Siamese CNN-based rank learning for quality assessment of inpainted images

Existing NR-IIQA (no reference-based inpainted image quality assessment) algorithms assess the quality of an inpainted image via artificially designed unnaturalness expression, which often fail to capture inpainted artifacts. This paper presents a new deep rank learning-based method for NR-IIQA. The model adopts a siamese deep architecture, which takes a pair of inpainted images as input and outputs their rank order. Each branch utilizes a CNN structure to capture the global structure coherence and a patch-wise coherence assessment module (PCAM) to depict the local color and texture consistency in an inpainted image. To train the deep model, we construct a new dataset, which contains thousands of pairs of inpainted images with ground-truth quality ranking labels. Rich ablation studies are conducted to verify the key modules of the proposed architecture. Comparative experimental results demonstrate that our method outperforms existing NR-IIQA metrics in evaluating both inpainted images and inpainting algorithms.     

闪烁体缺陷引起的CT图像伪影修复

为了修复X射线投影图像中闪烁体缺陷引起的图像伪影,提高X射线投影图像的三维重构质量,结合X射线成像过程中闪烁体缺陷的结构特点,提出了一种改进的BSCB修复算法(IBSCB)。利用Kirsch算子对本底图像进行处理,获得标记出闪烁体缺陷像素的掩膜图像。进而对样品投影图像中相应的缺陷区域按照由外及内的顺序迭代进行修复和扩散,在对外层缺陷区域修复完成后,利用修复后的信息修复内部缺陷区域,并且根据周围缺陷像素的个数确定修复和扩散过程中的迭代系数和迭代次数;对于其中的修复过程,采用log算子滤波,并将滤波后的信息沿等照度线方向扩散实现图像修复。从主观视觉和客观数据两方面对BSCB和IBSCB修复算法进行评价。不同放大倍率下X射线投影图像的修复结果表明:IBSCB不但提高了修复质量,而且其修复速度也比BSCB算法提高了5~6倍。比较修复前后X射线投影图像的三维重构图像,进一步验证了本文算法的有效性。     

Fuzzy two-step filter for impulse noise reduction from color images.

A new framework for reducing impulse noise from digital color images is presented, in which a fuzzy detection phase is followed by an iterative fuzzy filtering technique. We call this filter the fuzzy two-step color filter. The fuzzy detection method is mainly based on the calculation of fuzzy gradient values and on fuzzy reasoning. This phase determines three separate membership functions that are passed to the filtering step. These membership functions will be used as a representation of the fuzzy set impulse noise (one function for each color component). Our proposed new fuzzy method is especially developed for reducing impulse noise from color images while preserving details and texture. Experiments show that the proposed filter can be used for efficient removal of impulse noise from color images without distorting the useful information in the image.     

自然地表红外图像的模拟

自然界的地表是非常复杂的,影响其温度分布和红外辐射特性的因素很多,如地表的起伏、土壤类型、植被类型、土壤湿度和气象条件等.要精确计算自然地表的温度和红外辐射特性,生成红外图像,必须建立考虑各种影响因素的三维传热传质模型.这种方法要花费大量的计算时间,是不实用的.文中利用一维模型的计算结果并结合随机模拟方法,针对具体自然地表(不同植被、裸露地表等)的实际红外辐射强度的相关长度、均方根误差以及相邻像素点的空间距离,模拟生成了自然地表的红外图像.探测器的视场和视角对观察到的图像影响是很大的,对同一地面区域,使用不同视场的探测器观察,得到的图像不同,即使使用同一探测器,如果用不同的视角观察同一区域,得到的图像也是不同的.因此文中根据不同的红外探测器视场以及同一探测器的不同的视角,将该图像转换成了红外探测器视场内的图像,分析了对应不同视场和视角的自然地表红外图像的特征.     

A new image registration method for grey images

The proposed algorithm relies on a group of new formulas for calculating tangent slope so as to address angle feature of edge curves of image. It can utilize tangent angle features to estimate automatically and fully the rotation parameters of geometric transform and enable rough matching of images with huge rotation difference. After angle compensation, it can search for matching point sets by correlation criterion, then calculate parameters of affine transform, enable higher-precision emendation of rotation and transferring. Finally, it fulfills precise matching for images with relax-tense iteration method. Compared with the registration approach based on wavelet direction-angle features, the matching algorithm with tangent feature of image edge is more robust and realizes precise registration of various images. Furthermore, it is also helpful in graphics matching.     

