光滑逼近超完备稀疏表示的图像超分辨率重构

为改善单帧降质图像的分辨率水平,提出了一种新的基于稀疏表示的学习法超分辨率图像重构方法。针对信号在既定的欠定超完备字典下的非稀疏性问题,采用光滑的递减函数逼近L0范数以避免对稀疏度先验的依赖,从而实现待重构图像块的有效稀疏表示,同时通过梯度下降的迭代优化获得稳定的收敛解。与双立方插值相比,图像的三倍超分辨实验显示,图像峰值信噪比(PSNR)提高2dB,框架相似性(SSIM)改善0.04,重构图像剔除了更多的模糊退化及边缘伪迹。该方法适于单帧降质图像的超分辨率增强。     

基于贝塔过程联合字典学习的图像超分辨重建

为了提高图像超分辨效果,针对以往稀疏字典超分辨算法仅适用于单特征空间的问题,提出基于贝塔过程联合字典学习(BPJDL)的图像超分辨重建(SRR)方法。首先,根据图像退化模型生成训练样本图像,分别对高、低分辨率图像进行7×7分块,并利用吉布斯采样对图像块进行采样,生成字典训练样本。然后,依据贝塔过程先验模型,建立连接高、低分辨率图像空间的双参数联合稀疏字典,将字典稀疏系数分解为系数权值和字典原子的乘积,通过训练和更新字典,得到同时适用于两个特征空间的字典映射矩阵。最后,进行图像超分辨稀疏重构。实验结果表明:本文方法能以更小尺寸的稀疏字典重建超分辨图像,与当前最先进的稀疏表示超分辨算法相比,结果图像主观视觉上纹理细节信息更丰富,客观评价参数峰值信噪比(PSNR)提高约1.5 dB,结构相似性(SSIM)提高约0.02,超分辨重建时间降低约50 s。     

运用稀疏表示法进行单幅图像超分辨的内点方法

稀疏表示法在单幅图像超分辨率重建问题中受到广泛的关注.本文介绍了一种使用稀疏表示进行超分辨率图像重建的方案.该方案首先由低分辨率的输入图像块求取稀疏表示系数,然后根据此系数生成对应的高分辨率图像块,最后由高分辨率块重建出整幅图像.在求取稀疏表示系数时,本文采用了一种借助预处理共轭梯度算法计算搜索方向的内点方法.仿真结果...     

基于耦合过完备字典的红外云图超分辨率方法

针对红外云图分辨率低的问题,提出一种基于耦合过完备字典的超分辨率方法。在分析红外云图成像退化模型的基础上,建立了采用稀疏表示理论的超分辨率重构框架,首先随机抽取大量高、低分辨率云图的图像块,组成训练样本,经过字典学习获取针对高、低分辨率云图块的两个字典Dh和Dl,为保证对应的高、低分辨率云图块关于各自的字典具有相似的稀疏表示,提出一种耦合字典学习算法,该算法改变了字典对的更新策略,通过在每一步迭代中交替优化Dh和Dl,得到耦合的过完备字典对;最后对输入的低分辨率红外云图,采用最优正交匹配追踪算法(Optimized Orthogonal Matching Pursuit Algorithm,OOMP),得到满足重构约束的高分辨率云图。实验结果表明,本文方法与其他方法相比,红外云图重构质量有较为明显的改善,而且比同类方法具有更高的计算效率。     

基于稀疏表示的车牌图像超分辨率算法研究

介绍一种应用于车牌图像的稀疏表示超分辨率算法,依据稀疏表示理论,自然图像在合适的过完备字典下总存在稀疏的表示,为输入的低分辨率图像寻找一个稀疏表示,用稀疏系数来生成高分辨率输出图像。通过对低分辨率和高分辨率图像补丁的联合训练生成字典,该字典提供低分辨率图像补丁的稀疏表示,用来生成高分辨率图像补丁。     

基于图像自相似性及字典学习的超分辨率重建算法

图像超分辨率重建技术在重构图像细节,改善图像视觉效果等方面起着重要作用.为了提高超分辨率图像的重构质量,本文结合图像自身和自然图像库信息进行超分辨率重建.先利用图像在不同尺度的自相似性,形成图像金字塔,只用单幅低分辨率图像进行超分辨率重建;然后利用自然图像库进行字典学习并以初步得到的重建图像作为输入再次处理;在图像后处理时,利用图像非局部相似性和迭代反投影,进一步提高重建效果.实验结果表明,本文的方法与其它几种基于学习的超分辨率算法比较,无论主观视觉效果上还是峰值信噪比上都有明显提高.     

稀疏表示图像超分辨率重建的自适应方法

提出了一种参数自适应的图像超分辨率重建方法.在基于稀疏表示的图像超分辨率重建的经典算法模型框架下,正则化参数可以根据每个图像补丁本身情况自适应地确定,从而克服了人为选择参数且所有补丁参数需一致的缺点,因此使图像重建效果得到提升.实验结果表明,我们所提方法在不同尺寸扩大因子和噪声环境下都优于人工确定参数的情形,三种评价指标均表明所提方法是有效的.     

