搜索资源列表
siftDemoV4
- 对图像进行基于SIFT算法的特征提取并对图像特征并实现特征匹配-the implement of the sift algorithm and matching based on the feature extracted the image
TestSift_siftFeat
- 测试sift特征点,并且在图片中显示出来。直接在sift源码上修改的,将提取特征点部分和匹配部分分开了,这部分是提取特征点。在vs2010上可运行,需要配置opencv-Test sift feature points and displayed in the picture. On sift modified source code directly, the feature points are extracted portion and mating portion separated,
video_SIFT
- 可是实现对视频的sift特征提取,只需根据视频文档的位置修改路径即可-But to achieve sift feature extraction video, simply modify the path to the document based on the location of the video
Featurepoint2Delaunay
- 本代码使用Opencv开源库实现,首先使用sift算子进行特征点提取,然后使用opencv中的三角剖分函数以所提取的特征点为基本点进行三角剖分。-This code uses Opencv open source library implementation, first using sift operator the feature point extraction and use of triangulation opencv functions to the extracted featu
miefei
- 可以提取一幅图中想要的目标,这是第二能量熵的matlab代码,结合PCA的尺度不变特征变换(SIFT)算法。- Target can be extracted in a picture you want, This is the second energy entropy matlab code, Combined with PCA scale invariant feature transform (SIFT) algorithm.
sift11
- 用于提取sift特征,准确地说是提取dsift 特征,即密集采样的sift特征-it is used to extract dsift feature ,sdfasdfjlkajsdlkfjlkasjdf
SIFT_VC
- sift算子提取特征点,自动提取影像特征点,该算子具有良好的稳定性和实用性-sift operator extracting feature points
fanheng
- 可以提取一幅图中想要的目标,包括最小二乘法、SVM、神经网络、1_k近邻法,结合PCA的尺度不变特征变换(SIFT)算法。- Target can be extracted in a picture you want, Including the least squares method, the SVM, neural networks, 1 _k neighbor method, Combined with PCA scale invariant feature transform (SIF
qanyeng
- 结合PCA的尺度不变特征变换(SIFT)算法,重要参数的提取,可以广泛的应用于数据预测及数据分析。- Combined with PCA scale invariant feature transform (SIFT) algorithm, Extract important parameters, Can be widely used in data analysis and forecast data.
saibai
- 结合PCA的尺度不变特征变换(SIFT)算法,DC-DC部分采用定功率单环控制,重要参数的提取。- Combined with PCA scale invariant feature transform (SIFT) algorithm, DC-DC power single-part set-loop control, Extract important parameters.
SURF_features_extracting
- 用于图像的特征提取,运算速度快!比传统的SIFT算法快好多!(Feature extraction for images, fast operation! Much faster than the traditional sift algorithm!)