Blind quality assessment of tone-mapped images using multi-exposure sequences

The tone mapping operator (TMO) enables high dynamic range (HDR) images to be presented on low dynamic range (LDR) consumer electronic devices. However, the results obtained by this method are not always ideal due to the reduced number of bits. In comparison, the multi-exposure image fusion (MEF) bypasses the intermediate HDR image composition and directly produces an image presented on standard devices. Inspired by this, this paper proposes a quality assessment method for tone-mapped image (TMI) based on generating multi-exposure sequences. Specifically, the method uses a generative adversarial network (GAN) to generate a set of sequences with different exposure levels based on the TMIs. Then a two-branch convolutional neural network (CNN) is used to extract features from the tone-mapped images and the multi-exposure reference sequences, respectively. Finally, the transformer is used to mine the intrinsic connections between TMIs and multi-exposure sequences and learn the mapping relationships from feature space to quality space. We conducted extensive experiments on the ESPL-LIVE HDR database. The applicability and effectiveness of the proposed method are verified by comparing and analyzing relevant features and model configurations with existing mainstream evaluation algorithms.     

Copy-move image forgery detection based on Gabor magnitude

With advancement of media editing software, even people who are not image processing experts can easily alter digital images. Various methods of digital image forgery exist, such as image splicing, copy-move forgery, and image retouching. The most common method of tampering with a digital image is copy-move forgery, in which a part of an image is duplicated and used to substitute another part of the same image at a different location. In this paper, we present an efficient and robust method to detect such artifacts. First, the tampered image is segmented into overlapping fixed-size blocks, and the Gabor filter is applied to each block. Thus, the image of Gabor magnitude represents each block. Secondly, statistical features are extracted from the histogram of orientated Gabor magnitude (HOGM) of overlapping blocks, and reduced features are generated for similarity measurement. Finally, feature vectors are sorted lexicographically, and duplicated image blocks are identified by finding similarity block pairs after suitable post-processing. To enhance the algorithm’s robustness, a few parameters are proposed for removing the wrong similar blocks. Experiment results demonstrate the ability of the proposed method to detect multiple examples of copy-move forgery and precisely locate the duplicated regions, even when dealing with images distorted by slight rotation and scaling, JPEG compression, blurring, and brightness adjustment.     

Multimodal Medical Image Fusion Based on Sugeno's Intuitionistic Fuzzy Sets

Multimodal medical image fusion is the process of retrieving valuable information from medical images. The primary goal of medical image fusion is to combine several images obtained from various sources into a distinct image suitable for improved diagnosis. Complexity in medical images is higher, and many soft computing methods are applied by researchers to process them. Intuitionistic fuzzy sets are more appropriate for medical images because the images have many uncertainties. In this paper, a new method, based on Sugeno's intuitionistic fuzzy set (SIFS), is proposed. First, medical images are converted into Sugeno's intuitionistic fuzzy image (SIFI). An exponential intuitionistic fuzzy entropy calculates the optimum values of membership, non‐membership, and hesitation degree functions. Then, the two SIFIs are disintegrated into image blocks for calculating the count of blackness and whiteness of the blocks. Finally, the fused image is rebuilt from the recombination of SIFI image blocks. The efficiency of the use of SIFS in multimodal medical image fusion is demonstrated on several pairs of images and the results are compared with existing studies in recent literature.     

Improved joint reversible data hiding in encrypted images

This paper proposes an improved method of reversible data hiding in encrypted images (RDH-EI). Three parties constitute the proposed system: the image owner, the remote server and the recipient. To preserve privacy, an image owner encrypts the original image using a stream cipher algorithm and uploads the ciphertext to a remote server. On server side, a data-hider is allowed to embed additional message into the encrypted image using a swapping/shifting based algorithm. After downloading the marked encrypted image from the server and implementing the decryption, a recipient can extract the hidden messages and losslessly recover the original image. Experimental results show that the proposed method achieves a larger payload than the related works. Meanwhile, a limitation in the related works that few bits can be embedded into the encrypted medical images is also eliminated in the proposed method.     

基于特征提取的红外与可见光图像融合

为提高红外与可见光图像融合的效果,加快融合算法处理速度,提出了一种基于特征提取的图像融合算法。改进了数学形态学中的顶帽运算,用于提取源图像的特征图像及背景图像;设计融合规则,对特征图像及背景图像分别进行融合处理;最后重构得到融合图像。另外,对本文融合方法的参数选择进行了分析,并且设计了适用于背景图像融合的自适应加权融合规则。实验表明,该融合方法能有效获取源图像的特征信息,提供丰富的背景信息,运算速度快,易于硬件实现。     

基于最大相关准则的阈值处理算法

阈值法是图像分割的一种重要方法，在图像处理与识别中广为应用，本文提出了一种基于最大相关准则的自动选择阈值方法，该方法通过使图像中目标和背景分布的相关量最大来选择阈值，仿真分析显示该算法计算量与熵方法比较大大减少，分割效果则比Yen等人提出的算法更佳。     

