Inverse tensor transfer with applications to novel view synthesis and multi-baseline stereo

A new tensor transfer-based novel view synthesis (NVS) method is proposed in this paper. As opposed to conventional tensor transfer methods which transfer the pixel from the real input views to the virtual novel view, our method operates inversely in the sense that it transfers a pixel from the novel view image back to the real images. This inverse tensor-transfer approach offers a simple mechanism for associating corresponding image points across multiple views, resulting in geometrically consistent pixel chains across the input images. A colour consistency metric is used to choose the most likely colour for a pixel in the novel image by analysing the spread of colours in each of the possible pixel chains. By emphasizing colour consistency, rather than depth, our method avoids the need to precompute a dense depth map (which is essential for most conventional transfer methods), therefore alleviating many common problems with conventional methods. Experiments involving NVS on real images give promising results. The synthesized novel view image is not only photo-realistic but also has the right geometric relationship with respect to the other views.Since this method avoids explicit depth map computation, we further investigate its applicability to the multi-baseline stereo matching problem (MBS). By using this inverse transfer idea, we are able to handle non-ideally configured MBS in a natural and efficient way. The new MBS algorithm has been used for stereo vision navigation.     

一种改进的快速鲁棒性特征匹配算法

针对光照变化、噪声、局部遮挡等在图像配准技术中对配准精度有重要影响,提出了一种在多尺度空间下点预测快速鲁棒性不变特征的匹配算法。针对在探测对图像的尺度、旋转,仿射具有不变性的斑状特征极值点过程中计算复杂度较高的问题,提出一种特征点预测方法降低了描述子提取的复杂度,增强了对外部环境光照变化、噪声以及局部遮挡的适应能力;并在KD(KD Tree)树基础上,提出了一种动态平衡KD树(DBKD-Tree)快速搜索匹配算法,有效克服了KD树可能存在的病态划分,采用条件约束最邻近搜索,提升匹配效率,实现特征点高精度匹配。通过对在不同光照条件、噪声环境的仿射变换图像特征匹配测试,在加入20%的高斯噪声后,均能100%地完成重复特征检测,达到亚像素定位精度,误配率降低为零。     

匹配概率估计方法

用基准图每个像素的三个特征参数即边缘密度、粗糙度、标准差作为评价模板图像匹配的品质指标，结合Fisher线性分类原理把估计区域匹配概率问题转化为对像素的分类问题，提出了一种匹配概率估计的新方法。实验结果表明，该方法可以有效地估计匹配概率，遴选出适合要求的景象匹配区。     

A New Method for the Estimation of Mass Functions in?the?Dempster�CShafer��s Evidence Theory: Application to Colour Image Segmentation

In this paper, the problem of colour image segmentation is addressed using the Dempster–Shafer (DS) theory. Examples are provided showing that this theory is able to take into account a large variety of special situations that occur and which are not well solved using classical approaches. Modelling both uncertainty and imprecision, and computing the conflict between images and introducing a priori information are the main features of this theory. Consequently, the performance of such a segmentation scheme is largely conditioned by the appropriate estimation of mass functions in the DS evidence theory. In this paper, a new method of automatically determining the mass function for colour-image segmentation problems is presented. The mass function of each pixel is determined by applying possibilistic c-means (PCM) clustering to the grey levels of the three primitive colours. A reliability criterion, associated with each pixel and the mass functions of its neighbouring pixels, is used into a fuzzy based reasoning system in order to decide on the appropriate segmentation. Experimental segmentation results on medical and textured colour images highlight the effectiveness of the proposed method.     

An image pixel based variational model for histogram equalization

In this paper, we develop an image pixel based histogram equalization model for image contrast enhancement. The approach is to propose a variational model containing an energy functional to adjust the pixel values of an input image directly so that the resulting histogram can be redistributed to be uniform. This idea is different from existing histogram equalization algorithms where a histogram based on the input image is constructed, a mapping is determined to output a uniform histogram and then the pixel values of the input image are adjusted based on the mapping. In the variational model, a mean brightness term is incorporated to preserve the brightness of the input image, and a geometry constraint can also be added to keep the geometry structure of the input image. Theoretically, the existence of the minimizer of the proposed model, and the convergence of the proposed algorithm are given. Experimental results are reported to demonstrate that the performance of the proposed model are competitive with the other testing histogram equalization methods for several testing images.     

