Multi-focus image fusion based on block matching in 3D transform domain

Fusion methods based on multi-scale transforms have become the mainstream of the pixel-level image fusion. However,most of these methods cannot fully exploit spatial domain information of source images, which lead to the degradation of image.This paper presents a fusion framework based on block-matching and 3D(BM3D) multi-scale transform. The algorithm first divides the image into different blocks and groups these 2D image blocks into 3D arrays by their similarity. Then it uses a 3D transform which consists of a 2D multi-scale and a 1D transform to transfer the arrays into transform coefficients, and then the obtained low-and high-coefficients are fused by different fusion rules. The final fused image is obtained from a series of fused 3D image block groups after the inverse transform by using an aggregation process. In the experimental part, we comparatively analyze some existing algorithms and the using of different transforms, e.g. non-subsampled Contourlet transform(NSCT), non-subsampled Shearlet transform(NSST), in the 3D transform step. Experimental results show that the proposed fusion framework can not only improve subjective visual effect, but also obtain better objective evaluation criteria than state-of-the-art methods.

Improved block matching approach to fast disparity estimation

An improved block matching approach to fast disparity estimation in machine vision applications is proposed, where the matching criterion is the sum of the absolute difference（SAD）.By evaluating the lower bounds, which become increasingly tighter for the matching criteria, the method tries to successively terminate unnecessary computations of the matching criteria between the reference block in one image and the ineligible candidate blocks in another image.It also eliminates the ineligible blocks as early as possible, while ensuring the optimal disparity of each pixel.Also, the proposed method can further speed up the elimination of ineligible candidate blocks by efficiently using the continuous constraint of disparity to predict the initial disparity of each pixel.The performance of the new algorithm is evaluated by carrying out a theoretical analysis, and by comparing its performance with the disparity estimation method based on the standard block matching.Simulated results demonstrate that the proposed algorithm achieves a computational cost reduction of over 50.5% in comparision with the standard block matching method.

An Electronic Image Stabilization Algorithm Based on Efficient Block Matching on the Bitplane

This paper proposes an electronic image stabilization algorithm based on efficient block matching on the plane. This algorithm uses a hexagonal search algorithm, and uses the bit-planes to estimate and compensate for the translational motion between video sequences at the same time;As for the rotary motion vector generated in the video sequences, in order to highlight the intensity change of the image sequence, the algorithm firstly conducts Laplace transform for the reference frame, then select a number of characteristics at the image edge to make block matching with the current frame, calculate and compensate for the rotational movement that may exist finally. Through theoretical analysis and simula-tion, we prove that, as for a mixed translational and rotational motion video sequences, the proposed algorithm can reduce required time for block matching computation ,while improving the accuracy of the electronic image stabilization.

3D Filtering by Block Matching and Convolutional Neural Network for Image Denoising

Block matching based 3D filtering methods have achieved great success in image denoising tasks. However the manually set filtering operation could not well describe a good model to transform noisy images to clean images. In this paper, we introduce convolutional neural network （CNN） for the 3D filtering step to learn a well fitted model for denoising. With a trainable model, prior knowledge is utilized for better mapping from noisy images to clean images. This block matching and CNN joint model （BMCNN） could denoise images with different sizes and different noise intensity well, especially images with high noise levels. The experimental results demonstrate that among all competing methods, this method achieves the highest peak signal to noise ratio （PSNR） when denoising images with high noise levels （σ 〉 40）, and the best visual quality when denoising images with all the tested noise levels.

Fast inter-mode decision method based on best matching block for H.264 encoding

In H.264 encoder, all possible coding modes should be checked to choose the most appropriate mode for every macroblock, which adds a heavy computation burden to the encoder. In this paper, a fast inter-mode decision method is presented to reduce computation complexity of an H.264 encoder. By detecting the best matching block （BMB） before transform and quantization, some coding modes can be skipped and the corresponding encoding steps can be omitted for these BMBs. Meanwhile this method can also be used to detect all-zero blocks. The experimental results show that this method achieves consistently significant reduction of encoding time while keeping almost the same rate-distortion performance.

Predictive Block-Matching Algorithm for Wireless Video Sensor Network Using Neural Network

This paper proposed a back propagation neural network model for predictive block-matching. Predictive block-matching is a way to significantly decrease the computational complexity of motion estimation, but the traditional prediction model was proposed 26 years ago. It is straight forward but not accurate enough. The proposed back propagation neural network has 5 inputs, 5 neutrons and 1 output. Because of its simplicity, it requires very little calculation power which is negligible compared with existing computation complexity. The test results show 10% - 30% higher prediction accuracy and PSNR improvement up to 0.3 dB. The above advantages make it a feasible replacement of the current model.

