搜索资源列表
image_suppression.rar
- 背景剪除提取前景运动物体。用于单帧图像，制作样本,Cut away the background of the prospect of moving object extraction. For single frame images, the production of samples
normizeimage
- 用于遍历一个文件夹下所有的图片文件，对图片进行归一化，同时还进行翻转，对于机器学习制作样本，归一化非常有用（环境opencv2.2 vc2010)-Traverse a folder for all image files, the picture is normalized, while the flip, making samples for machine learning, normalization is very useful (Environmental opencv2.2 vc2
woodpicturerecognization
- 黄山松、棘柏、江南油杉 、马尾松、日本扁柏、日本香柏、水杉 和雪松等8种针叶材样本，按照常规方法制作横切面木材切片，并统一采用奥林巴斯OLYMPUS BX51显微镜和DP70数码显微成像系统采集显微图像。-Pinustaiwanensis，Juniperus formosana，Keteleeria cyclolopis，Pinus massoniana，Chamaecyparis obtusa，Thujastandishii，Metasequoia glyptostroboides...
mousecut
- 基于opencv。直接用鼠标点击，来获取多个图像同意位置的像素值，并直接制作成想要的特征。左键点击获取正样本，右键获取负样本，滚轮点击获取第三类样本。-based on opencv,using mouse to get the value of 6 pictures in the same location.
NumberRecognize
- 根据RBM深度网络（Hinton，2006）进行MINST手写文字的分类器的训练，利用训练得到的权值制作了这个小程序，通过这个程序可以看出训练结果对数据集内的测试样本和训练样本都能进行很好的识别，但是对其他的手写字体识别就没有那么好了。-According to RBM depth network (Hinton, 2006) conducted MINST handwritten text classifier training, using the training to get the r
info
- 用于制作正负样本的info，opencv---haartrain。本人的cv没有编辑的程序，自己写matlab班的。-Info for the production of positive and negative samples, opencv--- haartrain. My cv no program to edit, write your own matlab classes.
SampleMakingTool
- 用于目标检测制作正负样本，正样本在选取框的周围采样，负样本在图片其他位置采样。(For target detection, making positive and negative samples, positive samples are sampled around the selection box, and negative samples are taken at other locations in the picture.)
Matlab制作代码
- 这是一个有关于用Matlab对图像灰度化，二值化以及制作样本的方法。(This is about the use of Matlab grayscale images, two values, as well as the production of samples.)
change
- 用于Opencv样本制作，读取文件夹下的图片转为灰度和设定大小的图片(For Opencv sample production, read the folder under the picture to grayscale and set the size of the picture)
SVMTrain
- 基于OpenCV SVM分类器的一个行人检测程序，可以自己制作样本训练，ＶＳ２０１０亲测可用,随时解答问题(A pedestrain detection program based on OpenCV SVM)