A new method for evaluating the log-likelihood gradient (score) oflinear dynamic systems

A novel method is presented that is based on the optimal smoothing equations. The result can be used for efficient calculations and approximations of gradient-search algorithms for maximum-likelihood estimation of the unknown system parameters. The method is applied to the continuous-discrete case     

A new method for improvement of image quality in medical ultrasonic diagnostics

The problem of dividing noise and texture elements with regard to specific features of an ultrasonic image is studied. A mathematical model is developed that describes statistical and spectral properties of various elements of the image structure. Based on the mathematical model, the procedure of noise suppression is realized. Clinical tests of the method proved its effectiveness.     

A new standard method of subjective assessment of barely visible image artifacts and a new public database

Assessing image quality is an important aspect of developing new display technology. A particularly challenging assessment is determining whether a bitwise lossy operation is visually lossless. We define “visually lossless” and describe a new standard for a subjective procedure to assess whether the image quality meets these criteria. Assessments are made between a reference image and temporally interleaved reference and test images using a forced‐choice procedure. In extensive testing, we have validated that this method is suitable for discriminating between subtle differences in image rendering and is free of observer bias or criteria variability. The results of these tests demonstrate the efficacy of using as few as five randomly chosen observers. We have found that the subjective testing is more reliable than several widely available image quality metrics. As part of this work, we release a database of nearly 0.25 million subjective responses collected from 35 observers to 18 different images. The study uses a largely within‐subjects design and tested observers from two viewing distances. We encourage the use of this dataset in future research to refine objective image quality metrics to improve predictability of subtle but potentially visible compression‐induced image impairments.     

高动态范围图像客观质量评价方法

针对当前高动态范围（HDR）图像质量评价方法未考虑图像色度和结构信息的问题,提出了一种新的HDR图像客观质量评价方法。首先,利用HDR-VDP-2.2中的基于视觉感知的模型得到关于亮度与对比度的视觉保真度特征;然后,将HDR图像转换到YIQ彩色空间,对彩色空间中的Y、I、Q通道分别进行处理,求得色度相似度和结构相关度特征;最后,利用支持向量回归（SVR）的方法对特征进行融合,预测得到高动态范围图像质量的客观评价值。实验结果表明,与HDR-VDP-2.2相比,该方法的Pearson相关系数和Spearman等级相关系数分别提升了23.09%和25.34%;均方根误差（RMSE）降低了38.01%。所提出的方法与主观视觉感知具有更高的一致性。     

A brain-inspired computational model for extremely few reference image quality assessment

In the study of brain science, the free energy principle and attention perception mechanism have been the two of the most critical findings during the past few decades, arousing a wide range of attention and valuable applications from the research fields of image and video processing, computer vision, etc. Motivated by the aforementioned two important findings, we in this paper develop a brain-inspired computational model for extremely few reference image quality assessment (IQA), dubbed as BCM. The proposed BCM implements with the two main steps. First, we combine free energy principle and sparse perception mechanism to achieve the goal of only using extremely few reference for assessing the image quality. Second, we further introduce the attention perception mechanism to boost the assessment performance by improving the sparse perception mechanism mentioned above. Based on the most commonly used image quality database, it was found that our proposed model has derived higher performance than the peer extremely few reference IQA models and competitive performance as compared with the benchmark full reference IQA models.     

A simple and practical method for evaluating machine translation quality

This article describes a simple and cost effective evaluation method based on post-editing. The results of an experiment using this method, to investigate the improvement of an MT system over time are given, along with some practicalities in carrying through the evaluation (time, effort etc.)     

No reference image quality classification for JPEG-distorted images

In this paper, we address the Image Quality Assessment (IQA) of JPEG-distorted images. We approach the IQA field by focusing on a classification problem that maps different objective metrics into different categorical quality classes. To this end, we adopt a machine learning classification approach, where No Reference (NR) metrics are considered as features, while the assigned classes come from psycho-visual experiments. Eleven NR metrics have been considered: seven specific for blockiness and four general purpose. We evaluate the performance of single metrics and investigate if a pool of metrics can reach better performances than each of the single ones. Five as well as three quality classes are considered, and the corresponding classifiers are tested on two well known databases available in the literature (LIVE and MICT), and on a new database (IVL) presented in this paper.     

A new benchmark image test suite for evaluating colour texture classification schemes

Several image test suites are available in the literature to evaluate the performance of classification schemes. In the framework of colour texture classification, OuTex-TC-00013 (OuTex) and Contrib-TC-00006 (VisTex) are often used. These colour texture image sets have allowed the accuracies reached by many classification schemes to be compared. However, by analysing the classification results obtained with these two sets of colour texture images, we have noticed that the use of colour histogram yields a higher rate of well-classified images compared to colour texture features. It does not take into account any texture information in the image, this incoherence leads us to question the relevance of these two benchmark colour texture sets for measuring the performances of colour texture classification algorithms. Indeed, the partitioning used to build these two sets consists of extracting training and validating sub-images of an original image. We show that such partitioning leads to biased classification results when it is combined with a classifier such as the nearest neighbour. In this paper a new relevant image test suite is proposed for evaluating colour texture classification schemes. The training and the validating sub-images come from different original images in order to ensure that the correlation of the colour texture images is minimized.     

