局部遮挡下的目标识别算法

规格化互相关算法是用得较普遍的目标识别方法,但是当目标区域被局部遮挡时,该方法通常不能正确定位目标.提出了一种新的基于选择互相关系数的目标识别算法用于搜索有局部遮挡的目标区域.算法分两步进行:用增量互相关算法计算出模板图和场景图的增量图像,比较二者增量图像的一致性,计算出选择互相关系数矩阵;结合选择互相关系数矩阵,用规格化互相关算法在场景图中搜索目标区域.当场景图存在较严重的噪声时,可对选择互相关系数矩阵进行修正以克服噪声的影响.实验结果表明,基于选择互相关系数的目标识别算法对局部遮挡和高亮度变化情况有较强的鲁棒性.     

SMD缺陷检测中快速图像匹配算法研究

传统灰度归一化互相关匹配算法存在匹配时间太长及不适合旋转情况匹配的缺点.提出改进的层叠二分互相关匹配算法,通过将图像多次缩小一半后进行粗匹配,再依次返回到缩小之前的图像上进行小范围的精匹配来减小匹配时间;并提出旋转搜索窗口的方法来使算法适合旋转的匹配;通过使用增量法计算互相关值来进一步减小匹配时间;最后研究了改进的算法在SMD缺陷检测中的应用并进行实验测试,结果表明算法能够快速准确检测元件的位置偏移和角度偏转.     

交互式复杂纹理图像区块间互相关算法

传统纹理图像处理算法无法检测出多方向上图像重要信息,空间分布信息也会出现部分丢失,导致图像区块间的相关系数无法得到准确描述.提出交互式复杂纹理图像区块间互相关算法.选定图像中心点划分互相关区块,利用小波变换的平滑算法平滑不同图像区块,去除由噪声产生的极大值点,将多个边缘信息匹配并连接在一起,获取准确边缘信息.利用互相关算法计算处理后的区块系数,通过两个区块间互相关值与自相关值的偏差程度,准确描述区块间的互相关系数,实现交互式复杂纹理图像区块间互相关算法.仿真结果表明,除了图像区块自身相似偏差为0％外,相同文字图像区块之间的相似偏差为2.2％,不同文字图像区块的相似偏差均在21.4％以上.实验结果验证所提方法能够精准描述复杂纹理图像不同区块之间的相关程度,应用效果较好.     

基于互相关信息的图像目标检测方法研究

针对背景变化下运动目标的检测问题,采用一种结合互相关信息的目标检测算法,利用混合优化,Powll和粒子群(Pso)交替优化两幅图像间的互相关信息,直到互信息值最大,得到图像间的最佳平移旋转参数,将图像进行空间配准.最后采用三帧差分相乘法检测出目标并增强目标区域,实现运动目标的准确检测.通过对变化背景图像的运动目标检测仿真,结果证明了检测算法的准确性和可行性.     

基于亮度累加直方图的夜间车辆检测算法

为提高夜间环境下车辆检测的精度,提出一种基于亮度累加直方图的车辆检测算法,利用汽车尾灯的高亮特征检测自车前方车辆.通过统计大量的尾灯亮度信息得到分割阈值,由该阈值确定最大类间方差法的初始阅值.在亮度累加直方图中采用改进的最大类间方差法确定最佳分割阈值,并使用该阈值分割图像提取尾灯目标.结合尾灯的形状、位置和颜色等特征进行尾灯筛选和配对,以检测到的尾灯对为目标实现夜间车辆的检测.实验结果表明,该算法能够准确地分割出尾灯目标,对夜间前方车辆的检测率较高、适应性较好.     

一种用于图像认证的半脆弱数字水印算法

数字水印作为数字媒体版权保护的有效办法之一,近年来越来越为人们所重视.新型的基于CDMA调制可以进行图像认证的半脆弱数字水印算法.首先利用混沌序列生成的规格化序列将二值水印数据进行加密并扩频调制后嵌入到图像的DWT低频域,检测时利用规格化序列的特性不仅有效实现了盲检测,又实现了图像内容认证和图像的篡改定位.实验结果表明,算法对JPEG有损压缩、滤波和噪声等水印攻击显示出较强的鲁棒性.     

