Image analysis by Tchebichef moments

This paper introduces a new set of orthogonal moment functions based on the discrete Tchebichef polynomials. The Tchebichef moments can be effectively used as pattern features in the analysis of two-dimensional images. The implementation of the moments proposed in this paper does not involve any numerical approximation, since the basis set is orthogonal in the discrete domain of the image coordinate space. This property makes Tchebichef moments superior to the conventional orthogonal moments such as Legendre moments and Zernike moments, in terms of preserving the analytical properties needed to ensure information redundancy in a moment set. The paper also details the various computational aspects of Tchebichef moments and demonstrates their feature representation capability using the method of image reconstruction.     

采用径向Tchebichef矩不变量的飞机型号识别

针对几何矩非正交性对目标描述的不足以及连续正交矩在处理数字图像方面存在离散化误差的缺陷,为了提高识别精度,提出了一种利用离散正交的Tchebichef矩结合全局特征和局部特征的飞机型号识别方法。首先,根据几何矩和Tchebichef矩之间的关系,利用归一化几何中心矩、圆谐函数得到径向Tchebichef矩的旋转、尺度和平移(RST)不变量;然后,利用径向Tchebichef矩提取飞机目标的局部和全局特征构成特征向量;最后,利用Matlab构造了四类飞机的样本集,采用支持向量机(SVM)作为分类器识别测试样本飞机型号,分析了几何矩、Zernike矩和本文方法在识别精度上的差异以及训练样本集大小对识别精度的影响。实验结果表明,本文提出的算法提高了识别精度,并且在训练样本集较小时仍能获得90%以上的识别精度。     

Image fusion based on discrete Chebyshev moments

Though deep learning-based methods have demonstrated strong capabilities on image fusion, they usually improve the fusion performance by increasing the width and depth of the network, increasing the computational effort and being unsuitable for industrial applications. In this paper, an end-to-end network based on fixed convolution module of discrete Chebyshev moments is proposed, which does not need any pre- or post-processing. The proposed network is roughly composed of three parts: feature extraction module, fusion module and feature reconstruction module. In the feature extraction module, a novel fixed convolution module based on discrete Chebyshev moments is proposed to obtain different frequency components in a short time. To improve the image sharpness and fuse more details, a spatial attention mechanism based on average gradient is proposed in fusion module. Extensive results demonstrate that the proposed network can achieve remarkable fusion performance, high time efficiency and strong generalization ability.     

Image analysis by Krawtchouk moments

A new set of orthogonal moments based on the discrete classical Krawtchouk polynomials is introduced. The Krawtchouk polynomials are scaled to ensure numerical stability, thus creating a set of weighted Krawtchouk polynomials. The set of proposed Krawtchouk moments is then derived from the weighted Krawtchouk polynomials. The orthogonality of the proposed moments ensures minimal information redundancy. No numerical approximation is involved in deriving the moments, since the weighted Krawtchouk polynomials are discrete. These properties make the Krawtchouk moments well suited as pattern features in the analysis of two-dimensional images. It is shown that the Krawtchouk moments can be employed to extract local features of an image, unlike other orthogonal moments, which generally capture the global features. The computational aspects of the moments using the recursive and symmetry properties are discussed. The theoretical framework is validated by an experiment on image reconstruction using Krawtchouk moments and the results are compared to that of Zernike, pseudo-Zernike, Legendre, and Tchebyscheff moments. Krawtchouk moment invariants are constructed using a linear combination of geometric moment invariants; an object recognition experiment shows Krawtchouk moment invariants perform significantly better than Hu's moment invariants in both noise-free and noisy conditions.     

Verification system robust to occlusion using low-order Zernike moments of palmprint sub-images

This paper proposes a palmprint based verification system which uses low-order Zernike moments of palmprint sub-images. Euclidean distance is used to match the Zernike moments of corresponding sub-images of query and enrolled palmprints. These matching scores of sub-images are fused using a weighted fusion strategy. The proposed system can also classify the sub-image of palmprint into non-occluded or occluded region and verify user with the help of non-occluded regions. So it is robust to occlusion. The palmprint is extracted from the acquired hand image using a low cost flat bed scanner. A palmprint extraction procedure which is robust to hand translation and rotation on the scanner has been proposed. The system is tested on IITK, PolyU and CASIA databases of size 549, 5239 and 7752 hand images respectively. It performs with accuracy of more than 98%, and FAR, FRR less than 2% for all the databases.     

