-
Nonsubsampled-Contourlet-Transform
非下采样contourlet相关去噪，论文程序，包括非下采样contourlet变换工具箱，已通过仿真(Related denoising nonsubsampled contourlet paper program, including non-sampling contourlet transform toolbox has been through the simulation)
- 2012-08-10 21:30:38下载
- 积分：1
-
Gaussian
打开24位彩色bmp文件, 显示该图像
将图像内容顺时针旋转90度后显示出来
将图像分成等大小的4块，将第1和第3块像素互换后保存
将旋转后的图像转换成灰度图像显示，并保存
对灰度图像求Sobel边缘图，显示出来，并保存
对灰度图像进行Gaussian平滑，并保存（需要体会平滑的作用）
对灰度图像进行2值化(Open 24-bit color bmp files, displays the image will rotate clockwise image content displayed image is divided into four equal-sized 90 degrees, the first and three pixels after swap to save the rotated image conversion ashes of the image display, and save images to grayscale seeking Sobel edge map is displayed, and save the gray image Gaussian smoothing, and save (experience required smoothing effect) grayscale image binarized)
- 2020-06-29 07:40:01下载
- 积分：1
-
py-faster-rcnn-master
图像检测的算法，Faster R-CNN算法，先对整张图像进行卷积计算，然后通过感兴趣区域池化层(RoI Pooling Layer)将选择性搜索算法推荐出来的候选区域和卷积网络计算出的特征映射图进行融合，得到候选区域对应的特征矢量，这种共享卷积计算的操作极大地减少了卷积计算的次数。而且这些特征矢量的维度统一，方便后续的分类工作。通过感兴趣区域池化层处理卷积特征，并将得到的特征送往两个并行计算任务进行训练，分类和定位回归。通过这些方法和改进的框架，Fast R-CNN 用更短的训练和测试时长，取得了比 R-CNN 更好的效果(Faster R-CNN algorithm first convolutes the whole image, then fuses the candidate regions recommended by the selective search algorithm and the feature mapping maps calculated by the convolution network through the RoI Pooling Layer to get the corresponding feature vectors of the candidate regions, which greatly reduces the number of convolution calculations. Moreover, the dimension of these feature vectors is unified, which facilitates the subsequent classification work. The convolution feature is processed by the pooling layer of the region of interest, and the obtained feature is sent to two parallel computing tasks for training, classification and positioning regression. Through these methods and improved framework, Fast R-CNN uses shorter training and testing time and achieves better results than R-CNN.)
- 2020-12-11 15:39:18下载
- 积分：1
-
lankton_stereo
基于双目的深度图获取,根据图像合成深度图左右视点( depth map based on binocular)
- 2016-11-15 21:11:59下载
- 积分：1
-
MarchingCubes
三维表面重建算法，matchingcube快速算法。(3D surface reconstruction algorithm)
- 2021-01-27 12:38:41下载
- 积分：1
-
my-DPCM
对图像进行预测编码，使用DPCM编码方案，实现代码简单易懂(images of predictive coding, the use of DPCM coding scheme to achieve easy-to-read code)
- 2007-06-15 09:58:51下载
- 积分：1
-
simulation
循环理论相关MATLAB程序：滚动轴承仿真信号的产生(加噪声干扰)(Cyclostationary related)
- 2011-12-12 13:45:34下载
- 积分：1
-
ncut_multiscale_1_4
图像分割算法，包括matlab代码，说明文档和运行结果截图(Image segmentation algorithms, including the matlab code, documentation and operating results screenshot)
- 2008-04-30 17:14:21下载
- 积分：1
-
SPIHT_bandelet
我写的基于bandelet域的spiht图像压缩算法。效果比经典的SPIHT好。文章已发，希望代码对大家有用。(I wrote bandelet domain-based SPIHT image compression algorithm. SPIHT is better than a good classic. Article has been distributed, I hope the code useful for everyone.)
- 2007-07-26 15:37:24下载
- 积分：1
-
去除图像的噪点
图像去噪，去除图像的噪点
图像去噪，去除图像的噪点(Image Denoising)
- 2011-09-25 19:47:35下载
- 积分：1
