基于Contourlet变换的图像压缩感知重构

根据图像信号在Contourlet变换域的稀疏特性,分析Contourlet变换的基本原理,提出一种基于Contourlet变换的压缩感知重构方法。针对Contourlet变换的基函数并不严格规范正交、无法构造正交变换矩阵的问题,采用改进梯度投影算法恢复稀疏处理后的系数,在保证图像质量的情况下,实现图像的低速率重构。实验结果表明,该算法的鲁棒性较好。     

基于小波变换的图像压缩感知

针对图像变换后系数采样数量和图像重建质量之间的矛盾,从图像的结构和纹理特性出发,提出基于小波变换的图像压缩感知算法.讨论图像经过多尺度小波变换后系数的稀疏性,保留图像变换后的低频系数,只对高频系数进行测量,同时利用正交匹配追踪算法重构高频系数.实验仿真结果表明,该算法能有效提高图像重建质量.     

基于灰度纹理信息的图像压缩感知编码与重构

引入了压缩感知(Compressed Sensing,CS)理论,在分析图像DCT系数分布特性的基础上,提出了一种基于灰度纹理信息的压缩采样方法。该方法通过提取图像分块离散余弦变换交流系数的能量,进而对用于对测量过程进行加权修正,充分利用代表图像细节纹理信息的交流分量系数,基于图像轮廓纹理细节信息来分配测量维数,最终实现对不同图像块有区别的压缩采样。比较同类研究结果表明,提出的采样方法在有效减少测量维数或提高重构图像的峰值信噪比和主观视觉效果,以及在降低计算复杂度方面均有更好的表现。     

基于Curvelet变换的图像压缩感知重构

压缩感知主要采用离散余弦变换(DCT)和正交小波进行图像的稀疏表示,但是DCT时频分析性能不佳,小波方向选择性差,不能很好地表示图像边缘的信息。为此,利用Curvelet变换具有的多尺度、各向奇异性、更高稀疏表示性能等特性,提出基于Curvelet变换的图像压缩感知重构算法,采用Curvelet对图像进行稀疏表示和小波域阈值处理,以此解决信号重构噪声问题。实验结果证明,与传统小波变换和Contourlet变换相比,该算法在Lena图像上峰值信噪比平均提高了1.86 dB和1.15 dB。将Curvelet变换应用于压缩感知,能使图像边缘和平滑部分得到最优的表示,图像细节部分重构效果得到大幅提升,有效提高图像整体重构质量。     

基于PCA硬阈值收缩的平滑投影Landweber图像压缩感知重构

利用压缩感知理论对图像进行测量和重构时,基于分块思想可有效提高重构速度,但同时会带来较强的块效应.为了解决该问题,在编码端提出了一种基于边缘检测的自适应分块压缩感知测量方案;在解码端提出了一种基于主成分分析(PCA)的平滑投影Landweber(SPL)重构法,该算法运用PCA训练出适合于图像结构的稀疏字典,用于进行硬阈值收缩,从而有效消除了块效应,提升了重构图像的质量.为了提高硬阈值收缩效率和减少训练复杂度,采用了3种基于块的PCA硬阈值收缩方案:全局PCA、局部PCA和分层PCA.仿真实验结果表明:所提出的自适应压缩感知测量方案与SPL重构法相结合,和传统分块压缩感知方案相比,峰值信噪比(PSNR)值均提升了1～3 dB;本文算法,无论在传统分块压缩感知方案下还是在自适应分块压缩感知方案下,与基于方向小波阈值收缩的SPL重构算法相比,均获得了更高的PSNR值.     

基于压缩感知和GHM多小波变换的信息隐藏算法

针对基于秘密信息置乱方法等类型的信息隐藏算法不可见性低和抗攻击性弱这一问题,提出了一种基于压缩感知和GHM多小波变换的信息隐藏算法。首先,将载体图像进行一次GHM多小波变换,再对所得到的中间能量区域进行一次小波变换得到HH分量,将HH分量进行奇异值分解;其次,将秘密图像进行小波变换,将得到的小波系数进行压缩感知得到观测矩阵,再对观测矩阵元素进行奇异值分解;最后,利用秘密图像的奇异值替换掉载体图像的奇异值来完成秘密信息的嵌入。实验结果表明,相比两种加密算法,算法不可见性（PSNR值）分别提高5.99%和22.11%;对低通滤波、椒盐噪声、高斯噪声、JPEG压缩等常见攻击具有良好的鲁棒性,相关系数（NC）平均增强了4.11%和11.53%。     