基于视觉注意力机制的多源遥感图像语义分割

近年来,随着空间感知技术的不断发展,对多源遥感图像的融合处理需求也逐渐增多,如何有效地提取多源图像中的互补信息以完成特定任务成为当前的研究热点。针对多源遥感图像融合语义分割任务中,多源图像的信息冗余和全局特征提取难题,本文提出一种将多光谱图像（Multispectral image, MS）、全色图像（Panchromatic image, PAN）和合成孔径雷达 （Synthetic Aperture Radar, SAR）图像融合的基于Transformer的多源遥感图像语义分割模型Transformer U-Net （TU-Net）。该模型使用通道交换网络（Channel-Exchanging-Network, CEN）对融合支路中的多源遥感特征图进行通道交换,以获得更好的信息互补性,减少数据冗余。同时在特征图拼接后通过带注意力机制的Transformer模块对融合特征图进行全局上下文建模,提取多源遥感图像的全局特征,并以端到端的方式分割多源图像。在MSAW数据集上的训练和验证结果表明,相比目前的多源融合语义分割算法,在F₁值和Dice系数上分别提高了3.31%~11.47%和4.87%~8.55%,对建筑物的分割效果提升明显。      

基于局部特征差异的异源图像融合算法

针对现有异源图像融合多以光学 图像为主、合成孔径雷达 (SAR)图 为辅和 光学图像 极易受 传播媒介 干扰 且 不 能同时保留纹理细节与颜色信息 等 问题, 提出一种新的基于局部特征差异的异源图像融合算法。 首先通 过 自适应分割 将 SAR 图像划分为规则特征区和不规则特征区两个区域;然后 进行 平移不变 离散 小波变换(SIDWT), 再根据 局部特征差异 性 设计 融合规 则,将 SAR 图像与全色遥感(PAN)图像的 小波系数 进行融合 , 以期保留图像的特征 信息与色彩信息 ;最后 通过 信息量 、 清晰度等 客观 评价指标 对 融合结果进行评价与分析 。 仿真实验 证明 了算法的有效性。     

基于Blob-Harris特征区域和NSCT-Zernike的鲁棒水印算法

为了有效抵抗水印图像的几何攻击,该文提出了一种基于Blob-Harris特征区域和非下采样轮廓波变换(NSCT)和伪Zernike矩的鲁棒水印算法。首先原始图像进行两层非下采样Contourlet变换后提取其低频图像,然后利用Blob-Harris检测算子对低频图像进行特征点提取,根据各个特征点的特征尺度确定其特征区域,优化筛选出稳定且互不重叠的特征区域并将其四周补零,得到稳定的互不重叠的方形特征区域作为水印嵌入区域,最后计算每一个方形特征区域的Zernike矩,将水印信息嵌入在量化调制正则化Zernike矩的幅值当中。实验结果表明,Lena图峰值信噪比达到40 dB以上时,本文算法对常规图像处理以及缩放、旋转、剪切等几何攻击和组合攻击都有相对较强的鲁棒性。     

基于非负矩阵分解和红外特征的图像融合方法

针对传统图像融合方法鲁棒性较差的缺点,提出了一种基于非负矩阵分解和红外特征的图像融合方法,实现源图像的目标区域和背景区域分别融合.首先将源图像作为原始数据进行非负矩阵分解得到特征基图像,特征基图像包含了源图像的整体特征;利用红外图像目标与背景灰度显著差异,通过区域生长方法从红外图像提取目标区域,将红外目标区域与特征基图像背景区域相融合得到融合图像.实验结果表明,该方法不仅简单易行,而且在保留了可见光的高空间分辨率和纹理细节信息同时,突出了红外图像对热目标敏感特点,提高了图像的可判读性.     

基于Zernike矩与SIFT特征的商标检索算法

为降低商标检索算法的误检率,提出一种结合Zernike矩(ZM)和尺度不变特征变换(SIFT)的商标检索算法,该算法由离线数据库构建和在线检索组成。分别从查询图像中提取ZM和SIFT特征;根据查询图像的特征集与数据库中存储的图像的特征集之间的ZM特征进行相似度度量,形成候选商标集;最后,利用SIFT特征对查询图像与候选图像精准检测,对相似距离进行排序,将结果返回给用户。实验结果表明：与当前流行的商标检索算法相比,该算法具备更好的检索性能,在缩放、平移、模糊、透视、斜切、扭曲等变换干扰下,仍呈现出更理想的Precision- Recall曲线以及F值。     

Some computational aspects of discrete orthonormal moments

Discrete orthogonal moments have several computational advantages over continuous moments. However, when the moment order becomes large, discrete orthogonal moments (such as the Tchebichef moments) tend to exhibit numerical instabilities. This paper introduces the orthonormal version of Tchebichef moments, and analyzes some of their computational aspects. The recursive procedure used for polynomial evaluation can be suitably modified to reduce the accumulation of numerical errors. The proposed set of moments can be used for representing image shape features and for reconstructing an image from its moments with a high degree of accuracy.     

Adaptive river segmentation in SAR images

There is difficulty for distinguishing of river and shadow in Synthetic Aperture Radar (SAR) images. A method of river segmentation in SAR images based on wavelet energy and gradient is proposed in this paper. It mainly includes two algorithms: coarse segmentation and refined segmentation. Firstly, The river regions are coarsely segmented by the wavelet energy feature,and then refined segmented accurately by the gradient threshold which is got adaptively. The experimental results show the validity of the method, which provides a good foundation for targets detection above the river.     

