Description: HOG feature extraction
Description
This program is used to extract HOG(Histograms of oriented gradients) features from images. The integral histogram is used for fast histogram extraction. Both APIs and binary utility are provided.
It is written in C++.
References
N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005., vol. 1, 2005.
How to use:
1. To compile the code, you need download Boost library(http://www.boost.org/) with version 1.35 or higher.
2. To run the binary, you should make sure Boost so library is avaliable
3. The program are tested with Ubuntu 7.04, however, the API files are compitable with Windows also, and the binary utility hog.cpp depends on unistd.h.
To Search:
File list (Check if you may need any files):
HOG_linux
.........\bin
.........\...\hog
.........\...\runtest.sh
.........\...\runtest.sh~
.........\...\test.jpg
.........\...\test.kps
.........\HOG_linux.pro
.........\HOG_linux.pro.user
.........\include
.........\.......\CImg.h
.........\.......\hog_extractor.h
.........\.......\image.h
.........\.......\integral_histogram.h
.........\Makefile
.........\README
.........\src
.........\...\hog.cpp
.........\...\hog_extractor.cpp
.........\...\integral_histogram.cpp
.........\~$README
Download