CNN Based No-Reference HDR Image Quality Assessment

Motivated by the problems of non-universality and over-reliance on the original reference image in High dynamic range (HDR) Image quality assessment (IQA), a convolutional neural network-based algorithm for no-reference HDR image quality assessment is proposed. The Salience detection by self-resemblance (SDSR) algorithm which extracts the salient regions of the HDR image, is used to simulate the human visual attention mechanism. Then a visual quality perception network for training quality prediction models is designed according to the visual characteristics of luminance and contrast sensitivity. And this network consists of an Error estimation network (Error-net), a Perceptual resistance network (PR-net) and a mixing function. The experimental results indicate that the method proposed has high consistency with subjective perception, and the value of assessment metrics Spearman rank-order correlation coefficient (SROCC), Pearson product-moment correlation coefficient (PLCC) and Root mean square error (RMSE) correspondingly reaches 0.941, 0.910 and 8.176 as well. It is comparable with classic full-reference HDR IQA methods.     

No-reference image quality assessment based on hybrid model

The aim of research on the no-reference image quality assessment problem is to design models that can predict the quality of distorted images consistently with human visual perception. Due to the little prior knowledge of the images, it is still a difficult problem. This paper proposes a computational algorithm based on hybrid model to automatically extract vision perception features from raw image patches. Convolutional neural network (CNN) and support vector regression (SVR) are combined for this purpose. In the hybrid model, the CNN is trained as an efficient feature extractor, and the SVR performs as the regression operator. Extensive experiments demonstrate very competitive quality prediction performance of the proposed method.     

A no-reference perceptual image quality assessment database for learned image codecs

The drastic growth of research in image compression, especially deep learning-based image compression techniques, poses new challenges to objective image quality assessment (IQA). Typical artifacts encountered in the emerging image codecs are significantly different from that produced by traditional block-based codecs, leading to inapplicability of the existing objective IQA algorithms. Towards advancing the development of objective IQA algorithms for recent compression artifacts, we built a learning-based compressed image quality assessment (LCIQA) database involving traditional block-based image codecs, hybrid neural network based image codecs, convolutional neural network based and generative adversarial network (GAN) based end-to-end optimized image coding approaches. Our study confirms the statistical difference and human perception difference between reconstructions of learned compression and traditional block-based compression. We propose a two-step deep learning model for learning-based compressed image quality assessment. Extensive experiments on LCIQA database demonstrate that our proposed model performs better than other counterparts on learning-based compressed images, especially on GAN compressed images, and achieves competitive performance to the state-of-the-art IQA metrics on traditional compressed images.     

No-reference Stereoscopic Image Quality Assessment Using Binocular Self-similarity and Deep Neural Network

Quality assessment of three-dimensional (3D) images is more challenging than that of 2D images. The quality of 3D visual experience is one of the most challenging areas of human binocular perception and is affected by multiple factors such as asymmetric stereo image/video compression, depth perception, visual discomfort, and single view quality. In this paper, we propose a new no-reference quality assessment method for stereoscopic images based on Binocular Self-similarity (BS) and Deep Neural Networks (DNN). To be more specific, a BS index is defined and computed according to binocular rivalry and suppression based on the depth image-based rendering technique. Then, a DNN is trained in an opinion unaware way to predict local quality. Binocular integration (BI) index is calculated by using the trained DNN, accounting for binocular integration behaviors. Finally, the final quality score of stereoscopic image is obtained by combining the BS and BI indexes together. Experimental results on four public 3D image quality assessment databases demonstrate that compared with existing methods, the proposed method can achieve high consistency with subjective perception on stereoscopic images with both symmetric and asymmetric distortions.     

