基于自适应核学习相关向量机的乳腺X线图像微钙化点簇处理方法研究

采用自适应核学习相关向量机方法, 结合形态学滤波和Kallergi分簇标准, 研究了乳腺X线图像中微钙化点簇的处理. 首先将微钙化点检测看作一个监督学习问题, 然后应用自适应核学习相关向量机作为分类器判断图像中每一个位置是否为微钙化点并采用形态学处理滤除干扰噪声, 最后对获得的微钙化点采用Kallergi标准进行分簇. 为提高运算速度, 在微钙化点检测时将整个图像分解为多个子图像并行运算, 实现了一种基于自适应核学习相关向量机的微钙化点簇快速处理方法. 实验结果和分析表明, 自适应核学习相关向量机方法算法性能优于相关向量机方法, 特别是实现的快速方法能进一步降低微钙化点簇的处理时间. 关键词： 乳腺X线图像 微钙化点簇 相关向量机 自适应核学习     

基于小波变换和图论方法识别乳腺微钙化点簇

成簇的微钙化点是早期乳腺癌的一个重要表征,用计算机辅助诊断时需要在乳腺片图像中判断有无钙化点簇。提出了一种利用Daubechies小波对乳腺图像进行增强,用二维熵阈值分割法对增强后的图像进行阈值分割,然后采用图论方法提取出成簇钙化点的方法。从而实现了计算机辅助诊断系统辅助医师判断恶性钙化。     

基于CCD的乳腺X线摄影图像预处理方法的研究

为提高由闪烁屏到CCD的光耦合效率,减小大相对孔径和近距离成像造成CCD图像严重失真,提出一种有效补偿图像失真的预处理方法。该方法根据物像共轭关系将物面划分为与图像传感器像素相对应的许多微小物元,应用蒙特卡罗方法模拟从每一物元发出的光在像面上形成的光分布,即点扩散函数。由所有物元的点扩散函数构成一个点扩散数组,数组的每一行对应一个物元的点扩散函数。基于该点扩散数组建立描述像元与物元关系的线性方程组,解线性方程组可得到接近实物的图像。用实际光学系统的计算结果验证了该方法的有效性。     

一种基于对比度增强和柯西模糊函数的红外与弱可见光图像融合算法

由于可见光图像在低光照环境下其可视性较差,为了提高红外与弱可见光图像融合的效果,提出了一种基于对比度增强和柯西模糊函数的图像融合算法.首先用改进的引导滤波自适应增强提高弱可见光图像暗区域的可视性;其次,利用非下采样剪切波变换将红外和增强后的弱可见光图像分解,得到相应的低频和高频子带;再后,分别用直觉模糊集构建柯西隶属函数和自适应双通道脉冲发放皮层模型对低频、高频子带进行融合;最后,使用非下采样剪切波变换对融合得到的高低频子带进行逆变换重构得到融合图像.实验结果表明,与其它融合算法相比,该算法有效地增强了弱可见光图像的暗区域,保留了更多的背景信息,从而提高了融合图像的对比度和清晰度.     

基于SIFT特征和ISM的X射线图像危险品检测方法

针对行李安检时X射线图像中的危险品检测问题,提出一种基于尺度不变特征变换(SIFT)和隐式形状模型(ISM)的检测方法。首先,采集不同姿态的危险品X射线图像,并标注目标位置,构建训练数据集。然后,通过SIFT算法提取目标关键点,并以此构建目标的ISM模型。在检测过程中,将提取的目标SIFT描述符与ISM模型中的视觉描述符进行匹配,通过投票机制来判断目标是否为危险品。通过手枪和酒瓶的检测实验表明,该方法能够从X射线图像中准确检测出危险品,且对目标姿态变化具有鲁棒性。     

基于哈希理论和线性近邻传递反馈的乳腺X线图像肿块检索方法

在乳腺X线图像肿块检测中存在较高的假阳性率,通过基于内容的肿块检索,将待判定肿块与已确诊肿块进行相似性分析,可有效降低假阳性率.本文提出了一种结合可区分锚点图哈希和线性近邻传递的乳腺图像肿块检索方法.针对传统锚点图哈希在相似度定义中没有考虑病理相关性的问题,引入病理类别至锚点图哈希图像相似度计算,提出了可区分锚点图哈希以重新表示图像.利用线性近邻传递作为相关反馈技术,基于图像底层特征表达与图像高层语义间的学习机制,实现交互式肿块图像检索.采用北京大学人民医院乳腺中心提供的临床图像作为实验数据,实验结果表明,引入病理类别的可区分锚点图哈希图像表达在肿块相似性分析上优于传统锚点图哈希.相比于现有方法,本文提出的方法在肿块检索性能上得到明显提高.     