基于局部和非局部正则化的图像压缩感知

基于低秩正则化的非局部低秩约束(Nonlocal low-rank regularization, NLR)算法利用相似块的结构稀疏性,获得了目前最好的重构结果。但是它仅仅利用了图像的非局部信息,忽略了图像像素间的局部信息,不能有效地重建图像的边缘,同时Logdet函数不能很好地替代矩阵秩,因为它跟真实解之间存在着不可忽视的差距。因此,本文提出了一种基于局部和非局部正则化的压缩感知图像重建方法,同时考虑图像的非局部低秩性和图像像素的局部稀疏梯度性。选择利用Schatten-p范数来替代矩阵秩,同时选择交替方向乘子算法求解产生的非凸优化问题。实验结果表明,与传统的稀疏性先验重建算法和NLR算法相比,本文算法能够获得更高的图像重构质量。     

基于小波变换的图象感知熵编码

本文提出了一种基于小波变换的图象感知熵量化编码方法，此法首先通过小波变换将图象在频率域内进行分解；然后在充分考虑人眼对图象的视觉效果的基础上对小波系数进行量化和行程编码；最后针对小波系数量化和行程编码所得的码字分布特性，采用感知熵编码实现编码码率趋近于图象的感知熵，采用该方法可在保证一定图象质量的情况下，消除冗余信息，提高图家编码的压缩比。     

Contourlet域方向子带稀疏表示的图像压缩感知

为了提高压缩感知中图像的稀疏表示性能, 提出了一种Contourlet域方向子带稀疏表示的图像压缩感知算法。将图像Contourlet分解后的多个高频子带根据方向正交特点进行重组, 采用随机高斯矩阵对重组后的子带分别进行测量, 实现压缩采样; 利用正交匹配追踪法重建各子带系数, 并进行Contourlet反变换重构原图像。实验结果表明, 在相同采样率下, 算法重构图像的主观视觉效果和峰值信噪比都优于小波压缩感知算法。     

基于感知生成对抗网络的图像压缩感知重建

现有的深度压缩感知重建算法在低采样率下,由于使用像素损失指导优化的网络会使得重建的图像无法有效地提取出原始图像的纹理细节,导致重建图像视觉观感较差.针对上述问题,提出了基于感知生成对抗网络的图像压缩感知重建算法,用感知损失代替像素损失,使得重建图像细节和纹理特征保留.通过对比实验表明,提出的基于感知生成对抗网络的图像压缩感知重建算法在低采样率下重建出的图像具有更强的视觉效果和真实性.     

Pan-sharpening based on common saliency feature analysis and multiscale spatial information extraction for multiple remote sensing images

ABSTRACT

The requirements of spectral and spatial quality differ from region to region in remote sensing images. The employment of saliency in pan-sharpening methods is an effective approach to fulfil this kind of demands. Common saliency feature analysis, which considers the mutual information between multiple images, can ensure the consistency and accuracy when assigning saliency to regions in different images. Thus, we propose a pan-sharpening method based on common saliency feature analysis and multiscale spatial information extraction for multiple remote sensing images. Firstly, we extract spatial information by the guided filter and accurate intensity component estimation. Then, a common saliency feature analysis method based on global contrast calculation and intensity feature extraction is designed to obtain preliminary pixel-wise saliency estimation, which is subsequently integrated with text-featured based compensation to generate adaptive injection gains. The introduction of common saliency feature analysis guarantees that the same pan-sharpening strategy will be applied to regions with similar features in multiple images. Finally, the injection gains are used to implement the detail injection. Our proposal satisfies diverse needs of spatial and spectral information for different regions in the single image and guarantees that regions with similar features in different images are treated consistently in the process of pan-sharpening. Both visual and quantitative results demonstrate that our method has better performance in guaranteeing consistency in multiple images, improving spatial quality and preserving spectral fidelity.     

Compressed sensing based remote sensing image reconstruction via employing similarities of reference images

In the traditional reconstruction algorithm for compressed sensing, we use the measurement matrix and the corresponding observed image to recover the target image. In the application of remote sensing, there are many multi-source and multi-temporal reference images that have similar information to that of the target image. In this paper, we propose an algorithm to reconstruct the target image with information from multi-source and multi-temporal reference images to improve the image reconstruction accuracy, in other words, to improve the degree of similarity between the reconstructed image and the target image. The basic principle of our method is to construct a penalty term with the similarity of the target sparse coefficient and the reference sparse coefficient to constrain the reconstruction process. The experimental results demonstrate the effectiveness of our method.     