基于二维最大熵阈值分割的SIFT图像匹配算法

提出了一种基于二维灰度直方图最大熵阈值分割的SIFT图像特征匹配算法。与传统SIFT算法相比,该算法首先综合利用图像像素的灰度信息和邻域空间信息,生成图像二维灰度直方图,并基于此直方图的最大熵对图像进行阈值分割,然后检测分割后图像的DoG尺度空间局部极值,并以此作为特征点进行图像匹配。实验结果表明,基于所提出的匹配算法,可以有效降低图像背景噪声和边缘像素点对目标匹配的干扰,进而提高图像目标的匹配性能。     

语义分割网络重建单视图遥感影像数字表面模型

该文提出了一种仅依靠激光探测与测量数据,实现单视图遥感影像数字表面模型(DSM)重建的新方法。该方法基于深度学习技术设计了一种编码-解码结构的语义分割网络,该网络采用多尺度残差融合的编码块与解码(MRFED)块从输入图像中提取语义信息,进而逐像素预测高度值;采用特征图跳跃级联的策略保留输入图像的细节特征和结构信息。该文采用了一个包含DSM数据的遥感影像公开数据集训练与测试模型,实验结果表明：DSM重建结果与真值的平均绝对误差(MAE)为2.1e-02,均方根误差(RMSE)为3.8e-02,结构相似性(SSIM)为92.89%,均优于经典的深度学习语义分割网络。实验证实该方法能够有效实现单视图遥感影像的DSM重建,具有较高的精度,以及较强的地物分布结构重建能力。     

语义分割网络重建单视图遥感影像数字表面模型

该文提出了一种仅依靠激光探测与测量数据,实现单视图遥感影像数字表面模型(DSM)重建的新方法。该方法基于深度学习技术设计了一种编码-解码结构的语义分割网络,该网络采用多尺度残差融合的编码块与解码(MRFED)块从输入图像中提取语义信息,进而逐像素预测高度值;采用特征图跳跃级联的策略保留输入图像的细节特征和结构信息。该文采用了一个包含DSM数据的遥感影像公开数据集训练与测试模型,实验结果表明:DSM重建结果与真值的平均绝对误差(MAE)为2.1e-02,均方根误差(RMSE)为3.8e-02,结构相似性(SSIM)为92.89%,均优于经典的深度学习语义分割网络。实验证实该方法能够有效实现单视图遥感影像的DSM重建,具有较高的精度,以及较强的地物分布结构重建能力。     

二层减法聚类图像颜色迁移算法

提出了一种图像自动颜色迁移方法,利用二层减法聚类将图像分成一定数量的子块,通过灰度差值直方图方法提取子块纹理特征,建立目标图像与源图像间子块的最佳对应关系,选取各子块数据点密度较大的像素组成子块的样本块,在对应源图像样本块中查找目标样本块的最佳匹配像素,完成样本块间颜色迁移,进而根据已上色的样本块完成目标图像的全局颜色迁移.该算法既适用于彩色图像间颜色迁移也适用于灰度图像上彩色.     

Automated 2-D cephalometric analysis on X-ray images by a model-based approach

Craniofacial landmark localization and anatomical structure tracing on cephalograms are two important ways to obtain the cephalometric analysis. In order to computerize them in parallel, a model-based approach is proposed to locate 262 craniofacial feature points, including 90 landmarks and 172 auxiliary points. In model training, 12 landmarks are selected as reference points and used to divide every training shape to 10 regions according to the anatomical knowledge; principle components analysis is employed to characterize the region shape variations and the statistical grey profile of every feature point. Locating feature points on an input image is a two-stage procedure. First, we identify the reference landmarks by image processing and pattern matching techniques, so that the shape partition is performed on the input image. Then, for each region, its feature points are located by a modified active shape model. All craniofacial anatomical structures can be traced out by connecting the located points with subdivision curves according to the prior knowledge. Users are permitted to modify the results interactively in many different ways. Experimental results show the advantage and reliability of the proposed method.     

Fast copy-move forgery detection algorithm based on group SIFT

Aiming at the high computational complexity of the existing copy-move image forgery detection algorithm,a copy-move forgery detection algorithm based on group scale-invariant feature transform (SIFT) was proposed.Firstly,the simple linear iterative clustering (SLIC) was utilized to divide the input image into non-overlapping and irregular blocks.Secondly,the structure tensor was introduced to classify each block as flat blocks,edge blocks and corner blocks,and then the SIFT feature points extracted from the block were taken as the block features.Finally,the forgery was located by the inter-class matching of the block features.By means of inter-class matching and feature point matching,the time complexity of the proposed copy-move forgery detection algorithm in feature matching and locating forgery region was effectively reduced while guaranteeing the detection effect.The experimental results show that the accuracy of the proposed algorithm is 97.79%,the recall rate is 90.34%,and the F score is 93.59%,the detecting time for the image with size of 1024×768 is 12.72 s,and the detecting time for the image with size of 3000×2000 was 639.93 s.Compared with the existing copy-move algorithm,the proposed algorithm can locate the forgery region quickly and accurately,and has high robustness.     