Application of image enhancement method for digital images based on Retinex theory

The image enhancement and implementation of the methods for the digital image enhancement were studied. The characteristics of different image enhancement methods, including contrast enhancement, linear transformation, piecewise linear transformation, grayscale slice transformation and Retinex clearing algorithms were analyzed in detail. Retinex enhancement algorithms were studied and the implementation process for the Retinex algorithm is given. Finally, an example of image enhancement using the multi scale Retinex algorithm (MSR) is achieved. It is shown that MSR can realize the image color constancy, local dynamic range compression, color enhancement and the overall dynamic range compression under certain circumstances.     

A novel method for detecting light source for digital images forensic

Manipulation in image has been in practice since centuries. These manipulated images are intended to alter facts — facts of ethics, morality, politics, sex, celebrity or chaos. Image forensic science is used to detect these manipulations in a digital image. There are several standard ways to analyze an image for manipulation. Each one has some limitation. Also very rarely any method tried to capitalize on the way image was taken by the camera. We propose a new method that is based on light and its shade as light and shade are the fundamental input resources that may carry all the information of the image. The proposed method measures the direction of light source and uses the light based technique for identification of any intentional partial manipulation in the said digital image. The method is tested for known manipulated images to correctly identify the light sources. The light source of an image is measured in terms of angle. The experimental results show the robustness of the methodology.     

基于改进CLAHE的SF_6红外图像增强

针对六氟化硫(SF_6)红外图像对比度低、纹理细节模糊而难以增强泄漏区域的问题,提出了基于改进限制对比度的自适应直方图均衡化(CLAHE)的SF_6红外图像增强算法。采用双边滤波将原始图像分为基础图像和细节图像;采用CLAHE算法来处理基础图像,提高泄漏区域的对比度;对细节图像进行分段线性变换和拉普拉斯变换图像,以突出图像的边缘;将两幅图像进行线性叠加以获取最终的红外图像,实现图像增强。实验结果表明,算法对SF_6红外图像泄漏区域的增强效果优于常见的几种红外图像增强算法,不仅有效地抑制了噪声和提高泄漏区域的对比度,而且突出泄漏区域的边缘,丰富了细节信息。     

基于数学形态学和匹配滤波的视网膜血管图像增强方法

针对视网膜图像成像过程的特点,提出了一种新的视网膜图像血管信息增强方法。由于存在光照不均匀的情况,采用同态滤波的方法设计了一种滤波器,对光照不均匀的情况进行了有效的校正;使用数学形态学中的Top Hat变换,对背景信息进行抑制,使得血管信息得到增强;最后进一步采用匹配滤波的方法,探测血管信息,使得血管信息的亮度得到提高,增强了与背景的对比度,血管信息具有明显的可视性。实验结果表明了提出的方法的有效性,对临床疾病的诊断及治疗具有较大的参考价值。     

Fusion method of infrared and visible images based on neighborhood characteristic and regionalization in NSCT domain

On fusing infrared and visible image, the traditional fusion method cannot get the better image quality. Based on neighborhood characteristic and regionalization in NSCT (Nonsubsampled Contourlet Transform) domain, the fusion algorithm was proposed. Firstly, NSCT was adopted to decompose infrared and visible images at different scales and directions for the low and high frequency coefficients, the low frequency coefficients which were fused with improving regional weighted fusion method based on neighborhood energy, and the high-frequency coefficients were fused with multi-judgment rule based on neighborhood characteristic regional process. Finally, the coefficients were reconstructed to obtain the fused image. The experimental results show that, compared with the other three related methods, the proposed method can get the biggest value of IE (information entropy), MI(VI,F) (mutual information from visible image), MI(VI,F) (mutual information from infrared image), MI (sum of mutual information), and Q^AB/F (edge retention). The proposed method can leave enough information in the original images and its details, and the fused images have better visual effects.     

