efficient with complexity in the order of N ³ log N. The authors have done reconstructions of simulated 3-D radon derivative data assuming sampling conditions and image quality requirements similar to those in medical computed tomography (CT)     

基于组合特征和HSI颜色空间的阴影检测

为了更有效地检测视频序列中的阴影,提出基于组合特征和HSI颜色空间的阴影检测算法.对提取的前景,先采用扩展的不变矩和Gabor小波变换分别抽取待识别区域的全局特征和局部特征来建立组合特征向量,再通过建立的HSI空间的阴影颜色模型来准确检测出目标的阴影.实验结果表明,该算法具有良好的阴影检测效果.     

一种基于Fourier变换的人脸识别算法

针对现有的多数人脸识别算法在单训练样本时识 别性能并不理想这一问题,提出一种基于Fourier-Mellin变换的频域不 变性以及时域不变性的特征提取算法。首先,采用图像亮度作为原始特征,将对图像亮度标 准化以改善光照变化,通过应用2D小波变换降维来管理频域不变量的复杂度;然后,为进一 步改进识别性能,根据分析的Fourier-Mellien变换(AFMT) 以及正交Fourier-Mellin矩(OFMM)法不变量的特征,将两种算法混合,进行特征提取; 最后,利用分值标准化度量频域不变量与时域不变量,并存储到一个特征向量中用于分类。 通过最近邻分类器(NNC)和相关性系 数法(CCM)进行分类和融合。通过在YALE与ORL人脸数据库上进行了大量实验的结果表明, 本文提出方法的性能要优于传统的人脸识别算法。     

基于多尺度结构特征的快速异源图像匹配

针对异源图像提出一种基于多尺度密集结构特征的快速匹配算法。算法首先利用Gabor滤波器逐像素提取图像中的结构响应,再根据主方向响应对多尺度结构特征融合,然后使用快速傅里叶变换在频域计算各特征分量图像之间的卷积,最后将卷积生成的系数矩阵求和计算出图像之间的相似性并选择相似性最大位置作为匹配结果输出。本文算法能有效适应异源图像间的非线性灰度变化和噪声干扰问题。测试使用可见光、红外、雷达图像组成的异源图像数据集对本文算法和现有算法进行测试比较,结果表明:本文算法的平均误匹配率最低,并且计算速度有明显优势。     

基于Radon变换的多尺度虹膜特征提取算法

系统分析了基于虹膜特征的身份识别系统.针对典型预处理特点,设计了基于Radon变换的新特征提取算法.该算法在保持旋转、平移和尺度缩放不变性的同时,利用标准化方差加权的绝对距离,使识别准确度达到了93%.这种算法对于其它不规则图像的分析也具有启发意义.     

基于trace特征的ISAR像空间目标识别

论文提出了一种基于trace特征的逆合成孔径雷达（Inverse Synthetic Aperture Radar,ISAR）像空间目标识别算法.首先将ISAR像进行分割与归一化处理,利用Canny边缘检测、Hough变换方法提取空间目标ISAR像最长轴,确保所提特征具有旋转不变性;然后仅对最长轴所在局部区域进行Trace变换生成空间目标ISAR像的局部trace矩阵,使得所提trace特征满足低维要求;再将trace矩阵每一列向量进行移位对准操作以消除ISAR像平移对识别带来的影响并将其作为空间目标识别的特征向量;最后在特征空间内以最小欧氏距离作为不相似度,采用集成分类器AdaBoost.M2-KNN完成了5类空间目标的分类识别.通过5类空间目标的ISAR数据对该方法进行目标识别验证,并与现有的几种ISAR像特征提取方法进行了对比.结果表明论文所提算法可行有效,可以明显地提高识别率.     

基于局部特征差异的异源图像融合算法

针对现有异源图像融合多以光学 图像为主、合成孔径雷达 (SAR)图 为辅和 光学图像 极易受 传播媒介 干扰 且 不 能同时保留纹理细节与颜色信息 等 问题, 提出一种新的基于局部特征差异的异源图像融合算法。 首先通 过 自适应分割 将 SAR 图像划分为规则特征区和不规则特征区两个区域;然后 进行 平移不变 离散 小波变换(SIDWT), 再根据 局部特征差异 性 设计 融合规 则,将 SAR 图像与全色遥感(PAN)图像的 小波系数 进行融合 , 以期保留图像的特征 信息与色彩信息 ;最后 通过 信息量 、 清晰度等 客观 评价指标 对 融合结果进行评价与分析 。 仿真实验 证明 了算法的有效性。     

基于SVM的静态手写签名识别方法研究

研究离线（静态）签名文字识别的问题.针对静态手写签名只有空间信息,没有时序信息的问题,提出了一种基于支持向量机的签名文字识别算法.算法首先通过图像预处理提取签名图像,然后利用防射变化对初始签名图像进行配准和矫正,并在此基础上利用滑动窗口在不同方向上提取特征.最终的识别器训练利用支持向量机完成.通过仿真实验证明,提出的新的方法较其他方法具有更高的识别准确率,可以有效的实现离线签名字体的识别,该技术可应用在个人身份认证和识别系统中.     