基于隶属度的人脸图像特征抽取和识别

本文首先从代数理论和模糊数学导出一种新概念，矢量隶属函数，由此构造图像的隶属函数，并证明它具有一些不变性，提出一种基于隶属函数的图像特征抽取和识别方法，并应用于人脸图像识别问题。实验结果表明，隶属函数具有良好的识别分离能力。     

基于Sugeno补的广义模糊熵阈值分割方法

鉴于传统的基于模糊熵的图像阈值分割方法对于光照不均匀图像的分割结果很不理想,该文提出了基于Sugeno补的广义模糊熵图像阈值分割方法。首先按照Sugeno补函数不动点的变化,对一幅图像产生9个阈值,然后利用图像分割质量评价指标对这9个阈值进行评价,最后选择使得评价指标最大的阈值作为最优的阈值。与传统的模糊熵阈值分割方法相比,新方法增加了选择更好的分割结果的机会,对于光照不均匀的图像能够获得比传统模糊熵方法更好的分割效果。     

多时相遥感影像变化检测算法研究

本文首次将非下采样Contourlet变换和上下截集模糊Kohonen聚类网络相结合,提出了一种无监督的多时相遥感影像变化检测算法。该算法采用非下采样Contourlet变换提取与对数比图像中的每个像素相对应的多尺度和多方向纹理,并采用上下截集模糊Kohonen聚类网络将这些多尺度和多方向纹理分为变化类与未变化类两类,最终得到变化检测图像。实验结果表明,与传统方法相比,对于高斯和斑点噪声,该算法具有更高的抗噪性能和检测精确度。     

Feature analysis and centromere segmentation of human chromosome images using an iterative fuzzy algorithm

Classification of homologous chromosomes is essential to advanced studies of cancer genetics. Centromere intensities are believed to be an important differentiating feature between homologs. Therefore, segmentation of centromeres is a major step toward the realization of homolog classification. This paper describes an iterative fuzzy algorithm which successfully segments centromeres from images of human chromosomes prepared using fluorescence in-situ hybridization technique. The algorithm is based on assigning a fuzzy membership value to each pixel in the centromere image. An iterative algorithm then updates and minimizes a defined error function. Chromosome 22, a highly heteromorphic chromosome, is used to verify the centromere segmentation method. Homologs of this chromosome are classified based on their segmented centromere intensities as well as their morphological differences. The classification results of these two methods agree completely and are used to validate our developed algorithm.     

一种SAR图像的自动匹配算法及实现

合成孔径雷达(SAR)图像的匹配处理是SAR图像后处理及应用的重要环节。该文提出了一种基于图像特征的快速匹配实现方法。针对两幅SAR图像,该方法进行边缘检测和区域轮廓提取以及区域特征描述,最后实现图像的自动匹配。利用真实SAR图像进行了试验,获得很好的试验结果。     

复杂场景微波辐射图像的模拟

模拟生成微波辐射图像是为了用其作地形匹配制导中的基准图。文中分析了光学图像和微波辐射图像之间的几何关系，讨论了光学图像的分割、识别及表面方向获取的方法，论述了地物表面温度、亮度温度、视在温度、天线温度和天空温度之间的关系，并在此基础上提出了一种模拟生成复杂场景微波辐射图像的方法。仿真结果表明，方法完全可行。     

基于图像噪声分析的计算机生成图像检测算法

计算机生成图像与自然图像在物理生成机理上的差异性导致其在噪声分布上具有明显的区别,据此提出一种基于图像噪声分析的计算机生成图像检测新方法。首先,用小波隐马尔可夫(MMT)模型对图像噪声进行预处理;接着,基于最大似然估计方法估测图像参考模式噪声;最后,在提取图像模式噪声统计距及其与参考模式噪声相关差值基础上,利用支持向量机(SVM)分类器进行鉴别。实验结果显示,较已有的典型算法,该算法具有更好的检测率。     

An efficient reversible authentication scheme for demosaiced images with improved detectability

The existing probability based reversible authentication schemes for demosaiced images embed authentication codes into rebuilt components of image pixels. The original demosaiced image can be totally recovered if the marked image is unaltered. Although these schemes offer the goal of pixel-wise tamper detection, the generated authentication codes are irrelevant to the image pixels, causing some undetectable intentional alterations. The proposed method pre-processes the rebuilt components of demosaiced images and hashes them to generate authentication codes. With the guide of a randomly-generated reference table, authentication codes are embedded into the rebuilt components of demosaiced images. Since the distortions of image pixels are sensitive to the embedded authentication codes, the proposed method further alters the pre-processed pixels to generate a set of authentication codes. One of the authentication codes that minimizes the distortion is embedded to generate marked demosaiced images. The results show that the proposed method offers a better image quality than prior state-of-the-art works, and is capable of detecting a variety of tampering.