Keypoint Description Using Statistical Descriptor with Similarity-Invariant Regions

This article presents a method for the description of key points using simple statistics for regions controlled by neighboring key points to remedy the gap in existing descriptors.Usually,the existent descriptors such as speeded up robust features(SURF),Kaze,binary robust invariant scalable keypoints(BRISK),features from accelerated segment test(FAST),and oriented FAST and rotated BRIEF(ORB)can competently detect,describe,and match images in the presence of some artifacts such as blur,compression,and illumination.However,the performance and reliability of these descriptors decrease for some imaging variations such as point of view,zoom(scale),and rotation.The intro-duced description method improves image matching in the event of such distor-tions.It utilizes a contourlet-based detector to detect the strongest key points within a specified window size.The selected key points and their neighbors con-trol the size and orientation of the surrounding regions,which are mapped on rec-tangular shapes using polar transformation.The resulting rectangular matrices are subjected to two-directional statistical operations that involve calculating the mean and standard deviation.Consequently,the descriptor obtained is invariant(translation,rotation,and scale)because of the two methods;the extraction of the region and the polar transformation techniques used in this paper.The descrip-tion method introduced in this article is tested against well-established and well-known descriptors,such as SURF,Kaze,BRISK,FAST,and ORB,techniques using the standard OXFORD dataset.The presented methodology demonstrated its ability to improve the match between distorted images compared to other descriptors in the literature.

Target classification using SIFT sequence scale invariants

On the basis of scale invariant feature transform（SIFT） descriptors,a novel kind of local invariants based on SIFT sequence scale（SIFT-SS） is proposed and applied to target classification.First of all,the merits of using an SIFT algorithm for target classification are discussed.Secondly,the scales of SIFT descriptors are sorted by descending as SIFT-SS,which is sent to a support vector machine（SVM） with radial based function（RBF） kernel in order to train SVM classifier,which will be used for achieving target classification.Experimental results indicate that the SIFT-SS algorithm is efficient for target classification and can obtain a higher recognition rate than affine moment invariants（AMI） and multi-scale auto-convolution（MSA） in some complex situations,such as the situation with the existence of noises and occlusions.Moreover,the computational time of SIFT-SS is shorter than MSA and longer than AMI.

Active Shape Models Using Scale Invariant Feature Transform

A new active shape models (ASMs) was presented, which is driven by scale invariant feature transform (SIFT) local descriptor instead of normalizing first order derivative profiles in the original formulation, to segment lung fields from chest radiographs. The modified SIFT local descriptor, more distinctive than the general intensity and gradient features, is used to characterize the image features in the vicinity of each pixel at each resolution level during the segmentation optimization procedure. Experimental results show that the proposed method is more robust and accurate than the original ASMs in terms of an average overlap percentage and average contour distance in segmenting the lung fields from an available public database.

W-系统矩和Fourier变换下Volume Descriptors不变特征的三维模型检索

针对V-系统矩难以构造快速算法的不足,提出一种W-系统矩及其快速算法,并融合volume descriptors不变特征应用于三维模型检索.首先对模型体素化;其次计算体素模型的W-系统矩和物体运动不变量,得到特征向量;最后进行特征融合及匹配.实验结果表明,该算法的检索效率和性能均优于三维球面调和函数方法和三维Legendre矩方法.

Shape matching and retrieval based on multiple feature descriptors

A lot of 3D shape descriptors for 3D shape retrieval have been presented so far. This paper proposes a new mechanism, which employs several existing global and local 3D shape descriptors as input. With the sparse theory, some descriptors which play the most important role in measuring similarity between query model and the model in the dataset are selected automatically and an affinity matrix is constructed. Spectral clustering method can be implemented to this affinity matrix. Spectral embedding of this affinity matrix can be applied to retrieval, which integrating almost all the advantages of selected descriptors. In order to verify the performance of our approach, we perform experimental comparisons on Princeton Shape Benchmark database. Test results show that our method is a pose-oblivious, efficient and robustness method for either complete or incomplete models.

