基于迭代顺序滤波子空间约束的可拒识-支持向量机微钙化点检测

为提高钙化点检测速度,克服微钙化点检测中假阳性高的缺点,本文构造了一种迭代顺序滤波子空间约束的可拒识-支持向量机分类器用于钙化点检测.训练时利用迭代顺序滤波检测作为钙化点的粗检测算子,然后在其约束的子空间内收集非钙化点训练样本.对于输入模式,首先利用基于最大软间隔超平面的支持向量分类器(SVC)进行分类判决;然后对真实的钙化点样本特征空间求取最小的包含球形边界,得到钙化点样本的球形支持向量域表示(SVDD).对于输入模式即可利用钙化点的支持向量域表示进行拒识或接受处理.仿真实验结果表明,本文提出的算法在不影响微钙化点的检出率的情况下,大大提高了检测速度,部分解决了假阳性高的问题.     

采用尺度空间理论的红外弱小目标检测方法

为了检测红外场景中尺寸大小变化的弱小目标,针对传统滤波方法中固定大小滤波核对此类特性目标检测表现出的不足,提出一种基于尺度空间理论的红外弱小目标检测方法。首先对弱小目标特性进行分析,提出采用点扩散函数形式的目标模型来描述弱小目标;采用固定自适应邻域的方法对原始红外图像进行预处理,抑制背景杂波,增强目标能量;依据尺度规范化后的拉普拉斯尺度空间对图像不同元素滤波响应的不同,获取图像中的可疑目标,利用可疑目标点与其周围像素的梯度关系得到可疑目标点的中心坐标,并据此得到其在图中的尺寸大小;对每个可疑目标划分一个自适应大小窗口,获取分割阈值,分割出真实目标。实验结果表明,该方法能较好地检测出弱小目标,且具有较低的虚警率。     

改进的Harris算法在海洋遥感图像处理中的应用

研究HY-1B卫星水色图像数据时需要先对水域进行定位,一般采用轮廓明显的海岸线来辅助附近海域的定位。为了克服基于传统Harris角点检测算法带来的漏检、定位精度差等问题,提出一种改进Harris角点检测算法。在双边滤波预处理图像后引入多尺度空间表示,最终对候选角点集进行分组检测选取出最小尺度下的角点作为最佳角点。实验结果表明,改进的算法提高了角点检测率并且减少了冗余角点数量,优于多尺度Harris算法和Harris-Laplace算法。     

采用各向异性尺度空间的遥感图像配准

基于多特征点的遥感图像配准方法应用在油田遥感图像上时,很难为其找到足够多的正确对应关系且花费时间也较长.为此,提出了基于各向异性尺度空间的遥感图像配准方法.该算法首先使用自适应的侧窗滤波技术构建各向异性尺度空间,然后采用改进的邻域分块思想进行特征描述,最后使用增强的匹配点过滤增加特征点匹配的数量.实验结果表明,所提方法不仅保证了配准精度在90％以上,而且在速度上比原算法提高了10％以上.     

基于多尺度方向局部极值滤波和ASR的图像融合

为了更好地提取源图像的边缘和方向信息,充分利用边缘保持滤波器的保边缘特性和方向滤波器有效提取方向信息的能力,提出一种基于局部极值滤波和非下采样方向滤波器的多尺度方向局部极值滤波图像融合方法。源图像经多尺度方向局部极值滤波,得到低频子带以及一系列的高频方向细节子带,对低频子带系数提出一种基于自适应稀疏表示(ASR)的融合规则,采用空间频率与l1范数相结合的策略得到融合的稀疏表示系数,对高频方向细节子带系数提出一种基于改进拉普拉斯能量和匹配度的选择与加权平均相结合的融合策略。实验结果表明,本方法能够有效提取源图像的边缘等细节信息,融合结果对比度更高,具有更好的主观视觉效果,其客观评价指标也优于传统的图像融合方法。     

基于改进OS-SIFT的可见光与SAR图像自动配准

针对尺度不变特征变换（SIFT）算法配准可见光和合成孔径雷达（SAR）图像时性能较差的问题,提出了一种基于改进光学-SAR图像的SIFT(OS-SIFT)可见光和SAR图像配准算法。首先,利用非线性扩散滤波构建可见光和SAR图像的非线性扩散尺度空间,并采用多尺度Sobel算子和多尺度指数加权均值比算子分别计算可见光和SAR图像的一致性梯度信息。然后,用图像分块策略剔除尺度空间第一层后对尺度空间进行分块,在一致性梯度信息的基础上提取Harris特征点,得到稳定且均匀的点特征。基于梯度位置和方向直方图模板构建描述符并对其进行归一化处理,以克服影像间的非线性辐射差异。最后,利用欧氏距离进行特征匹配,并采用快速抽样一致性算法剔除误匹配。实验结果表明,相比联合位置、尺度和方向的SIFT算法和OS-SIFT算法,本算法的匹配率有明显提高,均方根误差也相对较低。     

