基于特征能量加权的红外与可见光图像融合

目前红外与可见光图像直接融合存在红外目标取舍和场景信息提取困难,结合非采样Contourlet的多尺度、多方向性和平移不变性的优点,本文提出了一种基于非采样Contourlet变换(NSCT)的红外与可见光图像融合方法.首先对源图像进行分解,然后低频子带通过构造基于区域的特征像素能量,进行加权融合,高频子带直接选用方差取大法融合.使用该算法进行了融合实验,并给出了融合质量评价.实验结果表明,本文提出的基于NSCT的图像融合算法在保留图像细节信息、增加信息量方面都有显著地提高.     

基于方向滤波器组与Laplacian能量和的图像融合算法

目的针对基于Contourlet变换的融合算法在边缘上易出现吉布斯现象,使其融合图像产生几何失真的问题,设计一种非下采样方向滤波器组耦合局部Laplacian能量和的图像融合算法。方法首先,结合多小波变换(multi-wavelet transform,MWT)与非下采样方向滤波器组(Non-Subsampled Direction FilterBank,NSDFB),将图像分解为3个高频方向系数和1个低频系数。对于低频系数,采用局部修正的Laplacian能量和(Local Sum-Modified-Laplacian,LSML)与脉冲耦合神经网络(Pulse couple neural network,PCNN)组合的LSML-PCNN模型来完成低频信息的融合。对于高频系数,通过提取低频和高频子带边缘,并利用系数绝对最大值法作为依据,实现高频系数的融合。结果实验数据表明,与当前图像融合方案相比,所提算法具有更高的融合质量,得到的融合图像边缘更加清晰和完整。结论所提算法拥有较高的融合视觉效果,可改善图像的对比度和分辨率,在图像处理领域具有一定的参考价值。     

基于多目标粒子群算法的多传感器图像融合

针对图像融合中参数优化的问题,提出了一种基于多目标粒子群优化算法的多传感器图像融合方法。首先采用非采样Contourlet变换(NSCT)对源图像进行多尺度、多方向分解;然后选取图像融合的客观评价指标为优化目标函数,采用多目标粒子群优化算法对低频系数的融合参数进行优化,带通方向子带系数采用取绝对值最大的融合规则;最后通过NSCT逆变换得到融合图像。分别对多聚焦图像融合和红外与可见光图像进行融合实验,并对融合图像进行主客观评价,实验结果表明,得到的融合图像具有较好的主观视觉效果和客观评价指标。     

基于NSST和SWT的红外与可见光图像融合算法研究

目的鉴于非下采样剪切波变换NSST的红外与可见光图像融合的结果存在细微特征缺失问题,提出一种基于NSST和SWT的红外与可见光图像融合算法,以提升融合图像的质量。方法首先分别对红外与可见光图像进行NSST分解,各得到一个低频系数和多个不同方向、尺度的高频系数。然后低频系数分别通过SWT分解得到新的低频系数和高频系数,通过SWT分解得到的新的低频系数和高频系数分别采用采用线性加权平均法和区域平均能量取大的融合策略,融合结果再进行SWT逆变换得到低频系数融合结果。高频系数采用区域平均能量取大的融合策略进行融合。最后通过NSST逆变换得到最终的融合图像。结果通过仿真实验结果表明,文中算法与NSST,SWT和NSCT等算法相比,融合图像在主观视觉上的红外目标更突出,图像细节更清晰,且在IE, AG, QAB/F, SF和SD等评价指标上也最优。结论文中算法的融合结果能更好地表现源图像的目标信息和细节纹理信息,表明该算法具有优越性。     

一种NSCT域多聚焦图像融合新方法

针对多聚焦图像融合存在的问题,提出一种基于非下采样Contourlet变换（NSCT）的多聚焦图像融合新方法。首先,采用NSCT对多聚焦图像进行分解;然后,对低频系数采用基于改进拉普拉斯能量和（SML）的视觉特征对比度进行融合,对高频系数采用基于二维Log-Gabor能量进行融合;最后,对得到的融合系数进行重构得到融合图像。实验结果表明,无论是运用视觉的主观评价,还是基于互信息、边缘信息保留值等客观评价标准,该文所提方法都优于传统的离散小波变换、平移不变离散小波变换、NSCT等融合方法。     

非下采样Contourlet变换域统计模型红外图像去噪

对红外图像进行非下采样Contourlet变换,分析其系数的统计特征,采用广义高斯分布来模拟系数的概率分布。根据非下采样Contourlet变换的带通子带各方向能量不同的特点,提出修正的贝叶斯阈值公式,为了克服软、硬阈值函数的缺点,又提出一种具有可调节自适应性的新阈值函数,最后利用新阈值函数估计出不含噪声的变换系数,并通过非下采样Contourlet逆变换得到去噪后的红外图像。仿真实验表明,文中方法在峰值信噪比及视觉效果上均优于经典的小波阈值去噪算法。     

基于NSCT和PCNN的红外与可见光图像融合方法

提出了一种基于非采样Contourlet变换(NSCT)和脉冲耦合神经网络(PCNN)的红外与可见光图像融合方法.首先用NSCT对已配准的源图像进行分解,得到低频子带系数和各带通子带系数;其次对低频子带系数采取一种基于边缘的方法以得到融合图像的低频子带系数;对各带通子带系数提出了一种改进的基于PCNN的图像融合方法来确定融合图像的各带通子带系数;最后经过NSCT逆变换得到融合图像.实验结果表明,本文方法优于Laplaeian方法、小波方法和传统的NSCT方法.     