Steganalysis of MSU Stego Video Based on Block Matching of Interframe Collusion and Motion Detection

MSU Stego Video is a public video steganographic tool, which has strong robustness and is regarded as a real video steganographic tool. In order to increase the detection rate, this paper proposes a new steganoalysis method against MSU, which uses the chessboard character of MSU embedded video, proposes a down-sample block-based collusion method to estimate the original frame and checks the chessboard mode of the different frame between tested frame and estimated frame to detect MSU steganographic evidences. To reduce the error introduced by severe movement of the video content, a method that abandons severe motion blocks from detecting is proposed. The experiment results show that the false negative rate of the proposed algorithm is lower than 5%, and the false positive rate is lower than 2%. Our algorithm has significantly better performance than existing algorithms. Especially to the video that has fast motion, the algorithm has more remarkable performance.

Block-Based Adaptive Image Steganography Using LSB Matching Revisited

Recently, an edge adaptive image stegano- graphic method based on least significant bit （LSB） matching revisited （EA-LSBMR） has been proposed, which holds good visual quality and proper security under appropriate embedding rates. However, from the extensive experiments to EA-LSBMR, we find that the discrete Fourier transform （DFT） spectrum of pixelpairs differences histogram still reveals the presence of a secret message even in a low embedding rate. To enhance the security, a modified scheme is proposed in this paper, which can defeat the above-mentioned analysis and keep the visual quality better than EA-LSBMR in higher embedding rates. Experimental results using a latest universal steganalysis method have demonstrated the proposed method＇s good performance.

Secure Transmission of Compressed Medical Image Sequences on Communication Networks Using Motion Vector Watermarking

Medical imaging plays a key role within modern hospital management systems for diagnostic purposes.Compression methodologies are extensively employed to mitigate storage demands and enhance transmission speed,all while upholding image quality.Moreover,an increasing number of hospitals are embracing cloud computing for patient data storage,necessitating meticulous scrutiny of server security and privacy protocols.Nevertheless,considering the widespread availability of multimedia tools,the preservation of digital data integrity surpasses the significance of compression alone.In response to this concern,we propose a secure storage and transmission solution for compressed medical image sequences,such as ultrasound images,utilizing a motion vector watermarking scheme.The watermark is generated employing an error-correcting code known as Bose-Chaudhuri-Hocquenghem(BCH)and is subsequently embedded into the compressed sequence via block-based motion vectors.In the process of watermark embedding,motion vectors are selected based on their magnitude and phase angle.When embedding watermarks,no specific spatial area,such as a region of interest(ROI),is used in the images.The embedding of watermark bits is dependent on motion vectors.Although reversible watermarking allows the restoration of the original image sequences,we use the irreversible watermarking method.The reason for this is that the use of reversible watermarks may impede the claims of ownership and legal rights.The restoration of original data or images may call into question ownership or other legal claims.The peak signal-to-noise ratio(PSNR)and structural similarity index(SSIM)serve as metrics for evaluating the watermarked image quality.Across all images,the PSNR value exceeds 46 dB,and the SSIM value exceeds 0.92.Experimental results substantiate the efficacy of the proposed technique in preserving data integrity.

限制插入位置的单面基因组框架填充问题研究

基因测序技术的发展使基因组序列的获取速度不断加快,但目前广泛使用的测序技术通常会产生部分基因缺失的基因组框架,使用基因组片段填充技术能够有效提高基因组框架的完整性,降低测序成本。在前期研究中,缺失基因可以在不完整序列的任意两个基因之间插入;在目前研究中,针对以片段重叠群(contig)、块匹配形式给出的待填充基因组框架,其对缺失基因插入位置的选择是有限制的,该类片段填充问题更具一般性。为此,针对限制插入位置的单面基因组框架填充问题进行研究,分析该问题的研究进展,详细讨论了现有FPT算法和近似算法的核心思想、流程以及优缺点等。在研究过程中发现了冗余公共邻接和近似性能低等问题,提出了相应的解决方案,并分析了未来的研究方向和挑战。

