-
docLisegmentationcode
精心收集博士生编写的图像分割源代码，可以在matlab环境下使用。(Carefully prepared collection of doctoral image segmentation source code, you can use in the matlab environment.)
- 2008-05-27 13:10:37下载
- 积分：1
-
SR
说明： 基于MP的信号稀疏分解参考程序。源程序是《信号与图像的稀疏分解及初级应用》中的(MP sparse decomposition based on the signal reference program. Source is " Signal and image sparse decomposition and primary application" in the)
- 2009-10-29 15:50:02下载
- 积分：1
-
BWLabel
一种二值图像连通区域标记方法，能用于目标跟踪，我已经应用过，效果不错。(It is a new connected componet labeling algorithm for binary image,and can be used in object tracking. It is effective to be proved.)
- 2013-06-24 14:08:47下载
- 积分：1
-
ikmeans
说明： 利用ikmeans算法实现图像分割matlab代码(ikmeans algorithm to deal image segmentation)
- 2020-09-22 10:55:52下载
- 积分：1
-
27220065
利用正交匹配跟踪原子库对信号进行稀疏分解程序(Using orthogonal matching pursuit atom libraries for signal sparse decomposition process)
- 2016-01-01 13:31:26下载
- 积分：1
-
m_map
说明： m-map工具箱，可以帮助画图，比如世界地图的背景(M-map toolbox, can help draw pictures, such as the background of the world map)
- 2021-03-21 21:09:16下载
- 积分：1
-
fusion
通过将高分辨率的图像和低分辨率的图像进行融合，来实现图像的融合。(By fusing high-resolution and low-resolution images, image fusion can be achieved.)
- 2019-01-02 13:38:51下载
- 积分：1
-
zhencha
简单的帧间差分法，不过可以和其他方法结合来改进算法(A simple inter-frame difference method, but other methods can be combined to improve the algorithm for)
- 2009-11-23 21:46:25下载
- 积分：1
-
matlab.QIyizhifenjie
关于奇异值分解，图像特征融合，图像处理的特征图提取方法(About the singular value decomposition
)
- 2015-03-31 15:10:38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