改进型抗混叠轮廓波的图像超分辨率重建

针对Contourlet变换中存在的频谱混叠现象,采用了基于抗混叠轮廓波变换的算法进行图像超分辨率重建.该算法首先用抗混叠塔式滤波器组替换掉Contourlet变换中的拉普拉斯塔式变换,对图像进行尺度变换;然后,根据尺度变换后不同尺度的高频子带之间的相似性,对相关高频分量用双三次插值做高频外推相似变换,再通过方向滤波器...     

多彩色空间相关分析的人脸识别算法

人脸识别是当前人工智能和模式识别的研究热点,得到了广泛的关注.基于对不同色彩空间数据的分析,论文提出了多彩色空间典型相关分析的人脸识别方法.文中对2维的Contourlet变换特性进行了分析和讨论,利用Contourlet的多尺度,方向性和各向异性等特点,提出了一种基于Contourlet变换的彩色人脸识别算法.算法对原图进行Contourlet分解,对分解得到的低频和高频图像进行cca分析.典型相关分析是一种有效的分析方法,其实际应用十分广泛.低频系数反映图像的轮廓信息,高频系数反映图像的细节信息,使用cca充分利用不同频率的信息,使不同色彩空间的不同分辨率图形的相关性达到最大,得到投影系数,最后,采用决策级最近邻分类器完成人脸识别.在对彩色人脸数据库AR的识别实验中,该算法识别率达到98％以上,与传统算法相比,该算法不仅既有良好的识别结果,而且具有很快的运算速度.     

改进提升小波变换的空间频率比图像融合

提出了一种新型图像融合算法.该算法在提升小波变换的基础上,通过取消其奇偶分裂环节,得到具有平移不变性的非采样提升小波变换.对图像经非采样提升小波变换后的低频分量首先定义一种空间频率比,再通过空间频率比来计算融合因子,然后采用加权与选择相结合的方法对低频分量进行融合.高频分量直接选择一种基于边缘信息的加权融合方法.最后通过非采样提升小波逆变换重构得到融合图像.实验结果显示,该算法相对传统的图像融合算法能更好地描述灰度的突变信息,获得含有丰富细节特征的融合图像.     

A novel brain image enhancement method based on nonsubsampled contourlet transform

In this article, a novel brain image enhancement approach based on nonsubsampled contourlet transform (NSCT) is proposed. First, the image is decomposed into a low‐frequency component and several high‐frequency components by the NSCT; Second, the gamma correction is applied to deal with the low‐frequency sub‐band coefficients, and the adaptive threshold is used to remove the noise of the high‐frequency sub‐bands coefficients; Third, the inverse nonsubsampled contourlet transform is adopted to reconstruct the processed coefficients; Finally, the unsharp filter is used to enhance the reconstructed image. The experimental results demonstrate that the performance of the proposed method is superior to the state‐of‐the‐art algorithms in terms of brain image enhancement.     

Medical image enhancement algorithm based on NSCT and the improved fuzzy contrast

In order to solve the problem of noise amplification, low contrast and image distortion in the process of medical image enhancement, a new algorithm is proposed which combines NSCT (nonsubsampled contourlet transform) and improved fuzzy contrast. The image is decomposed by NSCT. Firstly, linear enhancement method is used in low frequency coefficients; secondly the improved adaptive threshold function is used to deal with the high frequency coefficients. Finally, the improved fuzzy contrast is used to enhance the global contrast and the Laplace operator is used to enhance the details of the medical images. Experimental results show that the proposed algorithm can improve the image visual effects, remove the noise and enhance the details of medical images. © 2015 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 25, 7–14, 2015     

Multi-focus image fusion based on the non-subsampled contourlet transform

In this paper, a new image fusion algorithm based on non-subsampled contourlet transform (NSCT) is proposed for the fusion of multi-focus images. The selection of different subband coefficients obtained by the NSCT decomposition is critical to image fusion. So, in this paper, firstly, original images are decomposed into different frequency subband coefficients by NSCT. Secondly, the selection of the low-frequency subband coefficients and the bandpass directional subband coefficients is discussed in detail. For the selection of the low-frequency subband coefficients, the non-negative matrix factorization (NMF) method is adopted. For the selection of bandpass directional subband coefficients, a regional cross-gradient method that selects the coefficients according to the minimum of the regional cross-gradient is proposed. Finally, the fused image is obtained by performing the inverse NSCT on the combined coefficients. The experimental results show that the proposed fusion algorithm can achieve significant results in getting a new image where all parts are sharp.     