A post-processing method for correction and enhancement of chemical shift images

Chemical shift imaging (CSI) relies on a strong and homogeneous main field. Field homogeneity ensures adequate coherence between the precessions of individual spins within each voxel. Variation of field strength between different voxels causes geometric distortion and intensity variation in chemical shift images, resulting in errors when analyzing the spatial distribution of specific chemical compounds. A post-processing method, based on detection of the spectral peak of water and baseline subtraction with Lorentzian functions, was developed in this study to automatically correct spectra offsets caused by field inhomogeneity, thus enhancing the contrast of the chemical shift images. Because this method does not require prior field plot information, it offers advantages over existing correction methods. Furthermore, the method significantly reduces geometric distortion and enhances signals of chemical compounds even when the water suppression protocol was applied during the CSI data acquisition. The experimental results of the water and glucose phantoms showed a considerable reduction of artifacts in the spectroscopic images when this post-processing method was employed. The significance of this method was also demonstrated by an analysis of the spatial distributions of sugar and water contents in ripe and unripe bananas.     

Synthetic Aperture Radar image nonlinear enhancement algorithm based on NSCT transform

Due to the imaging mechanism, Synthetic Aperture Radar (SAR) images are susceptible to speckle noise, which affects radar image interpretation. So image denoising and enhancement are important topics of improving SAR image performance. A nonlinear image enhancement algorithm based on nonsubsampled contourlet transform (NSCT) is proposed in this paper. The image is decomposed into coefficients of different scales and directions through nonsubsampled contourlet transform. It is denoised by the threshold method of the multi-scale product of NSCT coefficients. Then thresholds of the nonlinear enhancement function are determined according to the coefficients of each scale. The two parameters of the function, among which one is used to control the range of enhancement and the other can determine the strength of enhancement, are obtained by solving nonlinear equations. The coefficients processed by the enhancement function are used to reconstruct the image. The simulation results on the Matlab platform show that the algorithm has a good effect of enhancing details of images and suppressing noise signals meanwhile.     

An adaptive fusion approach for infrared and visible images based on NSCT and compressed sensing

A novel nonsubsampled contourlet transform (NSCT) based image fusion approach, implementing an adaptive-Gaussian (AG) fuzzy membership method, compressed sensing (CS) technique, total variation (TV) based gradient descent reconstruction algorithm, is proposed for the fusion computation of infrared and visible images.Compared with wavelet, contourlet, or any other multi-resolution analysis method, NSCT has many evident advantages, such as multi-scale, multi-direction, and translation invariance. As is known, a fuzzy set is characterized by its membership function (MF), while the commonly known Gaussian fuzzy membership degree can be introduced to establish an adaptive control of the fusion processing. The compressed sensing technique can sparsely sample the image information in a certain sampling rate, and the sparse signal can be recovered by solving a convex problem employing gradient descent based iterative algorithm(s).In the proposed fusion process, the pre-enhanced infrared image and the visible image are decomposed into low-frequency subbands and high-frequency subbands, respectively, via the NSCT method as a first step. The low-frequency coefficients are fused using the adaptive regional average energy rule; the highest-frequency coefficients are fused using the maximum absolute selection rule; the other high-frequency coefficients are sparsely sampled, fused using the adaptive-Gaussian regional standard deviation rule, and then recovered by employing the total variation based gradient descent recovery algorithm.Experimental results and human visual perception illustrate the effectiveness and advantages of the proposed fusion approach. The efficiency and robustness are also analyzed and discussed through different evaluation methods, such as the standard deviation, Shannon entropy, root-mean-square error, mutual information and edge-based similarity index.     

A novel fringe adaptation method for digital projector

Aimed to obtain high-quality sinusoidal fringe projection, a new method to correct the output fringe of digital projector is presented. The method is based on the proposed fringe transform model, which describes the relationship of the input and output fringe pattern. Firstly, a series of fringe patterns are projected and from the fringe images, the transform function is calculated by the pattern shifting method. At last, by modifying the input fringe pattern, a standard sinusoidal output fringe can be achieved. Different from the previous methods, the waveform nonlinearity is estimated by varying the intensity of the projected fringe pixel by pixel; thus the waveform nonlinearity can be estimated precisely and the time cost is considerably reduced. Experimental results show that by modification of the input projection patterns the projector can project fringe with high-quality sinusoidal waveform leading to high performance of the projection system.