Locating the eye in human face images using fractal dimensions

Facial feature extraction is an important step in many applications such as human face recognition, video conferencing, surveillance systems, human computer interfacing etc. The eye is the most important facial feature. A reliable and fast method for locating the eye pairs in an image is vital to many practical applications. A new method for locating eye pairs based on valley field detection and measurement of fractal dimensions is proposed. Possible eye candidates in an image with a complex background are identified by valley field detection. The eye candidates are then grouped to form eye pairs if their local properties for eyes are satisfied. Two eyes are matched if they have similar roughness and orientation as represented by fractal dimensions. A modified approach to estimating fractal dimensions that is less sensitive to lighting conditions and provides information about the orientation of an image under consideration is proposed. Possible eye pairs are further verified by comparing the fractal dimensions of the eye-pair window and the corresponding face region with the respective means of the fractal dimensions of the eye-pair windows and the face regions. The means of the fractal dimensions are obtained based on a number of facial images in a database. Experiments have shown that this approach is fast and reliable     

基于支持向量回归的图像超分辨率重建算法

文章提出一种新的基于支持向量回归(SVR)和稀疏表示的图像超分辨重建算法。SVR对输入数据有良好预测输出类别能力。图像统计表明,图像块可以从过完备字典中通过稀疏线性组合很好的表示。对一幅低分辨率输入图像,可以将图像超分辨问题视为在高分辨图像中估计其像素位置。与传统的支持向量回归方法相比,本文采用的特征是不同类型的图像块的稀疏表示。研究表明,稀疏表示作为特征对噪声有一定的鲁棒性。实验结果表明,本文方法与传统支持向量回归方法相比在图像重建质量上有一定的优势。     

基于特征矢量匹配的SAR海洋图像舰船目标检测

根据SAR图像的基本特点 ,阐述了用DFBR场模型表达SAR图像的基本原理。在此基础上 ,通过提取SAR海洋图像中每个像素的分形值、分形模型拟合误差和方差统计量特征参数 ,结合图像像素的灰度值 ,形成一个对应于每个像素的特征矢量 ,并利用模糊数学的模糊子集概念 ,提出了一种基于特征矢量匹配的舰船目标检测方法。实际数据处理的结果表明 ,该方法具有较高的可靠性和准确性。     

基于局部二进制模式和图变换的快速匹配算法

针对图像匹配在图像拼接、目标识别等领域的应用中尺度不变特征变换（Scale Invariant Feature Transform,SIFT）算法计算复杂度高、实时性较差的问题,提出了一种基于局部二进制模式（Local Binary Patterns,LBP）和图变换（Graph Transformation Matching,GTM）的匹配算法.首先采用SIFT特征检测提取特征点并以特征点为中心取13×13的图像块作为特征区域;然后用本文提出的局部旋转不变二进制模式（Local Rotation Invariant Binary Patterns,LRIBP）描述子对特征区域进行描述产生29维的特征描述向量,降低了描述子的复杂度,并以欧氏距离为度量准则进行初始匹配;最后采用图变换匹配算法剔除误匹配点,从而提高算法的运算速率和匹配精度.仿真结果表明,本文所提算法不仅具有较高的精度和较强的鲁棒性,并且减少了算法的运算量,提高了算法的实时性.     

序列帧间双重匹配的红外点目标跟踪算法

针对海空复杂背景下红外点目标的检测与跟踪,提出了基于图像序列帧间双重匹配的边跟踪边检测算法,并建立了数学模型。它采用标记序列帧M以帧对帧的方式记录输入序列的帧间匹配结果,标记帧T以点对点的方式记录标记序列帧M的帧间匹配结果,统计帧S记录T中各像素的匹配成功次数,输入单帧图像同步输出矩阵T和S分别显示目标运动轨迹和迎头目标检测结果。算法匹配过程不随目标数目或运动状态而改变,且无需提前判断疑似目标位置,有效解决了目标在图像序列中突然丢失或出现被干扰情况下的跟踪,尤其可以对跟踪结果实时地进行目标分离,解决了迎头目标跟踪的难题。仿真和实际工程图像实验结果表明,算法具有较高的可靠性和实时性。     

一种混合神经网络在颗粒图像边缘检测中的应用

本文提出了一种应用混合神经网络进行颗粒图像检测的方法。混合神经网络由用于对边缘候选图像的二值输入模式进行聚类特征提取的自组织竞争子网络（ＡＳＣＳＮＮ）和用于获取颗粒图像边缘矢量信息的ＢＰ子网络（ＢＰＳＮＮ）组成,边缘候选图像是通过采用基于灰度极小值算法提取的边缘候选象素获得。神经网络以边缘候选图像中的边缘候选象素及其邻域象素的二值模式作为训练样本。对经过噪声污染的图像进行实验表明,该方法获得的边缘图像封闭性好、边缘描述真实,抗干扰能力较强,适用于颗粒图像的边缘检测。