BoF的做法是类似的:
- 对图库中的图像提取特征点,比如sift,surf,mser等
- 生成特征点的词典:对特征点进行聚类,k-means会是不错的选择
- 生成图片的BOF:对图片中的特征点,找到其在词典中的分类,然后计算该特征点的tf-idf权重,一张图像中所有特征点的分类和权重,构成了这张图像的BOF表示
- 查询过程是计算出查询图像的bof并跟图库中图像bof距离比较的过程
Just for Sharing
BoF的做法是类似的:
Posted in computer vision
Just another WordPress.com site
Just another WordPress.com site
我的心情魔方
希望能做一個分享各種資訊的好地方
西瓜大丸子汤的博客
Just another WordPress.com site
A Project By Melanie Coles
A blog about computer vision, robotics, and artificial intelligence.
paper review...
Blog for CS 7670 - Special Topics in Computer Vision
Life through nerd-colored glasses
Brainwaves Augmenting Consciousness
1,2,∞
and the university of nottingham
A bunch of random, thinned and stateless thoughts around the Web
Just another WordPress.com weblog
Chasing tomorrow's sunrise.