基于计算全息的Contourlet域数字水印算法

目的提出一种基于计算全息的contourlet域数字水印算法。方法首先,利用共轭对称延拓傅里叶计算全息方法,将原始二值水印图像生成全息水印图像;然后,将原始图像进行二级contourlet变换,得到8个中频方向子带系数;最后,将全息水印嵌入在其中频系数中。结果该方法可以有效抵抗高斯滤波、中值滤波和均值滤波以及打印-扫描攻击,同时,对噪声攻击、裁切攻击和JPEG压缩攻击也有很强的抵抗能力。在水印提取时无需原始图像,属于盲水印算法。结论该算法可以广泛应用于数字图像的版权保护中。     

A hybrid contextual compression technique using wavelet and contourlet transforms with PSO optimized prediction

Contextual compression is an essential part of any medical image compression since it facilitates no loss of diagnostic information. Although there are many techniques available for contextual image compression still there is a need for developing an efficient and optimized technique which would produce good quality images at lower bit rates. This article presents an efficient contextual compression algorithm using wavelet and contourlet transforms to capture the fine details of the image, along with directional information to produce good quality at high Compression Ratio (CR). The 2D discrete wavelet transform, which uses the simplest Daubechies wavelets, db1, or haar wavelet, is chosen and used to get the subband coefficients. The approximate coefficients of the higher subbands undergo contourlet transform employing length N ladder filters for capturing the directional information of the subbands at different scale and orientations. An optimized approach is used for predicting the quantized and the normalized subband coefficients resulting in improved compression performance. The proposed contextual compression approach was evaluated for its performance in terms of CR, Peak Signal to Noise Ratio, Feature SIMilarity index, Structure SIMilarity Index, and Universal quality (Q) after reconstruction. The results clarify the efficiency of the proposed method over other compression techniques.     

基于改良扩频技术的Contourlet域盲图像水印

提出了一种基于改良扩频技术的Contourlet盲图像水印算法。将二值水印图像经Arnold置乱后进行双极性映射,然后通过IMSS（Improved Modified Spread Spectrum）系统嵌入到宿主图像Contourlet域次高阶方向子带中能量最大的子带纹理最丰富的位置上,检测端采用相关检测并设置一最佳阈值来判决水印存在与否。实验结果表明该方案不仅具有很好的透明性,而且在常规的图像处理和攻击下比传统扩频水印有更强的鲁棒性,同时也克服了传统扩频水印在检测无水印图像时完全失败的缺点。     

无下采样轮廓波变换纹理图像检索系统

针对基本轮廓波变换纹理检索系统检索率较低的问题,提出了一种无下采样轮廓波变换(NSCT)纹理图像检索系统.该系统采用的轮廓波变换由无下采样拉普拉斯金字塔级联无下采样方向滤波器构成,特征向量采用子带系数的能量和标准偏差连接而成;以Canberra距离为相似度度量标准.比较了基于同样架构的基本轮廓波变换和NSCT纹理检索系统的性能.实验结果表明:在特征向量长度,检索时间、所需存储空间基本相同的情况下,NSCT检索系统比基本轮廓波变换检索系统具有更高的检索率;NSCT分解结构参数以及图像类型对于平均检索率也有较大的影响.     

An efficient and automatic glioblastoma brain tumor detection using shift‐invariant shearlet transform and neural networks

The detection and segmentation of tumor region in brain image is a critical task due to the similarity between abnormal and normal region. In this article, a computer‐aided automatic detection and segmentation of brain tumor is proposed. The proposed system consists of enhancement, transformation, feature extraction, and classification. The shift‐invariant shearlet transform (SIST) is used to enhance the brain image. Further, nonsubsampled contourlet transform (NSCT) is used as multiresolution transform which transforms the spatial domain enhanced image into multiresolution image. The texture features from grey level co‐occurrence matrix (GLCM), Gabor, and discrete wavelet transform (DWT) are extracted with the approximate subband of the NSCT transformed image. These extracted features are trained and classified into either normal or glioblastoma brain image using feed forward back propagation neural networks. Further, K‐means clustering algorithm is used to segment the tumor region in classified glioblastoma brain image. The proposed method achieves 89.7% of sensitivity, 99.9% of specificity, and 99.8% of accuracy.     

Statistical correlative model in the multimodal fusion of brain images

Fusing multimodal medical images into an integrated image, providing more details and rich information thereby facilitating medical diagnosis and therapy. Most of the existing multiscale-based fusion methods ignore the correlations between the decomposition coefficients and lead to incomplete fusion results. A novel contextual hidden Markov model (CHMM) is proposed to construct the statistical model of contourlet coefficients. First, the pair brain images are decomposed into multiscale, multidirectional, and anisotropic subbands with a contourlet transform. Then the low-frequency components are fused with the choose-max rule. For the high-frequency coefficients, the CHMM is learned with the EM algorithm, and incorporate with a novel fuzzy entropy-based context, building the fuzzy relationships among these coefficients. Finally, the fused brain image is obtained by using the inverse contourlet transform. Fusion experiments on several multimodal brain images show the superiority of the proposed method in terms of both visual quality and some widely used objective measures.