针对对比度变化的图像质量评价方法

由于对比度变化容易引入图像亮度和色彩等失真,本文提出了一种面向对比度变化的图像质量评价方法CCIQA。所提方法先将图像进行亮度和色度分离,再分别根据亮度强度变化和明暗对比度变化提取亮度失真因子和根据色度相似性提取色度失真因子,接着依照基于亮度强度的权重图进行融合并计算得到最终图像质量评价分数。所提CCIQA方法在4个常用的数据库,TID2008,TID2013,CID2013和CCID2014进行广泛测试。实验结果表明所提CCIQA算法符合人眼视觉对对比度变化的主观感知,且算法性能优于多个最新图像质量评价方法。      

基于非局部梯度的图像质量评价算法

图像质量评价研究的目标在于模拟人类视觉系统对图像质量的感知过程,构建与主观评价结果尽可能一致的客观评价算法。现有的很多算法都是基于局部结构相似设计的,但人对图像的主观感知是高级的、语义的过程,而语义信息本质上是非局部的,因此图像质量评价应该考虑图像的非局部信息。该文突破了经典的基于局部信息的算法框架,提出一种基于非局部信息的框架,并在此框架内构建了一种基于非局部梯度的图像质量评价算法,该算法通过度量参考图像与失真图像的非局部梯度之间的相似性来预测图像质量。在公开测试数据库TID2008, LIVE, CSIQ上的数值实验结果表明,该算法能获得较好的评价效果。

     

结合多尺度深度学习网络和Retinex理论的低光照图像增强算法

针对低光照增强任务缺乏参考图像及现有算法存在的色彩失真、纹理丢失、细节模糊、真值图像获取难等问题,本文提出了一种基于Retinex理论与注意力机制的多尺度加权特征低光照图像增强算法。该算法通过基于Unet架构的特征提取模块对低光照图像进行多尺度的特征提取,生成高维度的多尺度特征图;建立注意力机制模块凸显对增强图像有利的不同尺度的特征信息,得到加权的高维特征图;最后反射估计模块中利用Retinex理论建立网络模型,通过高维特征图生成最终的增强图像。设计了一个端到端的网络架构并利用一组自正则损失函数对网络模型进行约束,摆脱了参考图像的约束,实现了无监督学习。最终实验结果表明本文算法在增强图像的对比度与清晰度的同时维持了较高的图像细节与纹理,具有良好的视觉效果,能够有效增强低光照图像,视觉质量得到较大改善;并与其他多种增强算法相比,客观指标PSNR和SSIM得到了提高。     

Pair comparison based progressive subjective quality ranking for underwater images

Underwater images contain an interacting mixture of distortions due to the physicochemical properties of the water, suspended organic matter and floating particles in water. Unlike images in traditional natural image quality databases, underwater images are often difficult to acquire with reference images and sets of images with gradient distortion. Therefore, it is even more difficult for the viewers to assign an absolute psychophysical scale to the quality of underwater images. In this paper, we propose a pairwise subjective comparison procedure for underwater images quality ranking inspired by the intuitive suppression and competence mechanisms in visual perception. In the proposed method, we construct a preselection based initial image quality dataset by full pairwise comparison, which also enables online adaptive new image updating. The proposed method is not constrained by the lack of reference images, and is reliable and sensitive to images with discriminable distortion level and various image contents. The proposed pairwise comparison further allows an uncertain choice, which does not require a reinforce human opinion. To the best of our knowledge, this is the first implementation for underwater image subjective quality ranking, and a new approach to the image quality ranking for different image contents with unknown distortion level. We demonstrate that the obtained subjective image ranking correlates well with the human perception of quality difference among the underwater images than that of the single stimuli image quality assessment with finite labor burden. Moreover, our proposed method accurately characterize the gradual degradation in the underwater image sequence taken in controlled conditions. The proposed progressive learning ranking is also an alternative way to realize adaptive extension of the existing image quality databases.     

Nonlocal low-rank matrix completion for image interpolation using edge detection and neural network

In this paper, we propose a nonlocal low-rank matrix completion method using edge detection and neural network to effectively exploit the nonlocal inter-pixel correlation for image interpolation and other possible applications. We first interpolate the images using some basic techniques, such as bilinear and edge-directed methods. Then, each image patch is categorized as smooth regions, edge regions, or texture regions and adaptive interpolating mechanisms are applied to each specific type of regions. Finally, for each specific type of regions, neural networks and low-rank matrix completion are employed to accurately update the results. An iteratively re-weighted minimization algorithm is used to solve the low-rank energy minimization function. Our experiments on benchmark images clearly indicate that the proposed method produces much better results than some existing algorithms using a variety of image quality metric in terms of both objective image quality assessment and subjective quality assessment.     

