基于Contourlet变换和仿生模式识别的纹理图像识别方法

纹理图像的分类是目前一个非常活跃的研究课题。针对现有纹理图像分类算法的局限性,本文提出了一种基于Contourlet变换和仿生模式识别方法的纹理图像识别算法。首先应用Contourlet变换获得能量特征的方法提取能量特征,进而利用仿生模式识别算法实现对纹理图像的识别。采用Vistex纹理库数据进行仿真实验,结果表明:与传统的分类方法相比,利用Contourlet变换和仿生模式识别结合进行纹理图像的识别能获得更高的正确率和速度,最佳正确率可达100%。     

Tampering with a watermarking-based image authentication scheme

We analyse a recent image authentication scheme designed by Chang et al. [A watermarking-based image ownership and tampering authentication scheme, Pattern Recognition Lett. 27 (5) (2006) 439-446] whose first step is based on a watermarking scheme of Maniccam and Bourbakis [Lossless compression and information hiding in images, Pattern Recognition 37 (3) (2004) 475-486]. We show how the Chang et al. scheme still allows pixels to be tampered, and furthermore discuss why its ownership cannot be uniquely binding. Our results indicate that the scheme does not achieve its designed objectives of tamper detection and image ownership.     

一种低信噪比图像的模拟退火恢复算法

本文根据马尔可夫(Markov)随机场模型和全局最大后验概率估计技术提出了一种模拟退火图像恢复算法.应用这种算法对混入可加性独立高斯噪声的试验图像进行恢复的实验结果表明,该算法对低信噪比图像数据的恢复处理非常有效.     

A version of the Swendsen-Wang algorithm for restoration of images degraded by Poisson noise

An algorithm for restoration of images degraded by Poisson noise is proposed. The algorithm belongs to the family of Markov chain Monte Carlo methods with auxiliary variables. We explicitly use the fact that medical images consist of finitely many, often relatively few, grey-levels. The continuous scale of grey-levels is discretized in an adaptive way, so that a straightforward application of the Swendsen-Wang (Phys. Rev. Lett. 58 (1987) 86) algorithm becomes possible. Partial decoupling method due to Higdon (J. Am. Statist. Assoc. 93 (1998) 442, 585) is also incorporated into the algorithm. Simulation results suggest that the algorithm is reliable and efficient.     

噪声对PET图像质量的影响研究

研究PET图像噪声与质量的关系,作为选择最适当的PET重建迭代次数或迭代停止的依据.利用蒙特卡罗模拟Siemens ECAT PET扫描仪,用OSEM、MLEM迭代重建算法获得Huffman、Utah重建图像,使用了SSIM、PSNR两种不同质量评价方法估算图像质量并以标准偏差评估噪声.结果显示Huffman图像噪声随着迭代次数增加,图像质量随着迭代次数降低;均值滤波除燥会降低图像质量;利用Utah重建图像进行再度计算也得同样结果.说明噪声影响到图像质量的计算,噪声滤除会造成最优图像的计算错误.精准的估算噪声并且有效的滤除,将可获得真正最优迭代图像,作为停止迭代依据.     

Efficient convolution algorithms with an FIR representable as a spline

The convolution is calculated in the case when the finite impulse response can (FIR) be representable as a spline. This approach is a practical illustration of the method proposed in [4, 5] for constricting an efficient convolution algorithm. A brief theoretical justification of the approach is given. An efficient convolution algorithm for a Gaussian FIR is constructed as an example and is compared with other convolution algorithms. Vladislav Valer’evich Myasnikov. Born 1971. Graduated from the Samara State Aerospace University (SSAU) in 1994. Began his graduate study at SSAU in 1995 and received candidate’s degree in technical sciences in 1998. Senior researcher at the Image Processing Systems Institute of the Russian Academy of Sciences and associate professor at the SSAU Department of Geoinformatics. Research interests: digital signal and image processing, geoinformatics, neural networks, and pattern recognition. Author of more than 60 publications, including 24 papers and 1 monograph (coauthored). Member of the Russian Association for Pattern Recognition and Image Analysis. Ol’ga Aleksandrovna Titova. Born 1980. Graduated with honors from the Samara State Aerospace University in 2003. Graduate student at SSAU from 2003 to 2006. Assistant professor at the SSAU Department of Geoinformatics. Research interests: digital processing of signals and images, including remote sensing data; geoinformation systems; and pattern recognition. Author of 19 publications, including 4 papers. Member of the Russian Association for Pattern Recognition and Image Analysis.     

