共查询到20条相似文献,搜索用时 93 毫秒
1.
车牌字符识别是车牌识别系统中的关键环节。采用图像处理和神经网络相结合的方法设计新的车牌字符识别算法,先对分割出的车牌字符进行归一化处理,然后进行SOBEI.边缘检测和角点特征提取,最后输入BP神经网络进行训练、识别,其中BP神经网络模型属于改进型神经网络。通过一系列神经网络训练和仿真实验,车牌识别速度和正确率得到了明显的提高。 相似文献
2.
3.
针对工业生产中测试仪表显示数据的自动识别问题,提出一种基于机器视觉的数字仪表数据识别方法;文章方法利用图像获取、图像去噪、阈值分割、光学字符识别等技术有效远程识别LCD/LED显示的数字信息。通过实验验证,该系统能远程实时识别具有LCD/LED显示的数字化仪表的显示数据,识别率能达到99%以上,并且能够实现超限报警及数据保存功能。 相似文献
4.
5.
6.
7.
8.
9.
提出一种可用于半脆弱认证的鲁棒可逆水印算法。该算法利用了鲁棒的统计量-图像均值,通过计算相邻两个图像子块均值的差分,根据差分的范围,将差分进行不同程度地平移来嵌入水印;再根据差分的平移量分别调整两个子块的各个像素,以保证算法的可逆性。同时该算法利用分块直方图调整来避免像素的溢出。对常见图像和三类医学图像(CT、超声波、X光图像)进行仿真实验,发现该可逆水印算法对JPEG压缩具有良好的鲁棒性。与Ni的算法相比,该算法具有更好的图像质量。 相似文献
10.
提出了一种针对一类图像进行稀疏表示的字典训练方法,并证明了该算法的收敛性.该算法的几何解释是,以最少的超平面来逼近样本所在的一小块球冠.算法流程为聚类每一步迭代所产生的余项,将聚类中心作为新的字典原子,令字典能够更适应于样本的稀疏表示.该算法与传统的字典训练方法相比具有适应性强,对训练样本规模和字典规模要求低,收敛速度快,算法复杂度低等特点.利用该算法训练得到的字典用于压缩感知、图像去噪等实验表明,该字典具有很好的效果. 相似文献
11.
According to non-rigid medical image registration, new method of classification registration is proposed. First, Feature points are extracted based on SIFT (Scale Invariant Feature Transform) from reference images and floating images to match feature points. And the coarse registration is performed using the least square method. Then the precise registration is achieved using the optical flow model algorithm. SIFT algorithm is based on local image features that are with good scale, rotation and illumination invariance. Optical flow algorithm does not extract features and use the image gray information directly, and its registration speed is faster. The both algorithms are complementary. SIFT algorithm is used for improving the convergence speed of optical flow algorithm, and optical flow algorithm makes the registration result more accurate. The experimental results prove that the algorithm can improve the accuracy of the non-rigid medical image registration and enhance the convergence speed. Therefore, the algorithm has some advantages in the image registration. 相似文献
12.
基于几何代数的彩色光流场计算 总被引:4,自引:0,他引:4
提出了一种新的基于几何代数的彩色光流场计算方法.从新的角度出发讨论了运用几何代数的概念来解决彩色图像序列的可行性和简便性.在几何代数域内对彩色图像序列用多重矢量表示,证明了彩色光流场分析时进行约束条件时的测量问题,通过多重矢量而非多通道的图像处理方法来表示图像连续特性,从而扩大了测量范围;然后依据物体色彩在运动过程中保持不变的原理,在几何代数域内推导了彩色图像序列的光流约束方程及其解法.结果表明,该算法能够显著提高各种情况下的彩色光流场计算能力. 相似文献
13.
Discrete symmetrical perturbation and variational algorithm of disturbed Lagrangian systems 下载免费PDF全文
《中国物理 B》2019,(3)
We investigate the perturbation to discrete conformal invariance and the adiabatic invariants of Lagrangian systems. A variational algorithm is proposed for a system subjected to the perturbation quantities. The discrete determining equations of the perturbations to conformal invariance are established. For perturbed Lagrangian systems, the condition of the existence of adiabatic invariant is derived from the discrete perturbation to conformal invariance. The numerical simulations demonstrate that the variational algorithm has the higher precision and the longer time stability than the standard numerical method. 相似文献
14.