基于稀疏表示的立体图像客观质量评价方法

提出了一种基于稀疏表示的立体图像质量评价方法 ,分为训练和测试两个部分。在训练部 分,通过训练不同频带的立体图像获得立体图像的稀疏字典;在测试部分,根据稀疏字典计 算得到立体图 像的稀疏特征,定义了稀疏特征相似度衡量原始和失真图像信息的差异,并根据稀疏字典计 算了频带增益和左右视点的融合权值,最后融合稀疏特征相似度作为立体图像质量的 客观评价值。在立体图像测试库上的实验结果表明,本文方法的评价结果与主观评价结果有 较好的相关性,符合人类视觉系统的感知。     

Reduced-reference stereoscopic image quality assessment based on view and disparity zero-watermarks

As a practical and novel application of watermarking, this paper presents a zero-watermarking based objective reduced-reference stereoscopic image quality assessment (RR-SIQA) method. In the proposed method, two kinds of zero-watermarks are constructed according to the characteristics of image structure and stereoscopic perception. Concretely, two view zero-watermarks, which are constructed by judging the relation of the horizontal and vertical components of gradient vectors with respect to the two views, are used to reflect the image structure variation of the stereoscopic image. Meanwhile, a disparity zero-watermark, which is constructed with disparity map of the stereoscopic image, is used to reflect the stereoscopic perception quality variation. Then, the quality of stereoscopic image is objectively assessed by pooling the recovering rates of the detected zero-watermarks. The experimental results show that the stereoscopic image quality evaluation results assessed with the proposed RR-SIQA method are well consistent with subjective assessment, and the proposed method achieves better performance than the widely used full-reference stereoscopic image quality assessment method PSNR in assessing quality of stereoscopic images compressed with JPEG and JPEG2000.     

基于双眼视觉感知特征一致性的立体图像体验质量评价

3D图像被认为是多媒体技术的重要标志,其中,立体图像质量对3D图像发展起到至关重要的作用。不同于传统的2D图像质量评价,在3D图像质量评价中引入关于体验质量（ QoE）问题的新挑战,因此,本文提出一个基于双眼视觉感知特征一致性的立体图像体验质量评价算法。具体地,先对2个视点图像提取像素梯度作为视觉感知的低层次特征,再用梯度方向直方图特征（ HOG）建立立体图像的视觉感知特征向量,然后,由支持向量回归（ SVR）方法来学习视觉感知特征与立体图像体验质量得分的关系,最后,通过训练好的SVR模型来预测立体图像体验质量。实验结果表明所提算法能够有效地预测立体图像体验质量。     

No-reference image quality assessment based on spatial and spectral entropies

We develop an efficient general-purpose no-reference (NR) image quality assessment (IQA) model that utilizes local spatial and spectral entropy features on distorted images. Using a 2-stage framework of distortion classification followed by quality assessment, we utilize a support vector machine (SVM) to train an image distortion and quality prediction engine. The resulting algorithm, dubbed Spatial–Spectral Entropy-based Quality (SSEQ) index, is capable of assessing the quality of a distorted image across multiple distortion categories. We explain the entropy features used and their relevance to perception and thoroughly evaluate the algorithm on the LIVE IQA database. We find that SSEQ matches well with human subjective opinions of image quality, and is statistically superior to the full-reference (FR) IQA algorithm SSIM and several top-performing NR IQA methods: BIQI, DIIVINE, and BLIINDS-II. SSEQ has a considerably low complexity. We also tested SSEQ on the TID2008 database to ascertain whether it has performance that is database independent.     

基于人类视觉的感知立体图像质量评价方法

为了实现对不同失真类型的立体图像进行质量评 价,提出了一种基于人类视觉的立体图像 质量客观评价方法,分别从图像清晰度与立体感两方面进行评价。图像清晰度方面,将原始 与失真立体图 像分解为5个带通图像后利用对比度敏感度函数(CSF)优化各失真带通图像,并模拟掩 盖效应,通过整合各原始 带通图像,综合感知误差,构造信噪比(SNR)作为评价图像 清晰度的性能指标;立体感方面,对绝对差值图像进 行视觉感知模拟,建立SNR指标评价立体感的优劣。实验结 果表明,对不同失真类型立体图像的评价 结果表明,Pearson线性相关系数(PLCC)与Spearman等级 相关系数(SRCC)均优于现有评价方法。     

Image quality assessment based on deep learning with FPGA implementation

To improve image quality assessment (IQA) methods, it is believable that we have to extract image features that are highly representative to human visual perception. In this paper, we propose a novel IQA algorithm by leveraging an optimized convolutional neural network architecture that is designed to automatically extract discriminative image quality features. And the IQA algorithm uses local luminance coefficient normalization, dropout and the other advanced techniques to further improve the network learning ability. At the same time the proposed IQA algorithm is implemented based on Field Programmable Gate Array (FPGA) and further evaluated on two public databases. Extensive experimental results have shown that our method outperforms many existing IQA algorithms in terms of accuracy and speed.     