模糊推理最大熵图像恢复算法

与线性恢复算法相比,基于最大熵的图像恢复算法具有更好的图像恢复效果,但其收敛速度较慢。为了提高最大熵图像恢复算法的收敛速度,首先给出了算法的非周期反卷积模型,然后采用模糊推理系统在线确定算法的迭代步长。由于采用了可变步长,因此极大地提高了算法的收敛速度。仿真实验表明提出的算法收敛速度快,图像恢复效果好。     

特征驱动先验的归一化卷积超分辨率重建

目的 针对融合—复原法超分辨率重建中融合与复原两大环节,提出新的改进算法框架：用改进的归一化卷积实现融合,再用改进的最大后验估计实现复原,得到更优的超分辨率重建。方法 改进的归一化卷积引入了双适应度函数和一种新的混合确定度函数;改进的最大后验估计,引入一种特征驱动先验模型,该模型通过混合两种不变先验模型而得到,形式完全取决于图像自身的统计特征。结果 用本文算法对不同降质水平的图像进行重建,并与其他若干算法重建结果比较。无论从视觉效果还是从评价指标,本文算法均优于其他算法。结论 本文超分辨率重建算法,融合环节兼顾了邻域像素的空间距离和光度差,充分利用两种确定度函数的各自优势,可以抑制更多噪声和异常值;复原环节的先验模型依据图像特征而不是经验,对图像刻画更准确。实验结果也验证了本文算法的有效性。     

Software environment for simulating algorithms for image analysis and processing

We consider the purpose, functionality, configuration, and structure of a software environment designed for simulation and investigation of methods, algorithms, and information technology for digital images analysis and processing. Mikhail V. Gashnikov. Born 1975. Graduated from the Samara State Airspace University (SSAU) in 1998. Received candidate’s degree in Technology in 2004. He is now an assistant professor at the chair of earth information of the SSAU. Scientific interests: image processing, compression, statistical coding. Author of more than 30 publications, including 12 papers and one monograph (in coauthorship). Member of the Russian Association for Pattern Recognition and Image Analysis. Evgenii V. Myasnikov. Born 1981. Graduated from the Samara State Airspace University in 2004. He is now a post-graduate student at the Chair of Earth Information of the Samara State Airspace University. Scientific interests: development of software systems, image processing, image retrieval in databases. Author of 6 publications, including one paper. Member of the Russian Association for Pattern Recognition and Image Analysis. Andrei V. Chernov. Born 1975. Graduated from the Samara State Airspace University (SSAU) in 1998. Received candidate’s degree in Technology in 2004. He is now an assistant professor at the Chair of Earth Information of the SSAU and a research fellow at the Institute of Image Processing Systems, Russian Academy of Sciences. Scientific interests: image processing, pattern recognition, geoinformation systems. Author of more than 50 publications, including 11 papers and one monograph (in coauthorship). Member of the Russian Association for Pattern Recognition and Image Analysis. Nikolai I. Glumov. Born 1962. Graduated from the Kuibyshev Airspace Institute (at present, the Samara State Airspace University) in 1985. Received candidate’s degree in Technology in 1994. He is now a senior researcher at the Institute of Image Processing Systems, Russian Academy of Sciences. Scientific interests: image processing and pattern recognition, compression of images, simulation of systems of digital image formation. Author of more than 50 publications, including 21 papers and one monographs (in coauthorsip). Member of the Russian Association for Pattern Recognition and Image Analysis. Vladislav V. Sergeev. Born 1951. Graduated from the Kuibyshev Airspace Institute (at present, the Samara State Airspace University) in 1974. Received doctoral degree in Technology in 1993. Head of the Laboratory of Mathematical Methods for Image Processing at the Institute of Image Processing Systems, Russian Academy of Sciences. Scientific interests: digital signal processing, image analysis, pattern recognition, earth information. Author of more than 150 publications, including approximately 40 papers and two monographs (in coauthorship). President of the Povolzh’e Branch of the Russian Association for Pattern Recognition and Image Analysis. Corresponding member of the Russian Ecological Academy and of the Russian Academy of Engineering Sciences. Member of the International Society for Optical Engineering. A laureate of the Samara Provincial Government prize in science and engineering. Marina A. Chicheva. Born 1964. Graduated from the Kuibyshev Airspace Institute (at present, the Samara State Airspace University) in 1987. Received candidate’s degree in Technology in 1998. She is now a senior researcher at the Institute of Image Processing Systems, Russian Academy of Sciences. Scientific interests: image recognition, compression, fast algorithms for discrete transformations. Author of more than 40 publications, including 15 papers and one monograph (in coauthorship). Member of the Russian Association for Pattern Recognition and Image Analysis.     