亮度特征自相关和GMM相结合的目标检测

基于混合高斯模型(GMM)的背景建模算法被广泛运用于运动目标检测,但在一些发生快速光照变化的视频序列中,不能正确地检测出运动目标。此外在对GMM参数进行初始化时,若初始化图像中存在运动目标,则目标检测的结果会出现初始化图像中的运动目标,从而导致误检测。针对上述问题,提出一种基于亮度特征自相关的GMM算法,该算法根据亮度特征自相关参数判断初始化图像中是否存在运动目标,利用亮度特征自相关参数的拟合值判断当前帧是否发生快速光照变化,运用GMM和亮度差值相结合进行目标检测。对实际摄取的视频进行仿真实验,结果证明,该算法在GMM初始化图像存在运动目标的干扰条件下,能够较好地从发生快速光照变化的视频序列中提取出运动目标,满足准确性和实时性的要求。     

低对比度红外图像点目标运动检测方法

对于背景对比度较低的红外图像,若点目标的亮度不明显,加上探测器噪声的影响,很难分辨出红外图像中处于运动状态的点目标.为了解决这一问题,对探测器采集的相邻2幅图像进行基于灰度峰值与傅里叶相位相关算法的图像配准,计算出2幅图像之间的相对平移量;通过对2幅图像的重叠区域进行差分绝对值、高斯低通滤波及二值化运算;分离出运动的点目标.实验结果表明:检测方法可以有效地检测出低对比度红外图像中的运动点目标.     

基于相关系数符号的快速匹配算法*

针对经典灰度相关匹配算法耗时多的缺点,提出一种减少计算次数、提高匹配效率的新方法.该方法是先构造一幅相关图像,然后计算它与基准子图像的互相关数据并利用其符号分离候选匹配点,最后在匹配过程中,根据实时图像与相关图像的相关系数符号来选定匹配点区域,从而减少匹配计算次数,提高匹配速度.理论分析和实验表明,该方法不但能够保持经典灰度相关匹配算法具有较高的匹配精度和较强的抗噪能力的特点,而且大大缩短了匹配时间,使得经典灰度相关算法能够在实际中得以应用.     

基于互相关边界特性和图像积分的快速模板匹配算法

基于归一化算法求解相似度原理,提出了综合利用互相关的边界条件和图像积分计算相似度的快速算法,在不降低匹配精度的前提下较大地提高了匹配速度。计算相似度时,归一化算法需要计算各位置的自相关值和互相关值,本算法先只计算自相关值,再利用Holder不等式原理,结合给定的边界阈值,剔除不满足条件的位置,减少其对应的互相关值计算。应用图像的积分进行匹配在于整个图像的积分可以在匹配之前进行计算,而在匹配过程中每一个子区域的自相关可以通过图像积分快速求得。本算法已在焊线机芯片识别系统中应用,结果表明该算法匹配的速度快而又不降低匹配精度,具有实际应用价值。     

归一化互相关系数在图像序列目标检测中的应用

提出一种基于归一化互相关系数的图像序列运动目标检测方法。该方法以基于模板的归一化互相关系数作为度量函数,可以有效地检测出运动阴影和运动目标,而且不需要对背景进行实时维护。实验表明,该方法对光照变化具有一定的鲁棒性。     

1D-based defect detection in patterned TFT-LCD panels using characteristic fractal dimension and correlations