Savitzky-Golay滤波和L1范数优化相结合的视频稳像算法

近年来,越来越多的人利用手持设备拍摄视频表达自己或社会问题等,这类视频常存在抖动现象,如何消除视频序列中的随机抖动成为近年来的研究热点。本文面向视频去抖动应用场景,提出了一种Savitzky-Golay滤波和L1范数优化相结合的视频稳像算法。首先基于帧间配对特征点进行运动估计;然后利用Savitzky-Golay滤波算法进行路径平滑处理,去除运动路径中的高频抖动分量,避免了噪声对后续生成稳定路径的影响;进一步,对平滑后的有效路径信息进行基于优化的L1范数优化算法拟合,得到最终的稳定路径;最后对原始视频图像序列进行运动补偿,生成稳定的图像序列。对比实验结果表明,本文方法稳像效果优于原始L1范数优化算法,算法速度快于目前效果较好的二维稳像算法。      

基于改进局部不变特征的兴趣点匹配

该文提出了一种适用于目标跟踪的局部特征点检测与匹配方法,在尺度不变特征(Scale Invariant Feature Transform, SIFT)算法基础上进行了多方面的改进。在高斯差分尺度空间仅检测局部极大值,提高算法的稳定性;采用基于圆形邻域统计梯度方向直方图,来确定兴趣点的主方向和描述子,避免了图像旋转的运算代价;最后采用最近邻与次近邻之比来对96维的描述子进行匹配。所提方法在有效地提高匹配准确率的同时,大大提高了运算速度, 适用于对实时性要求较高的场合。     

采用局部特性对比的多弹迹点检测

针对红外图像中多弹迹点检测精度不高的问题,对红外图像中弹迹点的特性进行了分析,提出了一种基于局部特性对比的多弹迹点检测算法用于有效检测红外图像中低信噪比条件下的多弹迹点。该方法利用同态滤波和中值滤波两种综合滤波方法减少光照不均的影响,提高图像信噪比。然后根据弹迹点在红外图像中自身的局部特性,采用局部特性对比并结合边缘检测精确检测弹迹点位置。从理论上分析了检测算法的有效性,并通过仿真实验与其他检测方法进行了对比。实验结果显示,本方法能够在低信噪比条件下有效检测出红外图像多弹迹点,与基于Top-hat和基于局部均值等方法相比,检测准确度更高,鲁棒性更好。     

结合滚动引导滤波和相位信息的红外与可见光图像配准

针对红外与可见光图像尺度差异大、图像较模糊,且图像中可提取的特征点数量不足以及特征分布不均匀易导致现有配准算法失效的情况,提出一种结合滚动引导滤波和相位信息的红外与可见光图像配准方法.利用滚动引导滤波构建尺度空间,在不增加耗时的前提下尽可能保持图像边缘信息;提出一种改进的Shitomasi角点检测算法,提取具有尺度不变性且分布均匀的强角点;在特征描述阶段,给出一种新的加权函数进行频率扩展,以得到更显著的相位一致性信息,实现更准确的图像特征描述.实验结果表明,该配准方法对存在9倍尺度差异的红外与可见光图像仍能实现准确配准,且对多组图像对的配准RMSE误差均保持在2像素之内.     

Vibro-acoustic tissue mammography

A novel method for detection and imaging of microcalcifications in breast tissue is presented. The method, called vibro-acoustography, uses the radiation force of ultrasound to vibrate tissue at low (kHz) frequency and utilizes the resulting response to produce images that are related to the hardness of the tissue. The method is tested on human breast tissues. The resulting vibro-acoustographic images are in agreement with corresponding X-ray mammography images of the specimens. The existence of microcalcifications in locations indicated by vibro-acoustography is confirmed by histology. Microcalcifications as small as 110 microm in diameter are detected by this method. Resulting vibro-acoustographic images show microcalcifications with high contrast with respect to the background soft tissue. Structures such as dense sclerotic tissue do not seem to interfere with detection of microcalcifications.     