一种基于阶阵列的BRIEF特征描述子

局部特征匹配是机器视觉研究领域中的一个基础问题,也是该领域的研究热点之一,在目标识别、目标跟踪、场景区分等应用中具有重要的作用。而在局部特征匹配研究过程中,如何在满足多种图像变换的前提下,设计一种高效的图像特征描述子是需要解决的一个关键问题。现有的特征描述子,如SIFT和SURF,计算复杂性较高,难以胜任实时视频或移动计算环境;BRIEF特征描述子计算简单,匹配效率高,能满足实时视频或者移动计算环境的要求,但其仅考虑了单个像素,不具备方向,也就不具有旋转不变性。在BRIEF特征描述子的基础上,该文选择多个特征点,并引入阶排列方法,提出一种改进的特征描述子OPoBRIEF。相对于传统的特征描述子,OPoBRIEF能够包含更多的局部特征信息,并且计算复杂性较低。通过特征描述子稳定性实验,表明OPoBRIEF比BRRIEF具有更高的匹配正确率和更好的稳定性。而特征描述子旋转不变性的实验则表明,在旋转角度为10~12区间,OPoBRIEF与SIFT效果相当,但明显优于ORB算法。

多层次特征和粒子群优化的场景分类

针对遥感图像的场景分类精度问题,提出多层次特征和粒子群算法优化分类器的场景分类算法。利用聚集局部描述符编码算法对尺度不变特征变换算法提取的局部特征编码,获得中层特征,通过卷积神经网络提取高层特征,将提取的特征作为支持向量机的输入数据,引入粒子群算法优化该分类器的参数,进行场景分类。在RSC11和WHU-RS19两个公开的遥感图像数据集上进行实验,分类精度分别达到95.28和97.20。将WHU-RS19数据集的结果与其它方法比较,精度有明显提高。实验结果表明,在分类时对分类器参数进行优化,分类效果更佳。

基于RFNA和改进LBD的镜像线特征匹配方法

针对物体和镜像之间的匹配问题,引入RNFA(Relative Number of False Alarms)边缘链检测方法获取更丰富的线段。文中提出一种改进的LBD(Line Band Descriptor)算法用于构建局部不变特征描述符,通过比较局部不变特征描述符获得初始匹配对。采用全局投影角度的筛选方式,并通过拟合投影中线的方式剔除初始匹配对中误匹配项。在完成全局投影角度的选取和投影中线的拟合后,放宽对局部不变特征描述符阈值的筛选以获得更多的匹配对,提升召回率。图像集仿真实验结果表明,文中所提算法在纹理较弱区域能够更好地识别线段,且能够在保证原算法性能的基础上获得更多的匹配对,提高5%左右的正确匹配率,并达到90%以上的召回率。

PM-DFT:A New Local Invariant Descriptor Towards Image Copy Detection

Currently, global-features-based image copy detection is vulnerable to geometric transformations like cropping, shift, and rotations. To resolve this problem, some algorithms based on local descriptors have been proposed. However, the local descriptors, which were originally designed for object recognition, are not suitable for copy detection because they cause the problems of false positives and ambiguities. Instead of relying on the local gradient statistic as many existing descriptors do, we propose a new invariant local descriptor based on local polar-mapping and discrete Fourier transform. Then based on this descriptor, we propose a new framework of copy detection, in which virtual prior attacks and attack weight are employed for training and selecting only a few robust features. This consequently improves the storage and detection efficiency. In addition, it is worth noting that the feature matching takes the locations and orientations of interest points into consideration, which increases the number of matched regions and improves the recall. Experimental results show that the new descriptor is more robust and distinctive, and the proposed copy detection scheme using this descriptor can substantially enhance the accuracy and recall of copy detection and lower the false positives and ambiguities.

An invariant descriptor for conjugate forced convection-conduction cooling of 3D protruding heaters in channel flow

In this research, the temperatures of three- dimensional （3D） protruding heaters mounted on a conductive substrate in a horizontal rectangular channel with laminar airflow are related to the independent power dissipation in each heater by using a matrix G＋ with invariant coefficients, which are dimensionless. These coefficients are defined in this study as the conjugate influence coefficients （g＋） caused by the forced convec- tion-conduction nature of the heaters＇ cooling process. The temperature increase of each heater in the channel is quantified to clearly identify the contributions attributed to the self-heating and power dissipation in the other heaters （both upstream and downstream）. The conjugate coefficients are invariant with the heat generation rate in the array of heaters when assuming a defined geometry, invariable fluid and flow rate, and constant substrate and heater conductivities. The results are numerically obtained by considering three 3D protruding heaters on a twodimensional （2D） array by ANSYS/FluentTM 15.0 software. The conservation equations are solved by a coupled procedure within a single calculation domain comprising of solid and fluid regions and by considering a steady state laminar airflow with constant properties. Some examples are shown, indicating the effects of substrate thermal conductivity and Reynolds number on conjugate influence coefficients.