基于BM3D的脑MRI图像噪点剔除算法

磁共振成像(Magnetic Resonance Imaging,MRI)已经成为一种常见的影像检查方式,MRI的去噪算法影响着MRI的成像效果。基于深度学习的MRI去噪算法需要一定量的数据,绝大部分基于非深度学习的MRI去噪算法都是将MRI数据转化为实数之后进行去噪的,针对复数MRI中的复数数据类型的算法也存在着失真的问题。因此,提出一种通过单张MRI脑图像的原始数据进行噪点剔除的算法,以此更好得去除图像噪声。该算法从MRI的原始数据出发,利用了MRI噪声分布性质和MRI脑图像的特点,以判断MRI图像中噪声明显的点,从而剔除MRI中特定的莱斯分布的噪声。并将所提出的算法结合了MRI去噪中常用的非局部平均算法(Non-Local Means denoising,NLM)与三维块匹配算法(Block-Matching and 3D filtering,BM3D),并和不使用该算法剔除噪点的NLM、BM3D进行了对比评估。对比结果表明,在噪声密度不同的多种情况下,该算法总能优化与之相结合的图像去噪算法,在不同的噪声情况下使峰值信噪比(Peak Signal-to-Noise Ratio,PSNR)与结构相似性(Structural Similarity,SSIM)提高了1%~9%。最后将该算法结合BM3D,对比了DnCNN、低秩聚类算法(Weighted Nuclear Norm Minimization,WNNM)、BM3D、NLM等用于MRI去噪的算法,在莱斯噪声较多时,该算法在PSNR上有更好的表现。

基于图像块匹配约束的弥散磁共振成像

目的:改善高加速倍数下弥散加权成像的图像重建质量,从而实现加速采集。方法:利用图像块匹配的方法提取弥散图像内相似的图像块,进行低秩特性约束和稀疏约束,随后将其与传统的敏感度编码(SENSE)并行重建算法相结合来改善图像重建质量,降低图像噪声。实验采集两组人体数据,分别比较3倍加速和4倍加速下传统的SENSE重建、基于总变分约束的SENSE(SENSE-TV)重建以及本文方法的重建效果,定量分析弥散图像以及各向异性分数(FA)图与全采样的参考图像的误差。结果:在3倍加速和4倍加速采集下,本文方法均比传统的SENSE、SENSE-TV方法重建的弥散图像质量更好,定量分析的参数FA值更精确,误差更低。结论:利用图像内相似性图像块的低秩特性和稀疏特性约束图像重建,有望实现高加速倍数下的高质量成像。

联合多尺度块匹配的非局部均值去噪算法

针对非局部均值(Non-Local Means,NLM)图像去噪算法易产生伪影与平滑细节的问题,提出一种联合多尺度图像块匹配的像素相似性测度,提高NLM算法去噪性能。首先,研究与分析了加权欧氏距离与欧氏距离两种相似性度量以及图像块尺寸设置对NLM算法的影响。其次,通过引入图像特征信息并利用K-means聚类方法将图像划分为平坦区域和包含边缘与纹理的结构区域,对每个类别中的像素点,联合两种尺度图像块匹配计算像素的平滑权重。最后,优化了算法的滤波参数。实验结果表明,提出的算法在噪声去除与细节保持方面明显优于经典的NLM算法,相比其他改进的NLM算法也有优势。

机载阵列SAR点云区域网平差

阵列SAR技术作为一种新型的三维重建技术,是InSAR发展一个重要的方向。由于其存在与点云位置成非线性关系的高频误差,难以直接用于测绘产品生产。针对阵列SAR点云中误差的特点,首先对点云进行了噪点去除和点云匹配,然后对平面坐标采用线性精化模型,在对高程坐标采用二次多项式精化模型进行平差的基础上,通过增加对虚拟观测值的约束,构建阵列SAR点云数据的区域网平差模型。最后选择山区和城区两种典型地表数据进行实验。分析结果表明:文章所构建的区域网平差模型可有效降低阵列SAR点云定位中存在的高频误差影响;在不同控制点情况下,定位精度和解算稳健性均得到有效提升。

基于卷积神经网络的分形图像编码研究

为了解决图像压缩时间较长的问题,提出了一种基于卷积神经网络的分形图像编码方法。方法将分形图像编码中的Range块和Domain块进行相似度分类,通过采用卷积神经网络来设计新的图像块分类方法,实现编码过程中的并行化图像块分类,编码时每个类在各自类别中进行搜索,减少一些不必要的匹配过程,以此达到减少图像块匹配的计算量,减少图像压缩的时间。实验结果表明,上述方法的图像还原质量更高,且图像压缩编码时间较短,说明其具有较高的应用价值。

