搜索资源列表
基于神经网络的图像识别程序
- 基于神经网络的识别程序，程序采用三层BP网络训练，采用了普通定义中加入动量因子的训练法，精确度很高。-based on neural network identification procedures, procedures adopted a three-tier network training BP, with its definition of momentum into the training factor, a high degree of precision.
grimace
- 一个老外文章中用到的人脸数据库，包含多种肤色的人脸，可供做人脸识别的人员进行训练和测试用！-a foreigner article used the face database, a mixture of color face, Face recognition for the staff to do the training and testing with!
BPProcess
- 对于图像处理，采用BP网络进行训练。使用Matlab编写-for image processing using neural network training. Prepared using Matlab
SkinSegment
- 自己编的程序，有gui界面给出结果的。这是个自己建的皮肤高斯模型，通过训练的到的阈值。在ycbcr域对皮肤区域进行了分割。-developed procedures, gui interface is the outcome. This is a build their own skin Gaussian model, the training of the threshold. Ycbcr domain in the region of the skin segmentation.
faceproc
- 人脸识别的程序,通过求特征值来训练预测人脸-face recognition procedure for the adoption of eigenvalues for training forecast to Face
Adaboost_LPR_Matlab_081010.rar
- 对第二次上传的源码修改后的10月10日的Matalb的基于Adaboost算法的车牌定位的源码！不过训练时间还是很长！里面含有积分图像的获得，haar 特征的生成等。Matlab高手可以优化一下，感兴趣的欢迎下载！,From the second source of the revised October 10 of Matalb-based license plate location algorithm Adaboost source! But training is still a ver
Ada_car.rar
- training adaboost to detect car number,training adaboost to detect car number
shadow.rar
- 基于VC环境的人体边缘检测程序，包括种子填充、轮廓跟踪等算法的实习。,VC-based edge detection in human environmental procedures, including seed filling, the outline of the training algorithm for tracking.
Compression-sensing
- 压缩传感理论，用K-SVD算法训练字典，过完备字典-Compression sensing theory, SVD algorithm with K- had complete training dictionary, dictionary
PG_BOW_DEMO
- 图像的特征用到了Dense Sift，通过Bag of Words词袋模型进行描述，当然一般来说是用训练集的来构建词典，因为我们还没有测试集呢。虽然测试集是你拿来测试的，但是实际应用中谁知道测试的图片是啥，所以构建BoW词典我这里也只用训练集。 其实BoW的思想很简单，虽然很多人也问过我，但是只要理解了如何构建词典以及如何将图像映射到词典维上去就行了，面试中也经常问到我这个问题，不知道你们都怎么用生动形象的语言来描述这个问题？ 用BoW描述完图像之后，指的是将训练集以及测试集
cvHaarTraining.rar
- Opencv Haar training, the setting and parameter is configed. you can debug into the training process to get the whole flowchart of adaboost training.,Opencv Haar training, the setting and parameter is configed. you can debug into the training process
particlefiltertotrackhand2.rar
- 使用粒子滤波进行手部跟踪,动态转移矩阵训练得到.使用B样条曲线对手外部轮廓拟合,并引入形状空间限制维数.详细理论参考active contour由michael isard和Andrew blake完成.,The use of particle filter for hand tracking, the dynamic transfer matrix has been training. The use of B-spline curve fitting against an external
objectmaker_source.rar
- 利用Haar-like特征的训练代码，可用于人脸识别等应用,Haar-like features of the use of the training code, can be used in applications such as face recognition
An-HOG-LBP-Human-Detector
- 一种基于HOG-LBP特征的人脸检测方法，对于遮挡的人体非常有效。-By combining Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP) as the feature set, we pro- pose a novel human detection approach capable of handling partial occlusion. Two kinds of detectors
adaboostHaarFeature
- adaboost haar feature computation and training
HSV-Space-segmentation(Training-and-Testing)
- 在HSV色彩空间进行彩色图像分割源码，包括学习和训练算法，获得分割参数-In the HSV color space for color image segmentation source code, including learning and training algorithm, access to segmentation parameters
2009Based_on_Co-Training
- Co-Training的协同目标跟踪内容，感兴趣的看看吧-Co-Training for collaborative target tracking content, of interest to see it
undergrad
- 自适应超分辨率图像盲重建算法研究与应用 清华大学综合训练论文-Blind adaptive super-resolution image reconstruction algorithm and application of comprehensive training thesis of Tsinghua University
K-SVD-dictionary-training-algorithms
- 基于KSvd算法的图像重建，包括图像、代码、字典等-K-SVD dictionary training algorithms
Extended Yale B Database
- 这是MNIST数据库（一个手写数字的数据库，它提供了六万的训练集和一万的测试集，它的图片是被规范处理过的，28*28的灰度图） 总共4个文件: train-labels-idx1-ubyte: training set labels t10k-images-idx3-ubyte:? test set images t10k-labels-idx1-ubyte:? test set labels train-images-idx3-ubyte: training set images(T