一种基于MOD字典学习的图像超分辨率重建新算法

将低分辨率图像重建成高分辨率图像是图像处理领域中的一个重要课题。Yang提出一种基于联合字典学习的图像超分辨率重建算法,其算法样本选取与字典训练方法较为复杂。提出一种基于MOD字典学习的图像超分辨率重建新算法,首先采用少量的训练样本代替Yang的大量训练样本,然后使用MOD字典学习算法代替Yang的FFS字典学习算法,最后利用字典对图像进行稀疏表示与重建。实验结果表明,所提出的算法速度较快,并且重建图像的质量较高。     

一种基于自样本学习的人脸图像超分辨率复原算法

针对人脸图像超分辨率复原问题,提出了一种新的基于自样本学习的超分辨率复原算法.该算法从输入图像本身提取训练样本库,并采用矢量量化的方法对训练样本进行分类.再利用并行设计的多类预测器对每类样本进行学习训练,指导高频信息的估计重建.对来自输入图像本身的自样本训练集合和来自特定训练图像库的特定训练样本集合进行了对比研究.实验结果表明提出算法在图像重建质量和实现速度上都有很好的表现.     

一种改进的三维块匹配图像去噪算法

目的为了有效消除噪声图像中的椒盐噪声、高斯噪声甚至混合噪声,改进三维块匹配算法,提出一种新的图像去噪算法。方法首先,该算法将含噪声图像用图像块之间的相似性构建三维矩阵。然后,在图像块之间进行硬阈值滤波降低噪声,对图像块集合加权平均重建得到初步估计去噪图像。最后,对初步估计结果图像进行块匹配,在图像块内和图像块之间进行维纳滤波和加权中值滤波,得到最终去噪图像。结果仿真结果表明,该算法对图像采集的常见噪声均表现出理想的去噪效果,PSNR值均大于31 d B。对比维纳滤波、中值滤波、硬阈值小波滤波,文中算法对高斯噪声、椒盐噪声和混合噪声的去噪结果 PSNR值为31.5334~36.6466 d B,均高于其他算法,最高差值达到12.08 d B。结论结合中值滤波和三维块匹配算法的图像去噪算法,能够较好去除噪声图像的多种类型噪声,是一种较为优秀的去噪算法。     

基于可分离字典的稀疏和低秩表示图像去噪

目的 为了有效去除图像中的椒盐噪声，提高图像质量。方法 文中将可分离字典和低秩表示结合，提出基于可分离字典的稀疏和低秩表示算法(SLRR–SD)。首先，使用可分离字典代替传统的过完备字典可分离字典可以对二维图像直接表示。其次，使用Frobenius范数对分离字典进行约束以挖掘字典内部的低秩性。此外，为了挖掘图像内部的稀疏结构，对表示系数使用稀疏约束进一步提升表示的有效性。结果 提出的算法在噪声强度为5%、10%、20%和30%下，PSNR/FSIM的平均值分别为32.736/0.975、29.769/0.957、29.295/0.951和26.768/0.921。结论 文中算法保留了相邻列之间的相关性，并且可分离字典优化过程也降低了计算负担。实验结果表明，该算法在保留原图像信息的同时能更好地完成去噪任务。     

Improving representation-based classification for robust face recognition

The sparse representation classification (SRC) method proposed by Wright et al. is considered as the breakthrough of face recognition because of its good performance. Nevertheless it still cannot perfectly address the face recognition problem. The main reason for this is that variation of poses, facial expressions, and illuminations of the facial image can be rather severe and the number of available facial images are fewer than the dimensions of the facial image, so a certain linear combination of all the training samples is not able to fully represent the test sample. In this study, we proposed a novel framework to improve the representation-based classification (RBC). The framework first ran the sparse representation algorithm and determined the unavoidable deviation between the test sample and optimal linear combination of all the training samples in order to represent it. It then exploited the deviation and all the training samples to resolve the linear combination coefficients. Finally, the classification rule, the training samples, and the renewed linear combination coefficients were used to classify the test sample. Generally, the proposed framework can work for most RBC methods. From the viewpoint of regression analysis, the proposed framework has a solid theoretical soundness. Because it can, to an extent, identify the bias effect of the RBC method, it enables RBC to obtain more robust face recognition results. The experimental results on a variety of face databases demonstrated that the proposed framework can improve the collaborative representation classification, SRC, and improve the nearest neighbor classifier.     