Applying rotation-invariant star descriptor to deep-sky image registration

Image registration is a critical process of many deep-sky image processing applications. Image registration methods include image stacking to reduce noise or achieve long exposure effects within a short exposure time, image stitching to extend the field of view, and atmospheric turbu- lence removal. The most widely used method for deep-sky image registration is the triangle- or polygon-based method, which is both memory and computation intensive. Deepsky image registration mainly focuses on translation and rotation caused by the vibration of imaging devices and the Earth＇s rotation, where rotation is the more difficult problem. For this problem, the best method is to find corresponding rotation-invariant features between different images. In this paper, we analyze the defects introduced by applying rotation-invariant feature descriptors to deep-sky image reg- istration and propose a novel descriptor. First, a dominant orientation is estimated from the geometrical relationships between a described star and two neighboring stable stars. An adaptive speeded-up robust features （SURF） descriptor is then constructed. During the construction of SURF, the local patch size adaptively changes based on the described star size. Finally, the proposed descriptor is formed by fusing star properties, geometrical relationships, and the adaptive SURF. Extensive experiments demonstrate that the proposed descriptor successfully addresses the gap resulting from applying the traditional feature-based method to deep-sky image registration and performs well compared to state-of-the-art descriptors.

一种新的几何特征形状描述子

通过对平移旋转和伸缩变换下的不变量进行研究,证明了形状的长轴端点和重心是该变换下的不变量,提出了长轴两端点与重心所成的夹角这一几何特征的形状描述子,该形状描述子具有平移旋转和伸缩变换不变性,理论分析和实验结果表明该描述子简单高效,具有较好的形状匹配结果。

结合SURF特征点与DAISY描述符的图像匹配算法

图像匹配技术是许多计算视觉问题研究的基础,基于图像局部特征的方法是本领域研究的热点。为了解决经典的SURF算法在旋转不变性上表现欠佳的问题,提出了一种结合SURF特征点与DAISY描述符的图像匹配算法。在SURF算法特征点检测的基础上,提出一种适合DAISY描述符的主方向分配方法,并按照该主方向旋转获得新的DAISY描述符。本算法在略微增加运算成本的基础上,增强了经典SURF算法在图像旋转上的匹配能力。实验结果表明,在图像模糊、光照变化、JPEG压缩比变化、视场变化等多种复杂情况下,本算法具有更强的鲁棒性。

基于Harris角点和SURF特征的遥感图像匹配算法

Harris是一种高效的角点检测算法,但不具备尺度不变性。SURF(speeded-up robust features)算法虽然能很好地解决图像尺度变化问题,但是在特征点提取方面没有Harris稳定。针对Harris和SURF两种算法的特点,提出一种新的Harris-SURF特征点提取算法。首先用Harris算法检测图像角点,再用SURF算法提取图像特征点;然后合并角点和特征点,并剔除重复点获得新的特征点集,确定新特征点的主方向并生成特征描述符,再对图像使用比值法进行初匹配;最后利用RANSAC剔除错误匹配点实现精确匹配。实验结果表明,该算法对图像存在旋转、缩放、光照及噪声变化有较强的鲁棒性,同时提高了运行效率。

基于Bag-of-phrases的图像表示方法

在过去的几年,将图像内容表示为特定"视觉词"出现次数直方图的Bag-of-words模型,展示了其在图像内容分类方面的强大优势.然而,在这种统计特定"视觉词"出现次数直方图的模型中,"视觉词"之间的相互位置关系几乎被完全丢弃了.本文从分析Bag-of-words模型在文本分类和图像内容分类领域的对应关系的角度出发,提出一种加入"视觉词"之间的相互位置关系的图像表示方法—Bag-of-phrases模型.在标准数据集上验证了该图像表示方法对图像内容分类性能的影响.实验结果显示,本文提出的方法相对于传统的Bag-of-words模型可以达到更好的分类性能.