基于非线性SIFT框架SAR图像匹配

针对基于尺度不变特征变换（SIFT）的图像匹配算法性能受到SAR图像中严重斑点噪声而性能降低的问题，提出了一种改进的非线性尺度构建的SIFT算法，主要改进在于：在尺度空间构建阶段，该算法通过将滚动引导滤波器嵌入到尺度空间构造的过程中来生成多尺度图像金字塔，在去除斑噪的同时并保持边缘的方面表现出了较其他尺度空间构建算法更好的效果；在特征检测阶段，提出了一种使用ROEWA算子和Harris-Laplace检测算子相结合的特征点检测算法，有效地抑制SAR图像中的虚假特征点，并准确地提取具有高位置精度和低误差率的不变特征点。3种不同类型的仿真和真实SAR图像对该算法进行了检验，并与其他2种基于SIFT的方法相比较，实验结果表明，该算法在匹配精度和内联点比率方面可以实现更好的性能。     

低秩稀疏分解下多尺度积的运动目标检测方法

针对基于矩阵分解的运动目标检测方法易受自然场景中背景的小幅抖动和摄像头抖动等因素影响的问题,提出了一种利用多尺度积的低秩稀疏矩阵分解算法。算法假设,静态背景视频序列中,每帧图像背景可近似视为处于同一低秩子空间中,图像前景则可视为偏离低秩空间的残差部分。首先对图像序列进行滤波、仿射变换等预处理得到视频序列观测数据矩阵;然后对数据矩阵进行低秩稀疏分解得到序列图像的低秩背景部分和每帧图像的稀疏前景部分;最后对稀疏前景部分采用小波变换模极大值与多尺度积方法检测目标边缘,并进行形态学处理,得到准确的运动目标。实验结果表明,算法检测到的运动目标清晰、完整,能有效地处理光照变化、摄像头小幅度抖动、图像背景局部小幅度变化等情况下的运动目标检测。      

Effects of JPEG2000 data compression on an automated system for detecting clustered microcalcifications in digital mammograms.

The functionalities of the JPEG2000 standard have led to its incorporation into digital imaging and communications in medicine (DICOM), which makes this compression method available for medical systems. In this study, we evaluated the compression of mammographic images with JPEG2000 (16 : 1, 20 : 1, 40 : 1, 60.4 : 1, 80: 1, and 106 : 1) for applications with a computer-aided detection (CAD) system for clusters of microcalcifications. Jackknife free-response receiver operating characteristic (JAFROC) analysis indicated that differences in the detection of clusters of microcalcifications were not statistically significant for uncompressed versus 16: 1 (T = -0.7780; p = 0.4370), 20 : 1 (T = 1.0361; p = 0.3007), and 40 : 1 (T = 1.6966; p = 0.0904); and statistically significant for uncompressed versus 60.4 : 1 (T = 5.8883; p < 0.008), 80 : 1 (T = 7.8414; p < 0.008), and 106 : 1 (T = 17.5034; p = < 0.008). Although there is a small difference in peak signal-to-noise ratio (PSNR) between compression ratios, the true-positive (TP) and false-positive (FP) rates, and the free-response receiver operating characteristic (FROC), figure of merit values considerably decreased from a 60 : 1 compression ratio. The performance of the CAD system is significantly reduced when using images compressed at ratios greater than 40 : 1 with JPEG2000 compared to uncompressed images. Mammographic images compressed up to 20 : 1 provide a percentage of correct detections by our CAD system similar to uncompressed images, regardless of the characteristics of the cluster. Further investigation is required to determine how JPEG2000 affects the detectability of clusters of microcalcifications as a function of their characteristics.     

Detection of Clustered Microcalcifications on Mammograms Using Surrounding Region Dependence Method and Artificial Neural Network

Clustered microcalcifications on X-ray mammograms are an important sign in the detection of breast cancer. A statistical texture analysis method, called the surrounding region dependence method (SRDM), is proposed for the detection of clustered microcalcifications on digitized mammograms. The SRDM is based on the second-order histogram in two surrounding regions. This method defines four textural features to classify region of interests (ROIs) into positive ROIs containing clustered microcalcifications and negative ROIs of normal tissues. The database is composed of 64 positive and 76 negative ROI images, which are selected from digitized mammograms with a pixel size of 100 × 100 m² and 12 bits per pixel. An ROI is selected as an area of 128 × 128 pixels on the digitized mammograms. In order to classify ROIs into the two types, a three-layer backpropagation neural network is employed as a classifier. A segmentation of individual microcalcifications is also proposed to show their morphologies. The classification performance of the proposed method is evaluated by using the round-robin method and a free-response receiver operating-characteristics (FROC) analysis. A receiver operating-characteristics (ROC) analysis is employed to present the results of the round-robin testing for the case of several hidden neurons. The area under the ROC curve, A _z, is 0.997, which is achieved in the case of 4 hidden neurons. The FROC analysis is performed on 20 cropped images. A cropped image is selected as an area of 512 × 512 pixels on the digitized mammograms. In terms of the FROC, a sensitivity of more than 90% is obtained with a low false-positive (FP) detection rate of 0.67 per cropped image.     

