搜索资源列表
estimgaus
- matlab function for estimation gaussian and motion blur parapeters
Image-Restoration-with-BPNN
- 基于BP神经网络的高斯模糊图像复原的方法实现,结合了BP神经网络良好的非线性逼近功能,效果较传统的算法更好。-BP neural network based image restoration method of Gaussian blur implementation of BP neural network combines good nonlinear approximation function, the effect is better than traditional algorit
blur
- 将图形加以高斯噪声或者椒盐噪声。为图像处理的一种可靠的加噪方法。BLUR Test problem: digital image deblurring-Gaussian noise or the graphics to be salt and pepper noise. As a reliable image processing method with noise. BLUR Test problem: digital image deblurring
gaussian
- The Gaussian blur is a type of image-blurring filter that uses a Gaussian function (which also expresses the normal distribution in statistics) for calculating the transformation to apply to each pixel in the image
Copy-Detection
- 使用下采样帧构成的列向量的PCA系数作为每帧特征(原则上,也可以使用其他类型的关键帧特征),多帧特征构成特征矢量,以高斯概率模型的后验概率衡量相似性、并建立k维树结构的索引进行搜索,文中对噪声、模糊、再压缩、加Logo,及其这些变换的两两组合进行了实验(丢帧很少时也可以),速度很快,适合于大规模因特网视频的搜索。-Use sampling frame column vector of the PCA coefficients as each frame features (in principl
GaussKernel
- 计算高斯函数的模板,输入方差和维数即可获得模板参数,可用于图像的高斯模糊-Calculate the Gaussian function template, enter the variance and dimension can be obtained template parameter can be used to image the Gaussian blur
Image-restoration
- 图像复原,用PSF产生退化图像,生成运动模糊+高斯噪声图像MFN,计算噪信比,逆滤波复原-Image restoration, image degradation produced by PSF, Gaussian noise generated image motion blur+ MFN, calculate the noise signal ratio, inverse filtering restoration
Laplace-pyramid
- 拉普拉斯金字塔在图像融合中有所应用,方法是首先对两个待融合图像求拉普拉斯残差金字塔,然后用模板对每一级残差图像进行融合得到融合后图像的残差金字塔,然后对这个金字塔进行重构就能得到最终的融合图像,图像各尺度细节得到保留。(注:融合时模板一般会先用高斯函数模糊一下) 不过这里不实现融合,只实现拉普拉斯金字塔的建立。 -Laplace pyramid has applications in image fusion method is to first find two images to b
bwtext
- Finding Edges Gaussian Blur Rotation Skew Averaging filter
Projects_DIP3E
- 主要包括DIP 3/e—Student Projects的说明文档以及实验05-04的详细代码,实验的要求为: Instruction manual: (a) Implement a blurring filter as in Eq. (5.6-11). (b) Blur image 5.26(a) in the +45o direction using T = 1, as in Fig. 5.26(b). (c) Add Gaussian noise of 0 mean and
HDR_Imaging
- 采用基于梯度的算法,通过matlab实现高动态范围成像。高动态范围图像,相比普通的图像,可以提供更多的动态范围和图像细节,根据不同的曝光时间的低动态范围图像,利用每个曝光时间相对应最佳细节的低动态范围图像来合成最终高动态范围图像,能够更好的反映人真实环境中的视觉效果。这里采用的高斯模糊展示了高动态范围图像中超出取值范围的数值也是有用的,即使它们在转换成低动态范围图像的时候通常都要被裁掉。在原始的高动态范围图像中,这些像素都有非常大的亮度值。当图像模糊的时候,周围的像素亮度被“拉高”并且在色度映射