基于点不变特征的亚像素级图像配准技术

图像匹配是图像处理和计算机视觉领域的一个基础问题,它源自多个方面的实际问题.点特征匹配的首要任务就是提取稳定的特征,并进行描述.该特征能对旋转、尺度缩放、仿射变换、视角变化、光照变化等图像变化因素保持一定的不变性,而对物体运动、遮挡、噪声等因素也保持较好的可匹配性.提出一种基于点的尺度、旋转不变特征变换（SIFT）算法的亚像素级图像配准算法,首先在尺度空间进行特征检测,并确定关键点的位置和关键点所处的尺度,然后使用关键点邻域梯度的主方向作为该点的方向特征,以实现算子对尺度和方向的无关性.该方法具有旋转、尺度缩放、亮度变化不变性,对视角变化、仿射变换、噪声也保持一定程度的稳定.独特性好,信息量丰富,适用于在海量特征数据库中进行快速、准确的匹配.高速性,该匹配算法可以达到实时的要求.     

VOIR: a volumetric image reconstruction algorithm based on Fouriertechniques for inversion of the 3-D Radon transform

A novel volumetric image reconstruction algorithm known as VOIR is presented for inversion of the 3-D Radon transform or its radial derivative. The algorithm is a direct implementation of the projection slice theorem for plane integrals. It generalizes one of the most successful methods in 2-D Fourier image reconstruction involving concentric-square rasters to 3-D; in VOIR, the spectral data, which is calculated by fast Fourier techniques, lie on concentric cubes and are interpolated by a bilinear method on the sides of these concentric cubes. The algorithm has great computational advantages over filtered-backprojection algorithms; for images of side dimension N, the numerical complexity of VOIR is O(N(3) log N) instead of O(N (4)) for backprojection techniques. An evaluation of the image processing performance is reported by comparison of reconstructed images from simulated cone-beam scans of a contrast and resolution test object. The image processing performance is also characterized by an analysis of the edge response from the reconstructed images.     

湍流退化图像相位恢复算法研究

为克服气动光学效应对目标图像的影响．把相位恢复算法与气动光学效应机理研究结合起来,用于湍流退化图像的恢复。该算法是通过目标图像的傅里叶变换幅值来恢复目标图像,或等价地,恢复傅里叶变换相位。讨论了两类相位复原算法——迭代傅里叶变换（研）和解相关算法。对现有的解相关算法作了改进。采用共轭梯度法解高斯一牛顿方程,可有效提高算法的收敛速度。研算法不能保证迭代过程总能收敛到正确解,有时会出现停滞现象。将研和解相关算法组合起来,可以克服IFT算法的停滞现象,提高正确收敛率。给出了在信噪比为20dB情况下的湍流退化仿真图像恢复的实例,目标图像能较清晰地恢复出来。实验结果表明该算法具有较好的稳定性和抗噪声能力。     

基于频域信息融合和稀疏贝叶斯学习的高分辨ISAR成像

为了在ISAR成像中更好地压制噪声,消除条纹干扰,提高成像分辨率,本文提出一种基于双向插值处理和频域信息融合的稀疏贝叶斯学习算法,称之为BI?FF SBL算法。该方法首先对回波信号分别进行径向和横向插值预处理,将预处理得到的两份数据通过LA?VB算法进行ISAR成像;然后将得到的两幅ISAR图像通过二维傅里叶变换进入频域,并将两个二维频谱进行信息融合处理,以消除噪声和条纹干扰的相关信息并保留目标结构信息;最后对融合处理后的频谱进行二维傅里叶逆变换,得到最终的ISAR图像。为了验证BI?FF SBL算法的ISAR成像效果,本文进行了基于仿真数据和实测数据的成像实验,并将实验结果与R?D算法、L1?BP算法、LA?VB算法进行对比,发现BI?FF SBL算法在压制噪声和去除条纹干扰方面具有明显的优势,且能提供分辨率更高的ISAR图像。当实验数据信噪比降到0 dB时,BI?FF SBL算法依然能够提供清晰的ISAR图像,明显优于其他三种算法。测试超分辨重构误差的实验结果表明,相比于L1?BP算法和LA?VB算法,BI?FF SBL算法的重构误差更低,在实验数据信噪比为0 dB时,重构信噪比可以达到13.55 dB。     