Thin film transistor-liquid crystal display (TFT-LCD) is a major technology for flat panel display used in a wide range of electronic devices. As the TFT-LCD panel becomes dense, small defects can only be observed at an extremely high resolution. For fast imaging of a large-sized TFT-LCD panel at a high resolution, a one-dimensional (1D) line scan system is demanded. A TFT-LCD panel image at a fine resolution presents very complicated repetitive patterns, which increases the difficulty of the defect detection task. In this paper, we propose a 1D self-comparison defect detection scheme that directly works on the 1D line images of a TFT-LCD panel. The proposed method first uses the fractal transformation to enhance the periodicity and regularity of a 1D gray-level line image, and then divides the resulting fractal signal into small segments, each of the length of the repeated period. By calculating each divided segment’s normalized cross correlation with its neighboring segments and comparing the resulting correlation value with a predetermined threshold, the segments containing a defect can be effectively identified. Since the proposed method does not require a reference template, it is invariant to changes in illumination and image translation. Experimental results on a number of microdefects in patterned TFT-LCD panel surfaces show that the proposed method can well detect various ill-defined defects and is computationally very efficient.     

一种基于子块图像互相关的虹膜识别方法

虹膜识别是一种新兴的生物特征身份识别方法,在场所或资源的安全控制等方面具有重要的应用价值。该文提出了一种基于子块图像互相关的虹膜识别方法。在特征提取时,把图像划分为许多子块,计算两幅虹膜图像的对应子块间的归一化相关系数,并把最小的几个归一化相关系数去除掉,然后求得剩下的归一化相关系数的均值及方差,作为两幅虹膜图像的联合特征。这能够有效地减小图像强度的局部畸变对虹膜识别的影响。为了实现模式的非线性划分,判别函数采用径向神经网络来构造。最后,进行了小样本实验,实验结果表明,这种基于子块图像互相关的虹膜识别方法是可行的。     

A new approach to corner matching from image sequence using fuzzy similarity index

Corner matching in image sequences is an important and difficult problem that serves as a building block of several important applications of stereo vision etc. Normally, in area-based corner matching techniques, the linear measures like standard cross correlation coefficient, zero-mean (normalized) cross correlation coefficient, sum of absolute difference and sum of squared difference are used. Fuzzy logic is a powerful tool to solve many image processing problems because of its ability to deal with ambiguous data. In this paper, we use a similarity measure based on fuzzy correlations in order to establish the corner correspondence between sequence images in the presence of intensity variations and motion blur. The matching approach proposed here needs only to extract one set of corner points as candidates from the left image (first frame), and the positions of which in the right image (second frame) are determined by matching, not by extracting. Experiments conducted with the help of various sequences of images prove the superiority of our algorithm over standard and zero-mean cross correlation as well as one contemporary work using mutual information as a window similarity measure combined with graph matching techniques under non-ideal conditions.     

面向电力设备红外图像的温度值识别算法

为了快速准确地识别出红外图像中温度值实现缺陷检测，提出了面向电力设备红外图像的温度值识别算法。针对温度值区域背景复杂的问题，根据红外图像直方图自适应确定阈值进行预处理；结合轮廓与相对位置信息，准确定位温度值区域，并实现字符分割；建立温度值图像数据集，采用卷积神经网络进行训练和测试；基于MATLAB的App Designer模块，设计温度值识别与记录系统。结果证明，该算法对温度值识别准确率达到98.6%，高于传统的字符识别算法，能够实现快速识别与准确记录温度值，有效降低了电力巡检人员的劳动强度。     

多通道的小波域彩色图像水印算法

根据人类视觉系统的掩蔽特性和彩色感知特性，将伪随机二值水印序列不可感知地分别嵌入到每个彩色通道离散小波变换后的三个最大的细节子带中．水印检测利用三个彩色通道的互相关性，用联合相关值与门限作比较来判定图像中是否包含水印．文中算法在保证虚警概率为一个可允许值的约束条件下，最小化误检概率(Neyman-Pearson准则)，确定最优门限．新的门限选择机制仅仅依赖于嵌入水印后的图像，不需要水印能量等信息．实验结果证明了文中水印算法的有效性．     