一种仿射不变的直线描述子与直线匹配

从图像中提取的直线常出现不完整、端点位置不准确等问题,针对这些问题造成的直线匹配难点,本文提出了一种仿射不变的直线描述子.首先将待匹配直线离散为对应点的集合,将直线描述转化为点的描述,避免了直线不完整造成的支撑区域大小不一致的问题;然后结合直线的方向和长度,定义点描述子的主方向和尺度,通过统计离散点集的局部邻域的梯度信息使描述子具有仿射不变性.为了提高直线匹配速度,在进行直线描述之前,本文采用了极线约束精简了待匹配直线集合,再利用最近邻距离比准则对直线精确匹配.实验结果表明本文提出的直线描述子在仿射、亮度、视点、遮挡等变化条件下具有精确的匹配性能.

一种新的局部不变特征检测和描述算法

局部不变特征已经被成功地用来解决计算机视觉领域诸多实际问题.文中提出一种新的局部不变特征检测和描述算法,提取出的特征能够对旋转、尺度缩放、光照等变化,甚至弱仿射变换保持不变.一般说来,局部特征的提取分为特征检测和描述两个关键步骤.在特征检测阶段,首先在每一层尺度图像上提取Harris角点,然后在以Harris角点为中心的固定大小的搜索窗内搜索三维尺度空间的极值点作为局部特征点的位置和特征尺度,最后为每个特征点计算主方向.文中的特征检测算法具有良好的可重复率性能.在特征描述阶段,建立了梯度的距离和方向直方图来描述局部特征,文中的特征描述子不但具有良好的匹配性能,而且维数更低,十分有利于提高图像特征的匹配速度.大量的图像匹配与图像检索实验结果验证了文中算法的有效性.

基于不变特征描述符实现星点匹配

为了能够在星图存在旋转角度情况下,自动快速地完成星图匹配,提出了一种基于不变特征描述符的旋转不变匹配方法,将加速鲁棒特征(SURF)描述符应用于星点特征的描述和匹配。首先,对星图进行图像分割,抑制非极大值,并检测星点;然后,为计算星点分布尺度因子s,在半径为6s的圆形邻域内为每个星点计算主方向,之后将20s×20s的邻域与主方向对准,并在该邻域内为每个星点计算SURF描述符。最后,基于透视投影模型的匹配策略,提纯星点,计算匹配星图之间的变换矩阵。实验结果显示,该方法能够鲁棒地提取星点,并在图像存在旋转、平移及部分视角变化的情况下完成星图匹配,仿真实验的匹配星点的误差均在1pixel以下,实拍星图实验的匹配星点的误差均在1.5pixel以下,表明为每个星点建立描述符,进行匹配识别的思路是可行的。

基于旋转不变特征的SIFT描述子在图像配准中的应用

针对尺度不变特征变换(SIFT)算法中描述子维度高造成配准过程中计算量过大的问题,提出了一种改进的SIFT算法。该算法利用圆形的旋转不变性,以特征点为中心,在近似大小的圆形特征点邻域内构造特征描述子,以每个圆环作为一个子环,每个子环内只有像素位置发生了改变,像素之间其他相对信息是保持不变的。当图像发生旋转时,统计每个圆环内元素的梯度累加值进行排序,生成特征向量描述子,降低了算法的维度及复杂度,把特征描述子的维数从128维降低到48维。实验结果表明,改进算法旋转配准重复率在85%以上;在图像旋转、缩放和光照变化情况下,与SIFT算法相比,平均配准准确率提高5%,平均配准耗时降低30%左右,有效实现了对SIFT的改进。

一种基于SIFT算子的人脸识别方法

高独特性特征的选择以及合适匹配策略的选用是人脸识别技术的关键。讨论了基于仿射不变的几何特征SIFT算子进行人脸识别的方法。SIFT算子的计算复杂度较高,并且不同的人脸表情和图像模糊会加大特征匹配的难度。为克服上述缺点,提出了一种新的算法,将选择6个人脸上感兴趣子区域进行描述,并根据各自的独特性赋予不同的权值,最后在匹配过程中使用相似度的平方来减小偏差数据造成的影响。实验结果表明,该方法能有效减轻表情变化对于身份识别率急剧下降的影响,并可显著减少计算复杂度和特征匹配时间。