A new discriminative coding method for image classification

Multimedia Systems - The bag-of-words (BOW) based methods are widely used in image classification. However, huge number of visual information is omitted inevitably in the quantization step of the...     

一种针对高斯模糊图像的无参质量评价方法

针对模糊图像高频分量的特性,提出了一种针对高斯模糊图像的无参质量评价方法。该方法利用小波变换对模糊图像提取高频分量,在高频分量功率谱上构造评价指标。实验结果表明提出的评价指标优于PSNR和SSIM,其客观评价分数与主观评价分数具有更好的一致性。     

一种角膜新生血管图像的分割方法

为了提高眼科外眼病图像的分割效果，提出了一种基于直方图和形态学的分割方法，用于分割角膜新生血管的充血区域和血管像素，分割结果用于定量分析充血面积和充血密度，并给出实验结果和误差讨论。实验结果表明，该方法简单快速，分割效果较好。     

A new method of fictitious viscous damping determination for the dynamic relaxation method

This paper develops a new method for calculating the viscous fictitious damping of the dynamic relaxation (DR) method to overcome one of the most crucial difficulties in its application – the low convergence rate. The DR formulation was derived by error minimizations between two successive iterations to deduce an optimum fictitious mass and viscous damping with the aid of the Stodola iterative process. The efficiency of the new method was verified by its application to a wide range of typical structures with strong nonlinearity. The results show that compared to the conventional DR algorithm such as kinetic approach, the new method improves the convergence rate considerably.     

手指静脉图像质量评价

根据手指静脉图像本身的特征,首次提出了手指静脉图像质量评价方法.在分析人类视觉系统(HVS)性能的基础上,将图像有效区域、对比度、位置偏移度、模糊度、信息熵作为评价手指静脉图像质量的参数.并综合分析这些参数,加权获得静脉图像总质量评价函数.实验表明,得到了与主观评价结果相一致的客观评价值.     

面部美化图像质量无参考评价方法

针对目前面部美化已被广泛研究,然而缺乏有效美化图像质量评价方法限制美化技术进一步发展的问题,提出一种面部美化图像质量的无参考评价方法。该方法结合面部美感的认知与感知和面部美化技术以挖掘美化图像的质量表示,首先构建面部美化图像数据库,将面部图像分解为皮肤、眼睛和嘴巴三种区域,然后从肤色、光滑度、光照、灰度差和清晰度等五个方面提取面部美学特征,最后用支持向量回归（SVR）训练面部美化质量模型并预测美化图像的质量。实验结果表明,所提方法在构建的数据库上Pearson线性相关系数和Spearman等级相关系数分别达到0.920 5和0.900 9,优于BIQI（Blind Image Quality Indices）、NIQE（Natural Image Quality Evaluation）图像质量评价方法。     

一种新的星图中星的提取方法

在分析扫描法和矢量法的基础上,提出了块扫描法.首先,根据星像扩散范围和导航星间距确定扫描块的大小;其次,以扫描块为单位,获得其最大灰度值像素,若灰度大于设定背景阈值,则存储其位置信息与灰度值;再次,以存储像素为中心搜索3×3像素阵,若存在像素灰度值大于存储像素,则剔除存储像素;否则,判断像素阵中灰度大于背景阈值的像素个...     

A new level set method for inhomogeneous image segmentation

Intensity inhomogeneity often appears in medical images, such as X-ray tomography and magnetic resonance (MR) images, due to technical limitations or artifacts introduced by the object being imaged. It is difficult to segment such images by traditional level set based segmentation models. In this paper, we propose a new level set method integrating local and global intensity information adaptively to segment inhomogeneous images. The local image information is associated with the intensity difference between the average of local intensity distribution and the original image, which can significantly increase the contrast between foreground and background. Thus, the images with intensity inhomogeneity can be efficiently segmented. What is more, to avoid the re-initialization of the level set function and shorten the computational time, a simple and fast level set evolution formulation is used in the numerical implementation. Experimental results on synthetic images as well as real medical images are shown in the paper to demonstrate the efficiency and robustness of the proposed method.     

A new fast reversible method for image safe transfer

In this paper a novel reversible method for fast and safe image transfer is proposed. The method combines compression, data hiding and partial encryption of images in a single processing step. The proposed approach can embed data into the image according to the message size and partially encrypt the image and the message without changing the original image content. Moreover, during the same process the image is lossless compressed. Nevertheless, the compression rate depends on the upper bound of message size to embed in the image. The main idea is to decompose the original image into two sub-images and to apply various processes to each sub-image in order to gain space and increase the amount of embedded data. The two sub-images are then scrambled and partially encrypted. The most significant characteristic of the proposed method is the utilization of a single procedure to simultaneously perform the compression, the reversible data hiding and the partial encryption rather than using three separate procedures. Our approach reduces then the computational effort and the required computation time. This method is specially suited for medical images where one can associate the patient diagnostic to the concerned medical image for safe transfer purpose.