提出了一种基于高斯金字塔分解的数字图像扩频水印技术。
In this paper, a spread spectrum digital watermark based on Gaussian pyramid decomposition was proposed.
该函数执行高斯金字塔结构下采样的步骤。首先,它与内核的源图像进行卷积。
The function performs the downsampling step of the Gaussian pyramid construction. First, it convolves the source image with the kernel.
通过高斯金字塔模拟目标的多级尺度模型,利用不同级别的模型建立目标的多级BP网络模型。
In this paper, we simulate multi-scale models of targets through Gaussian pyramid, and then establish multiple BP nets of targets.
我们修改基于特征的增量编码模型,根据稀疏编码原理,将其扩展成层次结构,并利用高斯金字塔解决尺度问题。
We expand it into two-layer structure based on sparse coding theory, and use Gaus-sian pyramid to solve scale problems.
重点分析了高斯金字塔、拉普拉斯金字塔、对比度金字塔和小波金字塔在图像分解与重构中的原理及其融合算法。
The principle of image decomposition and reconstruction based on Gauss-pyramid, Laplacian-pyramid, contrast-pyramid and wavelet-pyramid is emphatically analyzed, as well as the fusion algorithm.
通过迭代求解法和高斯金字塔模型,快速精确地估计得到配准参数,采用凸集投影(POCS)算法对图像序列进行了超分辨率重建。
Based on the set theoretic formulation, a projection onto convex sets (POCS) algorithm is applied to find the solution to face image reconstruction.
利用输入图像的近似高斯金字塔,将经典的基于显著性的视觉注意模型改造为时空开销更小的版本,从而使其更加适合在嵌入式实时系统中实现。
Classical saliency-based visual attention models are adapted for embedding real-time systems with less time and space costs based on approximate Gaussian pyramids of the input image.
利用输入图像的近似高斯金字塔,将经典的基于显著性的视觉注意模型改造为时空开销更小的版本,从而使其更加适合在嵌入式实时系统中实现。
Classical saliency-based visual attention models are adapted for embedding real-time systems with less time and space costs based on approximate Gaussian pyramids of the input image.
应用推荐