应用复双谱对角切片的雷达多目标特征提取

提出了应用Chirp-z变换把依赖于傅里叶变换的双谱对角切片扩展为可在z平面上选择任意变换路径和任意频率分辨率的复双谱对角切片,并作为多目标模式的分类特征,能获取双谱以外的可分性特征。为压缩特征维数,选择可分性最好的特征,提出了实用的距离准则,在两类模式情况下,该准则等于Fisher准则,用于多类模式比Fisher准则更易于选择特征。最后应用上述方法,给出了雷达多目标特征提取的实验结果。     

基于小波包变换与RBF网络的大地目标辨识

利用正交小波包变换的高信号时频分辨特性引入小波包能量特征提取法，用于五类典型大地目标的特征提取和距离可分性测度计算。结果显示，小波包能量特征提取法提取的五类典型大地目标特征具有更好的可分性。将小波包能量特征提取法与径向基函数网络相结合，提出了一种大地目标辨识算法。仿真实验表明，对于分解层次m＝5，信噪比SNR≥0dB，五类典型大地目标能完全辨识。表明该大地目标辨识方法在一定条件下是可行的，具有强的抗噪声干扰能力。     

基于空间映射复Directionlet变换的图像纹理分类

Directionlet变换具有多方向各向异性基函数,能有效捕捉图像的奇异性特征。该文在此基础上构造了一种空间映射的复Directionlet变换,使其具备了更为灵活的方向选择性和近似的平移不变性。利用空间映射方法获得Directionlet变换的复函数空间,对多尺度各方向子带系数提取能量特征用于图像纹理分类。通过对Brodatz图像库及真实SAR图像的纹理分类实验表明,该文算法较之小波分析及其它多尺度几何分析方法,具有更优的纹理分类性能,也验证了Directionlet工具在图像分析中的应用潜力。     

CCD noise removal in digital images.

In this work, we propose a denoising scheme to restore images degraded by CCD noise. The CCD noise model, measured in the space of incident light values (light space), is a combination of signal-independent and signal-dependent noise terms. This model becomes more complex in image brightness space (normal camera output) due to the nonlinearity of the camera response function that transforms incoming data from light space to image space. We develop two adaptive restoration techniques, both accounting for this nonlinearity. One operates in light space, where the relationship between the incident light and light space values is linear, while the second method uses the transformed noise model to operate in image space. Both techniques apply multiple adaptive filters and merge their outputs to give the final restored image. Experimental results suggest that light space denoising is more efficient, since it enables the design of a simpler filter implementation. Results are given for real images with synthetic noise added, and for images with real noise.     

改进的ASIFT算法在图像配准中的应用

SIFT算法具有良好的图像匹配性能,是图像匹配的经典算法之一。针对传统SIFT算法在仿射变换情况下匹配效果不佳、鲁棒性弱的不足,给出一种改进的图像配准方法。首先对图像进行中值滤波处理,去除噪声。然后对图像做仿射变换,提取图像的SIFT特征点进行匹配。最后通过随机抽样一致性方法消除匹配后初始匹配点中的错误匹配点,提高匹配精度。实验结果表明,与SIFT算法相比,提出的方法具有更好的仿射不变性,在平移、旋转、仿射变换情况下均能得到较高的匹配精度,并且有较好的鲁棒性。     

Parameter Estimation of LFM Signals Based on Scaled Ambiguity Function

A method based on the scaled ambiguity function for parameter estimation of LFM signals under noncooperative conditions is presented. In the proposed algorithm, the scaling principle is employed to remove the linear frequency migration brought by the coupling between the time variable and the lag variable. Afterward, the Fourier transform is performed for feature extraction of LFM signals on the centroid frequency versus chirp rate plane. The method avoids centroid frequency information loss, which is almost inevitable in the Radon-ambiguity transform. Furthermore, fractional lower-order statistics and the scaled ambiguity transform are combined to improve the performance in practical impulsive noise environments. Simulation results show that the fractional lower-order scaled ambiguity transform is robust for both Gaussian and impulsive noise, and it achieves significant performance improvement in a heavy noise environment.