基于低分辨率图像融合的超分辨率恢复方法

提出一种基于多帧低分辨图像融合的超分辨率图像恢复算法。将多帧低分辨图像融合成一帧与高分辨图像分辨率一致的图像,并对其中一幅低分辨图像插值,形成迭代恢复算法的初始值,在此基础上以Tikhonov正则化方法求解原始高分辨图像。分析和实验结果表明,该算法具有良好的鲁棒性,并且计算速度较快。     

Motion correction based on an appropriate system matrix for statistical reconstruction of respiratory-correlated PET acquisitions

Respiratory motion correction in positron emission tomography (PET) seeks to incorporate motion information into an image reconstruction algorithm by using the full counting statistics of an acquisition to generate a single, motion-free volume. Here, we present a motion-incorporated ordered subsets expectation maximization (MOSEM) reconstruction based on a device-dedicated tomographic projector in which each matrix element is calculated directly from the voxels’ Cartesian coordinates alone. The motion is corrected by updating this projector as a function of the respiratory level. The performance of the reconstruction method was investigated with three datasets: two simulations of a transaxially or axially moving lesion on a patient acquisition and a third acquisition of a moving sphere. After the 16th sub-iteration, the normalized mean square error (NMSE, with a motionless acquisition as reference) was 0.20 for the non-corrected (ungated) image and 0.01 for the MOSEM image with transaxial motion simulation. Likewise, NMSE was 0.30 for the ungated image and 0.03 for MOSEM image with axial motion simulation. For the phantom, ungated reconstruction yielded an error of 0.78, whereas MOSEM yielded 0.43. The error reduction resulted from enhancement and reduced spreading of the moving uptake. Our results show that MOSEM reconstruction yields motion-corrected images which are similar to motionless reference images.     

基于融合细分的纹理图像重构模型

针对分段迭代曲线拟合存在的重建区域轮廓不连续、重建区域尺寸有误差等问题,提出了一种基于融合细分的纹理图像重构模型.首先提取原始图像的分割区域,经过轮廓跟踪与下采样得到区域形状的特征向量;然后利用三重逼近与三重插值统一的融合细分方法,重建区域轮廓曲线;最后合成区域纹理,得到纹理图像重构结果.在多幅自然场景图像上进行实验验证,并给出相应的实验结果和分析.实验结果表明,所提模型正确有效,具有和人类视觉特性相符合的重构结果; 所提算法能够减少图像重建时的处理时间,并在图像质量主观评价指标上明显优于多区域图像重建算法.     

基于深度学习的水下图像超分辨率重建方法

由于水体本身的特性以及水中悬浮颗粒对光的吸收和散射作用,水下图像普遍存在信噪比（SNR）低、分辨率低等一系列问题,但大部分方法传统处理方法包含图像增强、复原及重建,都依赖退化模型,并存在算法病态性问题。为进一步提高水下图像恢复算法的效果和效率,提出了一种改进的基于深度卷积神经网络的图像超分辨率重建方法。该方法网络中引入了改良的密集块结构（IDB）,能在有效解决深度卷积神经网络梯度弥散问题的同时提高训练速度。该网络对经过配准的退化前后的水下图像进行训练,得到水下低分辨率图像和高分辨率图像之间的一个映射关系。实验结果表明,在基于自建的水下图像作为训练集上,较卷积神经网络的单帧图像超分辨率重建算法（SRCNN）,使用引入了改良的密集块结构（IDB）的深度卷积神经网络对水下图像进行重建,重建图像的峰值信噪比（PSNR）提升达到0.38 dB,结构相似度（SSIM）提升达到0.013,能有效地提高水下图像的重建质量。     

Efficiency analysis of image compression algorithms based on hierarchical and wavelet representations