基于NSUDCT的红外与可见光图像融合

针对同一场景的红外与可见光图像,提出了基于非下采样均匀离散Curvelet 变换（NSUDCT）的图像融合方法。首先使用标记控制的分水岭分割（MCWS）算法对源图像进行区域分割,对各分割结果进行叠加得到联合区域图。然后对源图像进行非下采样均匀离散Curvelet 分解,分解后的低频系数采用区域对比度和区域标准差作为量测指标进行融合,高频方向系数使用基于局部能量的融合规则进行融合,并对融合系数做一致性检测。最后通过各频带融合系数重建得到融合图像。实验结果表明文中方法取得了比较好的视觉效果和量化数据,相比基于NSUDCT 的像素融合方法,此文方法的熵值提高了9.87%,交叉熵减少了68.04%,互信息提高了80%。     

水下气泡光学图像识别方法

针对水中气泡与固体悬浮微粒不易区分的问题,提出了一种基于Zernike矩与灰度计算的水下光学气泡图像识别方法。该方法主要分为图像划分、图像预处理和特征提取三个步骤。首先,获取水下悬浮微粒的图像,从中划分出单个气泡并选取部分样本;为了更好地提取与表示气泡轮廓与灰度特征,然后采用图像预处理方法增强气泡边缘特征,选择并构建气泡特征库;最后,采用Zernike矩计算悬浮微粒特征的相似度,区分圆形微粒与非圆形微粒,之后计算微粒中心与灰度变化趋势,辨别气泡与固体悬浮微粒。实验结果表明,在测试数据集上的气泡识别准确率达到94%。该方法不仅能够辨别圆形与非圆形微粒,而且能够融合灰度梯度计算方法以获取更好的结果。该方法从形状与灰度两个方面提取与辨别目标的特征信息,提高了气泡识别精度,具有较高的精确性与适用性。     

考虑圆形特征边缘模糊和偏心误差修正的高精度相机标定方法

针对立体视觉系统采用圆形特征点标定时存在的空间圆形投影边缘模糊和偏心现象问题,利用改进Zernike矩和偏心误差修正进行圆心的高精度定位,以此提高相机参数的标定精度。首先考虑了由于立体视觉成像系统的标定场景光照强度不均匀引起的圆形特征投影图像边缘模糊的问题,引入高斯误差函数对边缘过渡段的灰度分布进行描述,建立了高斯边缘模型,并基于该模型计算投影图像的Zernike矩,然后利用改进Zernike矩实现高精度的圆形特征投影边缘像素坐标定位。此外,分析了影响圆形特征中心投影点和拟合圆心间偏差大小的因素,基于该分析对迭代拟合圆心进行偏差补偿使之逼近真实的圆心投影,最后通过所提算法对99圆形标志点进行圆心坐标提取并用于相机参数的标定。仿真实验表明,文中算法对投影图像边缘定位的精度以及圆心拟合的精度均高于传统的算法;实测实验中,基于圆心高精度坐标得到的相机标定参数对标准杆进行三维重建,长度测量精度比传统算法提高了30%。     

基于空间与光谱注意力的光学图像和SAR图像特征融合分类方法

针对多源遥感图像的差异性和互补性问题,该文提出一种基于空间与光谱注意力的光学图像和SAR图像特征融合分类方法。首先利用卷积神经网络分别进行光学图像和SAR图像的特征提取,设计空间注意力和光谱注意力组成的注意力模块分析特征重要程度,生成不同特征的权重进行特征融合增强,同时减弱对无效信息的关注,从而提高光学和SAR图像融合分类精度。通过在两组光学和SAR图像数据集上进行对比实验,结果表明所提方法取得更高的融合分类精度。     

多尺度特征融合与特征通道关系校准的SAR图像船舶检测

目前深度学习技术在SAR图像的船舶检测中已取得显著的成果,但针对SAR船舶图像中复杂多变的背景环境,如何准确高效地提取目标特征,提升检测精度与检测速度仍存在着巨大的挑战.针对上述问题,该文提出了一种多尺度特征融合与特征通道关系校准的SAR图像船舶检测算法.在Faster R-CNN的基础上,首先通过引入通道注意力机制对...     

Performance of Object Classification Using Zernike Moment

Moments have been used in all sorts of object classification systems based on image. There are lots of moments studied by many researchers in the area of object classification and one of the most preference moments is the Zernike moment. In this paper, the performance of object classification using the Zernike moment has been explored. The classifier based on neural networks has been used in this study. The results indicate the best performance in identifying the aggregate is at 91.4% with a ten orders of the Zernike moment. This encouraging result has shown that the Zernike moment is a suitable moment to be used as a feature of object classification systems.