搜索资源列表
facedetect-test
- 基于hog特征与支持向量机的方式,使用opencv自带的haar特征分类器,检测人脸-Adapt to hog feature and support vector machine (SVM) method, based on positive and negative samples opencv training face,
ZhiSel
- 智睿多选品牌评选系统系统定位于投票评选行业的量身开发,打造行业的领先服务评选品牌,系统整合单选/多选一体化功能,分类模块独立投票使用,并适合图文评选,本系统定位品牌,选秀,活动,政府,公安,年度评选等相关活动,新增URL传送加密,问题验证,防外链接功,代理IP检测加强功能,时间效验功能等-Rui Chi brand multiple choice selection system systems targeted at the development of tailor-voted indust
Clustering-Algorithm
- 聚类分析又称群分析,它是研究(样品或指标)分类问题的一种统计分析方法,同时也是数据挖掘的一个重要算法。本代码主要用于过程监控故障检测-Clustering analysis, also called group analysis, which is a statistical analysis method of the research (sample or index) classification problem, is also an important algorithm of dat
NF
- 用matlab编写的快速纽曼算法,用于社团检测,对于不太复杂的网络分类效果很好-Prepared using matlab Newman fast algorithm for detecting community, for less complex network classification works well
huidugongshengjuzhen
- 灰度共生矩阵,用于砂纸检测的特征提取,从而训练分类器-GLCM, feature extraction for detection of sandpaper, so training a classifier
som
- 自组织映射的基本代码,可用于分类,聚类,异常检测等-This self-organizing map is basic code,which can ba used for classification,clustering,anomaly detaction,etc.
jpeg_tamper_detect
- 此工程是基于jpeg重压缩检测的篡改区域定位的opencv的svm分类器应用程序,可以检测出经过PS或者美图秀秀修改过的jpeg重压缩图片的篡改区域。-This project is based on jpeg recompression tamper detection area positioning opencv of svm classification application, or can be detected through the PS beauties Xiu Xiu mod
extract_feature
- 此工程实现提取jpeg图像的DCT系数首字母概率作为jpeg重压缩检测的特征,以此特征训练出分类模板,可以检测出一张jpeg图像是单压缩还是重压缩。-Works to achieve this extract jpeg image DCT coefficients of the first letter of the probability of detection as a jpeg heavy compression feature, this feature trained classif
improved-harris
- 从经典的Harris角点检测方法不难看出,该算法的稳定性和k有关,而k是个经验值,不好把握,浮动也有可能较大。鉴于此,改进的Harris方法()直接计算出两个特征值,通过比较两个特征值直接分类,这样就不用计算Harris响应函数了。 另一方面,我们不再用非极大值抑制了,而选取容忍距离:容忍距离内只有一个特征点。该算法首先选取一个具有最大最小特征值的点(即:max(min(e1,e2)),e1,e2是harris矩阵的特征值)作为角点,然后依次按照最大最小特征值顺序寻找余下的角点,当然和前一
proj4
- 使用滑动窗的人脸检测,滑动窗口能够独立地对图片块进行分类,以确定是否属于被检测目标。内容如下: 1)载入正样本训练集(人脸),并将其转化为HoG特征 2)载入负样本训练集(没有人脸的任意场景),也将其转化为HoG特征 3)使用SVM,对分类器进行训练,训练集包括正训练集和负训练集 4)使用训练好的分类器,在不同的尺度上,对测试集进行分类 -Face detection with a sliding window.
fougun
- 有循环检测,周期性检测,MIT人工智能实验室的目标识别的源码,Relief计算分类权重。- There are cycle detection, periodic testing, MIT Artificial Intelligence Laboratory identification of the target source, Relief computing classification weight.
offline-sEMG-recognition
- 提取人体手臂肌电信号,手势识别,包括肌电信号的预处理,端点检测,特征提取,特征降维,SVM分类识别-sEMG based hand movements recognition using SVM
foulang
- 遗传算法无功优化,含噪脉冲信号进行相关检测,可以实现模式识别领域的数据的分类及回归。- Genetic algorithm based reactive power optimization, Noisy pulse correlation detection signal, You can achieve data classification and regression pattern recognition.
AdaBoost
- 经典的行人检测算法,AdaBoost分类器-AdaBoost Classifier using MATLAB program
data
- 使用matlab编程的,行人检测的adaboost分类器的数据,-adaboost classifier pedestrian detection of programming data
eye-detection
- opencv人眼检测算法,此算法是基于haar分类器的简单算法,可以实现摄像头视频的实时监测。算法简单但是很是实用,所以上传与大家分享-opencv eye detection algorithm, which is a simple algorithm based on haar classifier, can achieve real-time video surveillance camera. Algorithm is simple but very practical, so uplo
ANN
- 本程序为自组织特征映射神经网络,注释将为详细。本程序通常可作为一种样本特征检测器,在样本排序,样本分类以及样本检测中有广泛的用途。-This procedure is a self-organizing feature map neural network, and usually can be used as a sample characteristics detector, the sample ordering, sample classification and sample dete
NPDFaceDetector
- NPD人脸检测主要内容: 1.图像特征:Normalized Pixel Difference(NPD),存在查找表中。 2.特征筛选:deep quadratic tree 3.分类:soft cascade classifier-NPD Face Detection Content: 1. Image features: Normalized Pixel Difference (NPD), the presence of a lookup table. 2. Filter
haar_face_detection
- 运用Adaboost算法haar分类器实现的人脸检测,帧率是32。-Using Adaboost face detection algorithm of Haar classifier, the frame rate is 32.
circle-detection
- 图片圆形区域检测(先生成灰度图,再分类)-Photos circular area detector (Mr. into grayscale, reclassification)