The efficiency of hierarchical and wavelet image compression methods is analyzed and compared. More specifically, hierarchical grid interpolation (HGI) is compared with JPEG-2000. The characteristics of both methods are analyzed, and recommendations are given concerning their use in various image-processing applications. Alina Yur’evna Bavrina. Born 1980. Graduated from the Samara State Aerospace University in 2003. Received her candidate’s degree in technical sciences in 2006. Junior researcher at the Image Processing Systems Institute of the Russian Academy of Sciences. Research interests: image processing, image compression, and geoinformation technology. Author of more than 20 publications, including 6 papers. Member of the Russian Association for Pattern Recognition and Image Analysis. Mikhail Valer’evich Gashnikov. Born 1975. Graduated from the Samara State Aerospace University (SSAU) in 1998. Received his candidate’s degree in technical sciences in 2002. Associate professor at the SSAU Department of Geoinformatics. Research interests: image processing, compression, and statistical coding. Author of more than 50 publications, including 21 papers and 1 monograph (coauthored). Member of the Russian Association for Pattern Recognition and Image Analysis. Nikolai Ivanovich Glumov. Born 1962. Graduated from the Kuibyshev Aviation Institute (now the Samara State Aerospace University) in 1985. Received candidate’s degree in technical sciences in 1994. Senior researcher at the Image Processing Systems Institute of the Russian Academy of Sciences. Research interests: image processing, pattern recognition, image compression, and simulation of digital image formation systems. Author of more than 90 publications, including more than 30 papers and 1 monograph (coauthored). Member of the Russian Association for Pattern Recognition and Image Analysis.     

Adaptive contourlet-wavelet iterative shrinkage/thresholding for remote sensing image restoration

In this paper, we present an adaptive two-step contourlet-wavelet iterative shrinkage/thresholding （TcwlST） algorithm for remote sensing image restoration. This algorithm can be used to deal with various linear inverse problems （LIPs）, including image deconvolution and reconstruction. This algorithm is a new version of the famous two-step iterative shrinkage/thresholding （TWIST） algorithm. First, we use the split Bregrnan Rudin-Osher-Fatemi （ROF） model, based on a sparse dictionary, to decompose the image into cartoon and texture parts, which are represented by wavelet and contourlet, respectively. Second, we use an adaptive method to estimate the regularization parameter and the shrinkage threshold. Finally, we use a linear search method to find a step length and a fast method to accelerate convergence. Results show that our method can achieve a signal-to-noise ratio improvement （ISNR） for image restoration and high convergence speed.     

光学合成孔径图像超分辨率重建技术研究

针对光学合成孔径固有的中低频损失而导致的成像模糊问题,提出一种改进的超分辨率生成对抗网络(SRGAN)进行图像复原研究;首先通过MATLAB构建光学合成孔径图像数据集,并对数据集进行数据增强处理,其次根据ASPP网络设计思想,构建多尺度SRGAN生成器的残差结构,最后与传统超分辨率重建算法进行复原效果对比;实验结果表明,该算法可加快模型收敛速度,提升模型获取图像细粒度特征的能力,对于光学合成孔径图像的复原效果更优。     

基于改进FOCUSS算法的电容层析成像算法研究

针对电容层析成像(electrical capacitance tomography,ECT)逆问题求解的病态性和不适定性,在压缩感知(compressed sensing,CS)的基础上,提出一种改进FOCUSS的ECT重建算法。采用离散余弦变换(DCT)基将原始图像灰度信号进行稀疏化处理,在使用正则化FOCUSS算法求解的过程中引入拟牛顿法逼近求解中间稀疏变量,以提高信号重构的准确性。仿真实验结果表明,同LBP、Tikhonov和Landweber和FOCUSS算法相比,改进的FOCUSS算法能够有效区分物场中的不同介质,改善图像过度平滑的问题,减小图像误差至0.23,提高图像相关系数至0.80,具有更好的成像效果,为ECT图像重建算法的研究提供新的思路。     

基于模糊阈值分割的ECT图像重建方法

电容层析成像(ECT)技术是近年来发展较快的过程成像技术之一,图像重建算法是其应用的关键。但由于ECT的软场特性,重建的图像往往具有边界模糊效应。提出一种基于模糊阈值的ECT图像重建方法。该方法采用Landweber法进行图像重建,引入模糊阈值法确定重建图像的最佳阈值。采用仿真实验对该方法进行了验证,结果表明:该方法重建图像精度较高,具有较大的实用价值。     

基于SURF的连续帧图像配准及高光去除

物体上的高光直接影响工业检测、模式识别和计算机视觉等领域中后续处理的算法性能。如何检测和消除图像中的高光区域一直是个热点问题。这里介绍了一种基于SURF的连续帧图像配准及高光去除的方法。首先,利用SURF特征检测及其特征描述方法,对连续帧图像进行自动配准;其次,在连续帧图像配准后,对图像进行融合;最后,输出去除高光的图像。实验表明:该方法用于消除或消弱高光区域有比较好的效果,有一定的理论和应用价值。