搜索资源列表
Hand-Detect 手势识别，使用OpenCV的haar 分类器
- 手势识别，使用OpenCV的haar 分类器。训练因为对各个环境不同，请大家自己下载或者自己训练样本。-Hand Recognition and Tracking using OpenCV. It uses Haar Classifier. Because Haar features are different, I did not include the .xml file, please download it online or train it yourself.
imageRecognition
- 有两组图片，分别为正样本，和负样本图片，利用SVM训练样本图片，然后输入图片，判断这副图片属于正样本还是负样本，一般用于模式识别中-Two sets of pictures, samples were positive, and negative sample images, the use of SVM training sample images, and then enter the picture, to judge this pair of images belong to the p
OCRecognization
- 基于OpenCV的OCR程序，可以实现数字识别，程序采用KNN算法，可以对样本数据进行计算-OpenCV on the OCR program, Digital Identification can be achieved, the program using KNN algorithm to calculate the sample data
How-to-build-classifier-
- 如何利用opencv训练自己的分类器，内有多篇资料，本人用过一次，可能样本太少，效果不太好-How-to build a cascade of boosted classifiers based on Haar-like features.
OpenCVtraining
- 用opencv自带的工具训练样本，并检测结果-With opencv own tools training samples, and the test results.
orl-eye-database
- orl人脸库中截取出来的眼睛样本，作为疲劳检测中的人眼训练样本-orl face database from the eyes of the interception of the sample, as the fatigue test samples in the training of the human eye
main
- opencv2.2 win 7 本程序可以为分类器创建大小统一的正样本。按下左键放大，右键缩小，中键保存。-This program based opencv2.2, it can create the uniform pictures for the classification of positive samples. Press the left key for zoom in, right key reduce, and the middle key to save.
SVM
- VC6.0编写，基于OpenCV的支持向量机分类程序，在400×400的平面上生3类随机样本点，然后给出利用SVM分类的决策面和支持向量-VC6.0 written OpenCV-based support vector machine classification procedures, the plane of 400 × 400 random samples of raw Category 3 points, and then give the decision-making surfac
HMM
- 基于HMM的单样本可变光照_姿态人脸识别-HMM-based single-sample variable lighting face recognition gesture _
ObjectMarker
- 该软件可以用来opencv训练样本，训练正样本和训练负样本-The software can be used opencv training samples
Bayesian-based-classifier-design
- 基于贝叶斯的分类器设计.用“cancer.mat”的数据作为训练样本集，建立Bayes分类器，用测试样本数据对该分类器进行测试，从而加深对所学内容的理解和感性认识。-Based on the Bayes classifier. ' Cancer.mat data as the training sample set, the establishment of the Bayes classifier, the classifier is tested with the test sampl
Face-recognition-based-on-PCA
- 基于vc++6.0和opencv1.0的单样本人脸识别。用了PCA和2DPCA降维，效果不错。附带样本-Face recognition based on the vc++6.0, and opencv1.0 single sample. With the PCA and 2DPCA dimensionality reduction, good results. Comes with sample
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.
123MNISTTrain
- 手写数字训练识别，基于MNIST库进行训练识别，6W个训练样本，识别率95 以上-Handwritten numeral recognition training, training on MNIST library identification, 6W training samples, the recognition rate of 95 or more
hogPsvm
- HOG特征点的提取并使用SVM分类器训练样本予以分类（样本尺寸可以不一）-HOG feature point extraction and SVM classifier using training samples to be classified (sample size may vary)
hand-label
- 道路场景识别，通过对样本图像处理和特征提取，再通过bp神经网络进行学习，最后通过学习后得到的权值进行样本识别。-Road scene recognition, through the sample image processing and feature extraction, and then through bp neural network learning, and finally by learning the weights obtained after the sample ide
faceLBP
- 包含一个性别分类的cpp文件，和已经训练好的gender.yml模型，最后计算出样本分类准确率。建议使用AR人脸数据库。使用格式为genderLBP 训练样本.txt 测试样本.txt。因为不用训练模型了，测试样本随便写个行了。测试样本的格式是：路径 1或者0。1表示男性，0表示女性。-Cpp file contains a gender classification, and has trained gender.yml model, and finally calculate the sam
PCA
- 用OPENCV实现了人脸识别系统，采用ORL人脸库进行测试，选择每个身份前5张做训练图，一共200个训练样本。-OPENCV achieved using face recognition system that uses the ORL testing, each identity before choosing to do training Figure 5, a total of 200 training samples.
cropnegativeimage
- opencv中处理负样本时随机从大尺寸样本图片中截取负样本图片-opencv random intercept negative sample images from the big picture when dealing with a sample size of negative samples
人头训练正负样本数据集
- 用来训练人头识别模型的正负样本数据集，正样本数据已经resize化。(The positive and negative sample data set is used to train the head recognition model, and the positive sample data has been resize.)