一种基于BM3D算法改进的图像去噪方法

在图像处理领域中,三维块匹配算法(BM3D)算法结合了空间域与频率域的相关特性,是当前图像去噪效果最好的算法之一。由于该算法存在计算耗时长、相似块提取不够准确、分割块内分布不同的相似特征无法提取等问题,论文提出基于Radon变换进行图像信息降维,并通过求解降维函数的方差值、以及方差最大值坐标定位进行相似块信息的判断,再计算各相似块相对参考块的像素均值比例,并放缩再用于去噪。实验结果显示,优化算法去噪图像相较于原算法去噪图像运行时间减短,图像质量提升。

基于FPGA的车载流媒体后视镜闪烁抑制系统

针对LED信号灯环境下车载流媒体后视镜面临的闪烁问题,并考虑局部图像快速运动与边缘纹理类复杂场景对图像修复的影响,提出了基于硬件加速系统FPGA的实时闪烁抑制系统。根据闪烁图像的多特征约束闪烁像素,基于连续三帧图像高效检测闪烁,提出了基于邻域图像群的运动估计算法,并通过改进图像匹配准则和对邻域图像矢量聚类的方式改善复杂场景下的图像修复效果;基于ZYNQ平台设计视频数据流的并行流水线架构实现系统加速。实验结果表明:提出的系统可满足分辨率800×480、帧率30 fps视频的实时性需求,且对复杂场景下的闪烁图像抑制效果良好。

基于改进三维块匹配滤波的图像去噪算法

为了有效滤除樱桃图像在获取过程中混杂的不同噪声,保障图像识别与机器自动采摘时良好的图像信息质量,提出一种改进三维块匹配滤波(block-matching and 3D filtering, BM3D)的图像去噪方法.首先,在三维块匹配滤波的基础估计阶段构建自适应中值滤波处理器,滤除图像中部分椒盐噪声,并改进优化硬阈值、滑窗步长及三维硬阈值等关键参数快速滤除高斯噪声;其次,在基础估计阶段与最终估计阶段之间引入中值滤波,最大限度地去除图像中剩余的混合噪声;最后,通过仿真实验验证所提算法的有效性,并对比分析改进前后算法的归一化均方误差、峰值信噪比、信噪比改善因子及结构相似性等性能.结果表明,改进的BM3D方法在保持好樱桃图像细节信息的同时,能有效去除高斯噪声和滤除大概率椒盐噪声,且随混合噪声干扰的增强,所提算法的去噪性能更佳且优于其他滤波方法.

结合人工结构引导和图像块匹配的萌坑村清代壁画修复

为萌坑村清代建筑壁画相关研究提供更为清晰的壁画图像信息,并为相似受损壁画的修复方法提供参考,提出一种融合人工引导和稀疏图像块模型算法的壁画数字化修复方法。从图像信息损失区域、损失程度与已知信息3个方面,对萌坑村清代建筑壁画的损伤现状与类型进行分析。针对壁画结构和内容缺失问题,通过加入人工结构引导的方式以明确修复区域边界。在人工结构引导下,基于图像块与稀疏表示模型算法实现损坏壁画区域的修复。萌坑村M-H-002壁画修复结果表明,所提出方法修复效果更为准确,视觉效果更佳,且在峰值信噪比和结构相似性方面,相较于传统的CDD(Curvature-Driven Diffusion)和Criminisi更优。

适应弱纹理与几何特征的十字匹配块的立体匹配

针对弱纹理、弱几何特征的双目视图,生成视差质量较差的问题,提出了适应弱纹理与几何特征的十字匹配块的立体匹配算法。采用双线性视差插值框架,以提高时间效率;通过双目视图中少量规则点计算其整体视差变化趋势,以较少时间确定视图的最大视差和规则点的视差;融合Census序列、色彩和梯度等信息计算十字匹配块的代价,以增强弱纹理特征的视图的视差生成质量;基于初始视差图像的局部几何特征,十字匹配块和子块旋转相应的最优角度进行代价计算,以增强弱几何特征的视图的视差生成质量。实验结果表明,与SGM、AD-Census、PMS、ELAS等算法比较,生成的视差图像质量整体效果好,对于弱纹理、弱几何特征局部区域,视差质量提升明显;基于6对测试图像,与PMS算法相比,视差图像的均方误差(MSE)减少30.97%,执行时间平均为其1/4。