心肌灌注核磁共振图像的非刚性配准

心肌灌注核磁共振图像中心脏的位置和形状会随着病人的呼吸和心跳而发生改变.同时,灌注图像的灰度也会随着造影剂在心腔中的流动而不断变化.这使得传统单纯依靠互信息、互相关等信息的配准算法很难在心肌灌注核磁共振图像中得到应用.使用马尔可夫随机场(M RF)模型对图像进行非刚性配准.在马尔可夫能量函数中对图像块进行归一化,以消除两幅图像的灰度差异对配准的影响.为了消除序列图像配准中产生的积累误差,对心肌灌注MR序列中的每幅图像计算对应的伪真实(PGT)图像,并将这幅伪真实图像作为配准模板.通过将心肌灌注MR序列中的每幅图像与其对应的伪真实图像进行配准,避免了序列图像配准中积累误差的产生.实验结果表明,该方法有效地矫正了心肌灌注MR图像中心脏的位移和弹性形变.     

Efficient normalized cross correlation calculation method for stereo vision based robot navigation

Stereo vision systems are widely used for autonomous robot navigation. Most of them apply local window based methods for real-time purposes. Normalized cross correlation (NCC) is notorious for its high computational cost, though it is robust to different illumination conditions between two cameras. It is rarely used in real-time stereo vision systems. This paper proposes an efficient normalized cross correlation calculation method based on the integral image technique. Its computational complexity has no relationship to the size of the matching window. Experimental results show that our algorithm can generate the same results as traditional normalized cross correlation with a much lower computational cost. Our algorithm is suitable for planet rover navigation.     

A self recoverable dual watermarking scheme for copyright protection and integrity verification

Dual watermarking implies embedding of robust as well as fragile watermarks into the same cover image. It facilitates integration of copyright protection and integrity verification into the same scheme. However, most of such existing state of art approaches either lacked the feature of tamper detection and original content recovery or provided an approximation using coarser block level approach. The proposed self recoverable dual watermarking scheme integrates all the aforementioned functionalities of copyright protection, tamper detection and recovery into one scheme. The scheme is independent of the order of embedding of robust and fragile watermarks as these are embedded in different regions of the cover image. It performs tamper detection and recovery, both at the pixel level. The scheme obtains recovery information for each 2×2 image block in just eight bits which are further encoded to only four bits via mapping table. This reduction in recovery bits allows efficient embedding of copyright information which is tested against comprehensive set of attacks. The scheme is found to be robust against noises, filtering, histogram equalization, rotation, jpeg compression, motion blur etc. Besides the normalized cross correlation value, the evaluation of the extracted copyright information is also being done using various objective error metrics based on mutual relation between pixels, their values and locations respectively. The imperceptibility and visual quality of the watermarked as well as recovered image is found to be satisfactorily high. Three major categories of images: natural, texture as well as satellite have been tested in the proposed scheme. Even minute alterations can be chalked out as the detection accuracy rate has been enumerated on pixel basis. The scheme can tolerate tampering ratios upto 50 percent though the visual quality of the recovered image deteriorates with increasing tampering ratio. Comparative results based on normalized cross correlation, probability of false acceptance, probability of false rejection and peak signal to noise ratio metrics validate the efficacy of the proposed scheme over other existing state of art approaches.     

基于最大目标函数的医学图像边缘检测

鉴于医学图像特点和传统算法的缺点,提出一种新的医学图像边缘检测算法,该算法通过考察3×3模板的理想边缘结构特征,将模板像素沿边缘方向分为两个集合,通过距离度量函数构造适当的目标函数,计算四个方向的目标函数值,从而获得最大目标函数值,并与给定的阈值比较,应用非极大抑制方法,判别该象素是否为边缘点,最后进行双阈值连接,可得到单像素边缘图像。仿真结果表明,该算法能够有效检测医学图像边缘,所检测出的图像边缘细节丰富,单像素宽,定位准确。