Performance of vibro-acoustography in detecting microcalcifications in excised human breast tissue: a study of 74 tissue samples

X-ray mammography is the principal modality used today for detection of breast microcalcifications and breast lesions associated with breast cancer. X-ray mammography, however, is ionizing and its sensitivity is greatly reduced in dense breasts. Hence, alternative noninvasive and nonionizing breast imaging tools that can aid physicians to better diagnose early-stage breast lesions are of great interest. Vibro-acoustography is a novel noninvasive imaging technique that uses ultrasound in a fundamentally new way. This method uses the radiation force of ultrasound to vibrate the tissue at low (kilohertz) frequency and records the resulting response to produce images that are related to the mechanical properties of the tissue. The goal of this study is to evaluate the performance of vibro-acoustography in detecting breast microcalcifications by conducting vibro-acoustography on 74 fixed breast tissue samples with known microcalcifications based on their radiographs. The results indicate that in most cases micro-calcifications can be detected by vibro-acoustography. Further development of vibro-acoustography may lead to a novel-imaging tool for in vivo detection of microcalcifications.     

基于多尺度红外与可见光图像配准研究

利用尺度空间理论对多分辨率的红外与可见光图像配准算法进行研究,提出利用红外与可见光图像的多尺度特征点及边缘作为配准的特征,利用特征尺度确定用于相似度匹配的子图像大小,使用LTS-Hausdorff(least trimmed square Hausdorff)距离判断子图像的相似性。利用尺度空间理论及多尺度下图像的特征能更加全面的对图像进行描述。在利用多尺度特征获取到匹配对后,再利用随机一致性检测对匹配对进行提纯并获取空间变换的参数,然后使用该参数对红外与可见光图像进行配准与融合。实验结果表明,基于多尺度的图像配准方法,能有效对红外与可见光图像进行配准。     

Mammogram Inspection by Computer

We have considered the problem of computerized picture processing of mammographic images for the early detection of breast cancer by determination of the very significant microcalcifications. Brightness measures, gray-level statistics, and a compactness measure are applied in a decision tree to characterize the candidate objects. A verification technique was evaluated to differentiate between significant groups of microcalcifications and isolated objects as well as false alarms. Feasibility of the microcalcification detection algorithm was demonstrated in experiments using 132 mammogram subareas, each consisting of 512 ×512 picture elements.     

Smoky vehicle detection based on multi-scale block Tamura features

Smoky vehicle, emitting visible black exhaust emissions from vehicle exhaust pipe, is representative heavy pollution vehicle. This paper presents an intelligent smoky vehicle detection method based on multi-scale block Tamura features. In this method, the Vibe background subtraction algorithm is adopted to detect vehicle objects. We propose the multi-scale block Tamura features and use this features to distinguish smoky vehicle images and non-smoke vehicle images. More specifically, the region at the back of the vehicle is divided into 1\(\times \)2 blocks. For each block, the multi-scale strategy based on Gaussian kernel with different standard deviations is proposed to extract features and utilize different scales information. Finally, the back-propagation neural network classifier is trained and used for classification. Our method can automatically detect smoky vehicle through analyzing road surveillance videos. The experimental results show that the proposed algorithm framework performs better than common smoke and fire detection method, and the proposed multi-scale block Tamura features can obtain higher detection accuracy than common Tamura features.     

机场跑道图像去雾增强算法及其实现

机场跑道场景下,由于雾、霾等恶劣天气以及大气散射的作用,使拍摄的图像对比度降低,颜色退化,物体特征难以辨认,影响机场跑道图像的异物检测与识别,带来一些安全隐患。针对上述问题,提出基于双线性插值和中值滤波的改进的引导滤波算法,提高图像对比度和处理速度,利于机场跑道异物检测与识别。仿真结果表明,改进的引导滤波算法与已有算法相比,处理速度提高了2~3倍,且图像彩色值分布更广,直方图更均匀。该算法拥有良好的边缘保持性,在细节增强方面有很好的指导意义。随后将改进的引导滤波算法移植到数字信号处理器( DSP)平台上,以满足实际工程应用对小型化的需求。