为了提高单基地多输入多输出(Multiple-Input Multiple-Output, MIMO)声呐阵列的波达方向(Direction of arrival, DOA)估计性能,提出了双尺度旋转不变子空间(Dual-Resolution Estimation of Signal Parameters via Rotational Invariance Techniques, DR-ESPRIT)算法。结合MIMO阵列虚拟阵列的结构特征,首先利用ESPRIT算法通过各条虚拟线阵内、基线间距不大于半波长的子阵间的旋转不变关系得到无模糊的粗估计结果,之后利用虚拟线阵间、基线较长的子阵间的旋转不变关系得到一组有模糊的精估计结果。参考粗估计结果对精估计结果进行解模糊,最终得到高精度无模糊的角度估计结果。为了降低运算复杂度,利用该思路对降维ESPRIT算法也进行改进,提出了双尺度降维ESPRIT算法。仿真试验首先验证了与传统算法相比,双尺度类DOA估计算法能够有效提高角度估计精度。此外,还分析了MIMO声呐阵列的发射、接收阵元的幅相扰动误差对算法角度估计性能的影响。 相似文献
15.
This paper indroduces the precision test of Lorentz invariance using ultra-stable and low-loss optical cavities. The effective-field
theory widely adopted in the analysis of experimental data has been reviewed. The sensitivity of the cavity resonant frequency
to the Lorentz-violating tensor field is discussed in detail. In addition, the polarization of the optical field has been
added to the model, and our analysis shows that the frequency shift due to Lorentz violation is not sensitive to the polarization
of the optical field.
相似文献
16.
针对包装质量检测精度易受外界光照影响的问题,在已有基于梯度幅值相似性的缺陷检测算法基础上,将局部二值模式算子引入到该算法中,提出了一种基于改进梯度幅值相似性的缺陷检测算法。该算法利用局部二值模式算子的旋转不变性和灰度不变性的特点,并将其与图像的梯度幅值特征进行融合后用于包装的缺陷检测中,提升了缺陷检测算法对光照的鲁棒性。实验结果表明,相比传统梯度幅值缺陷检测算法,该算法具有更好的抗光照影响能力,并且对于不同光照情况下的包装缺陷,该算法的检测准确率可达96.57%。因而,该算法能够被广泛地用于包装缺陷检测中,提高缺陷检测的精度。 相似文献
17.
The interplay of electron-electron interactions and spin-orbit coupling leads to a new contribution to the homogeneous optical conductivity of the electron liquid. The latter is known to be insensitive to many-body effects for a conventional electron system with parabolic dispersion. The parabolic spectrum has its origin in the Galilean invariance which is broken by spin-orbit coupling. This opens up a possibility for the optical conductivity to probe electron-electron interactions. We analyze the interplay of interactions and spin-orbit coupling and obtain optical conductivity beyond RPA. 相似文献
18.
基于直线的射影不变性和极线约束标定摄像机参数 总被引:1,自引:1,他引:0
提出一种用图像对标定摄像机参数的新方法。传统自标定方法需要先由图像特征计算基础矩阵,该方法则是从图像中提取一组未知长度和长度比的平行直线,以图像中心坐标为主点初值,利用直线的射影不变性先求得摄像机焦距、旋转矩阵和平移向量的初值;再由图像对固有的极线约束来优化摄像机的参数,从而得到高精度的主点、焦距、旋转矩阵和平移向量。使用该方法对图像目标进行三维重建,仿真实验表明:该方法对场景要求较少,原理简单,方法易行,标定摄像机参数精度较高。 相似文献
19.
In this work we introduce a new approach for corner extraction with rotation invariance. The method is based on an optical processor where the filter in the frequency plane is composed by a spiral phase function and a binary amplitude. The output image of the optical setup presents intensity peaks in each square corner location. The performance of the proposed method was tested on synthetic scenes by numerical simulations and by optical measurements. The presented results show that the method allows the corner extraction, even with rotated scenes. 相似文献