Retargeting images and video for preserving information saliency.

A nonphotorealistic algorithm for retargeting images adapts large images so that important objects in the image are still recognizable when displayed at a lower target resolution. Unlike existing image manipulation techniques such as cropping and scaling, the retargeting algorithm can handle multiple important objects in an image. To identify the important objects in an image, we must first segment the image. We use mean-shift image segmentation to decompose an image into homogeneous regions.     

Accurate saliency detection based on depth feature of 3D images

This paper presents an accurate saliency detection algorithm customized for 3D images which contain abundant depth cue. Firstly, depth feature is calculated based on the sharp regions’ positions within the focal stack. Then, we compute the coarse saliency map by subtracting the background region from the all-focus image according to the depth feature. Finally, we employ the contrast information in the coarse saliency map to obtain the final result. Experiments on light field dataset demonstrate that our approach favorably outperforms five state-of-the-art methods in terms of precision, recall and F-Measure. Moreover, the depth feature is validated to be a valuable complement to existing visual saliency analysis under the circumstance that the background regions are complex or similar to salient object regions.     

How important is location information in saliency detection of natural images

Location information, i.e., the position of content in image plane, is considered as an important supplement in saliency detection. The effect of location information is usually evaluated by integrating it with the selected saliency detection methods and measuring the improvement, which is highly influenced by the selection of saliency methods. In this paper, we provide direct and quantitative analysis of the importance of location information for saliency detection in natural images. We firstly analyze the relationship between content location and saliency distribution on four public image datasets, and validate the distribution by simply treating location based Gaussian distribution as saliency map. To further validate the effectiveness of location information, we propose a location based saliency detection approach, which completely initializes saliency maps with location information and propagate saliency among patches based on color similarity, and discuss the robustness of location information’s effect. The experimental results show that location information plays a positive role in saliency detection, and the proposed method can outperform most state-of-the-art saliency detection methods and handle natural images with different object positions and multiple salient objects.     

Robust palmprint identification based on directional representations and compressed sensing

In this paper, we propose a novel approach for palmprint recognition, which contains two interesting components: directional representation and compressed sensing. Gabor wavelets can be well represented for biometric image for their similar characteristics to human visual system. However, these Gabor-based algorithms are not robust for image recognition under non-uniform illumination and suffer from the heavy computational burden. To improve the recognition performance under the low quality conditions with a fast operation speed, we propose novel palmprint recognition approach using directional representations. Firstly, the directional representation for palmprint appearance is obtained by the anisotropy filter, which is robust to drastic illumination changes and preserves important discriminative information. Then, the principal component analysis (PCA) is used for feature extraction to reduce the dimensions of the palmprint images. At last, based on a sparse representation on PCA feature, the compressed sensing is used to distinguish palms from different hands. Experimental results on the PolyU palmprint database show the proposed algorithm have better performance than that of the Gabor based methods.     

一种基于目标先验信息的视觉跟踪算法

针对运动目标跟踪过程中出现的遮挡问题,提出了基于目标先验信息的视觉显著性遮挡目标跟踪算法。在粒子滤波框架下,利用目标先验信息生成视觉显著图,并根据粒子区域颜色特征与目标颜色特征模板之间的相似度来判断遮挡情况。当遮挡发生时,提高特征融合公式中显著性特征的融合权重,从而充分利用目标未被遮挡部分信息来完成跟踪。实验结果表明,利用目标先验信息的目标跟踪算法能显著提升跟踪遮挡目标的鲁棒性。     

An adaptive enhancement algorithm based on visual saliency for low illumination images

Applied Intelligence - In order to improve the brightness and contrast of low illumination color images and avoid over enhancement, an adaptive image enhancement algorithm based on visual saliency...     

Curvelet变换的多波段遥感图像融合研究

提出一种基于Curvelet变换的多波段遥感图像融合算法。Curvelet变换具有比小波变换更好的边缘表达,因而更适合图像的融合处理。采用具有多尺度、多方向特点的Curvelet变换对多波段遥感图像像进行分解。对于低频系数采用平均融合算法,根据高频子图边缘分布差异,对于方向高频系数采用区域边缘检测和区域谱熵算法实现多波段遥感图像的融合处理。实验结果表明,提出的算法与传统算法相比在保留原始图像边缘和纹理信息同时,可以有效地取得较好的融合视觉效果。