-
image
立体匹配sad算法，matlab基于SAD法对左右两幅图片进行匹配，并生成深度图像。.m文件。(Stereo matching sad algorithm)
- 2018-05-15 17:12:49下载
- 积分：1
-
siftregistration
这是一篇对于SIFT算法应用于非刚性图像配准的论文，相当不错(This is one for the SIFT algorithm is applied to non-rigid image registration of papers, quite good)
- 2008-12-30 15:47:17下载
- 积分：1
-
ACM
主动轮廓模型图像分割算法，讲XU改进的算法用MATLAB进行实现(Active Contour Model for Image Segmentation Algorithm, speaking XU improved algorithm using MATLAB for the realization of)
- 2008-01-17 20:45:45下载
- 积分：1
-
tuxiangfenge
说明： Matlab边缘检测和区域生长图像分割算法代码，适合于图像边缘检测。(Matlab edge detection and region growing image segmentation algorithm code, suitable for edge detection.)
- 2011-04-11 20:36:40下载
- 积分：1
-
yuhuiweixiang
迂回位相全息图matlab程序，经测试能正常运行，并且全息图效果良好(Detour phase hologram matlab procedures, have been tested to normal operation, and good hologram effect)
- 2008-07-07 11:17:29下载
- 积分：1
-
keypointDetection
点云关键点搜索，根据曲率极值法搜索关键点(PCL:keypoint detection, used for registration and segmentation)
- 2017-12-28 14:02:11下载
- 积分：1
-
aa
说明： 用matlab做彩色图像的二维直方图，比如rb、rg、bg等(use matlab to draw colour image histogram of two dimension )
- 2009-12-10 17:37:00下载
- 积分：1
-
fastRPCA-master
快速鲁棒性Pca方法的一段matlab程序(fastrpca eneneneneen)
- 2020-08-23 16:28:17下载
- 积分：1
-
Saliency
CVPR2013中出现的一种显著性特征检测算法，该算法用于模拟人眼视觉识别过程，提取图像中的显著性特征借后期目标对象的检测跟踪等使用，该算法(Context-Aware Saliency Detection。matlab implementation of an classical saliency detection alrogithm,which imitate our recognition process of eyes)
- 2013-10-03 22:45:25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