Denoising Medical Images Using Deep Learning in IoT Environment

Medical Resonance Imaging (MRI) is a noninvasive, nonradioactive, and meticulous diagnostic modality capability in the field of medical imaging. However, the efficiency of MR image reconstruction is affected by its bulky image sets and slow process implementation. Therefore, to obtain a high-quality reconstructed image we presented a sparse aware noise removal technique that uses convolution neural network (SANR_CNN) for eliminating noise and improving the MR image reconstruction quality. The proposed noise removal or denoising technique adopts a fast CNN architecture that aids in training larger datasets with improved quality, and SARN algorithm is used for building a dictionary learning technique for denoising large image datasets. The proposed SANR_CNN model also preserves the details and edges in the image during reconstruction. An experiment was conducted to analyze the performance of SANR_CNN in a few existing models in regard with peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and mean squared error (MSE). The proposed SANR_CNN model achieved higher PSNR, SSIM, and MSE efficiency than the other noise removal techniques. The proposed architecture also provides transmission of these denoised medical images through secured IoT architecture.     

Wavelet Based Restoration of Images with Missing or Damaged Pixels

This paper addresses the problem of how to restore degraded images where the pixels have been partly lost during transmission or damaged by impulsive noise. A wide range of image restoration tasks is covered in the mathematical model considered in this paper – e.g. image deblurring, image inpainting and super-resolution imaging. Based on the assumption that natural images are likely to have a sparse representation in a wavelet tight frame domain, we propose a regularization-based approach to recover degraded images, by enforcing the analysis-based sparsity prior of images in a tight frame domain. The resulting minimization problem can be solved efficiently by the split Bregman method. Numerical experiments on various image restoration tasks – simultaneously image deblurring and inpainting, super-resolution imaging and image deblurring under impulsive noise – demonstrated the effectiveness of our proposed algorithm. It proved robust to mis-detection errors of missing or damaged pixels, and compared favorably to existing algorithms.     

非负矩阵分解耦合视觉词典的图像检索算法

目的解决当前图像检索技术中,图像特征稀疏编码收敛速度慢,以及局部特征空间信息不足易导致检索误差较大等问题,提出一种基于l0稀疏约束非负矩阵分解耦合视觉词典优化的图像检索算法。方法首先,在非负矩阵分解(Non-negative Matrix Factorization,NMF)的基础上,对系数矩阵设置l0个约束来限制其稀疏性,从而定义一种l0稀疏约束的NMF方法。再通过一种自适应序列词典初始化方案,从训练样本获得词典的初始估计。然后,利用l0稀疏约束的NMF来增强视觉词典,对图像局部描述符进行稀疏编码,并利用最大池化操作来生成聚合特征向量,从而保留局部描述符的关键属性。最后根据得到的特征向量,引入Minkowski距离来衡量查询图像与数据库的相似性,输出检索图像。结果实验结果表明,与当前图像检索方案相比,所提算法具有更高的查准-查全率和收敛速度。结论所提算法返回的图像与查询图像相似度高,在包装商标检索等领域具有一定的参考价值。     

基于深度强化学习的图像去模糊方法

目的为了有效地去除多种图像模糊,提高图像质量,提出基于深度强化学习的图像去模糊方法。方法选用GoPro与DIV2K这2个数据集进行实验,以峰值信噪比(PSNR)和结构相似性(SSIM)为客观评价指标。通过卷积神经网络获得模糊图像的高维特征,利用深度强化学习结合多种CNN去模糊工具建立去模糊框架,将峰值信噪比(PSNR)作为训练奖励评价函数,来选择最优修复策略,逐步对模糊图像进行修复。结果通过训练与测试,与现有的主流算法相比,文中方法有着更好的主观视觉效果,且PSNR值与SSIM值都有更好的表现。结论实验结果表明,文中方法能有效地解决图像的高斯模糊和运动模糊等问题,并取得了良好的视觉效果,在图像去模糊领域具有一定的参考价值。     

Difference of Visual Information Metric Based on Entropy of Primitive

Image sparse representation is a method of efficient compression and coding of image signal in the process of digital image processing. Image after sparse representation, to enhance the transmission efficiency of the image signal. Entropy of Primitive (EoP) is a statistical representation of the sparse representation of the image, which indicates the probability of each base element. Based on the EoP, this paper presents an image quality evaluation method-Difference of Visual Information Metric (DVIM). The principle of this method is to evaluate the image quality with the difference between the original image and the distorted image. The comparative experiments between DVIM & PSNR & SSIM are carried out. It was found that there was a great improvement in the image quality evaluation of geometric changes. This method is an effective image quality evaluation method, which overcomes the weakness of other quality evaluation methods for geometrically changing images to a certain extent, and is more consistent with the subjective observation of the human eye.     

Determination of candidate subjects for better recognition of faces

In order to improve the accuracy of face recognition and to solve the problem of various poses, we present an improved collaborative representation classification (CRC) algorithm using original training samples and the corresponding mirror images. First, the mirror images are generated from the original training samples. Second, both original training samples and their mirror images are simultaneously used to represent the test sample via improved collaborative representation. Then, some classes which are “close” to the test sample are coarsely selected as candidate classes. At last, the candidate classes are used to represent the test sample again, and then the class most similar to the test sample can be determined finely. The experimental results show our proposed algorithm has more robustness than the original CRC algorithm and can effectively improve the accuracy of face recognition.