一种Enlighten-GAN网络的指纹超分辨率重建方法北大核心CSCD

将低分辨率(LR)图像重建为高分辨率(HR)图像的主流模型是生成对抗网络(GAN)。然而,由于基于GAN的方法利用从其他图像中学习到的内容来恢复高频信息,在处理新的图像时往往会产生伪影。由于,指纹图像的特征比自然图像更加复杂。因此,将以前的网络应用于指纹图像,尤其是中等分辨率的图像,会导致收敛不稳定伪影效果更加严重。针对以上弊端,本文提出了一种Enlighten-GAN超分辨率方法,来解决指纹图像的重建问题。具体来说,我们设计了启发块来控制网络收敛到一个可靠的点,并利用自我监督分层感知损失以改进损失函数提升网络性能。实验结果证明Enlighten-GAN方法在指纹图像的重建效果性能上具有更加卓越的效果。     

基于小波分析的图像稀疏保真度评价

该文针对传统的图像质量评价方法无法有效模拟人类视觉系统(HVS)存在的不足,提出基于小波分析的加权稀疏保真度(Weighting Sparse Fidelity, WSF)图像评价算法。算法以模拟人类视觉系统的神经网络为切入点,对图像进行一阶小波分解得到4个不同方向的子带图像,然后将子带图像分成88大小的图像块,采用快速独立分量分析(FastICA)的方法对各个图像块进行训练并提取图像特征检测矩阵,根据特征检测矩阵计算各子带图像块的稀疏特征值并建立稀疏保真度质量评价模型。在此基础上,根据细节信息的不同对低频子带图像进行区间划分并设置视觉权重,使之更加接近人眼的主观视觉。实验中对LIVE库中所有图像进行算法验证,其结果表明,所提方法能很好地对各种失真类型的图像进行评价。基于小波分析的稀疏保真度评价算法能够有效模拟人类视觉系统的多频特性和视觉皮层感知机制,弥补现有图像质量评价方法在此方面的不足。     

基于业务感知的认知网络QoS自适应控制技术

文章研究并提出了基于业务感知的认知网络服务质量(QoS)自适应控制架构。该架构在智能业务感知和分类模型的基础上对数据包进行分类和识别,并借鉴控制理论通过基于端路协同的认知网络业务流QoS自适应控制机制实现对网络流量的控制。在认知网络环境下,该架构可以构建QoS的自动感知、分析、关联、反馈、决策、配置和实施机制,进行资源的优化调整分配,适应网络环境的变化,优化网络端到端的性能,保证用户的服务质量。     

A reference-free underwater image quality assessment metric in frequency domain

Owing to the complexity of the underwater environment and the limitations of imaging devices, the quality of underwater images varies differently, which may affect the practical applications in modern military, scientific research, and other fields. Thus, achieving subjective quality assessment to distinguish different qualities of underwater images has an important guiding role for subsequent tasks. In this paper, considering the underwater image degradation effect and human visual perception scheme, an effective reference-free underwater image quality assessment metric is designed by combining the colorfulness, contrast, and sharpness cues. Specifically, inspired by the different sensibility of humans to high-frequency and low-frequency information, we design a more comprehensive color measurement in spatial domain and frequency domain. In addition, for the low contrast caused by the backward scattering, we propose a dark channel prior weighted contrast measure to enhance the discrimination ability of the original contrast measurement. The sharpness measurement is used to evaluate the blur effect caused by the forward scattering of the underwater image. Finally, these three measurements are combined by the weighted summation, where the weighed coefficients are obtained by multiple linear regression. Moreover, we collect a large dataset for underwater image quality assessment for testing and evaluating different methods. Experiments on this dataset demonstrate the superior performance both qualitatively and quantitatively.