Introduction

libvot is a fast implementation of vocabulary tree, which is an algorithm widely used in image retrieval and computer vision. It usually comprises three components to build a image retrieval system using vocabulary tree: build a k-means tree using sift descriptors from images, register images into the database, query images against the database. In this library, we use C++11 standard multi-thread library to accelerate the computation, which achieves fast and accurate image retrieval performance. Currently this library is under active development for research purpose. If you find this repository useful, please star it to let me know. :)

Installation

The build system of libvot is based on CMake. To take full advantages of the new features in C++11, we require the version of CMake to be 2.8.12 or above. Current we have tested our project under Linux (Ubuntu 14.04, CentOS 7) and MacOS (10.10) using gcc. The common steps to build the library are:

Extract source files.
Create build directory and change to it.
Run CMake to configure the build tree.
Build the software using selected build tool.
Run "make test"
See src/example for the usage of this library.

On Unix-like systems with GNU Make as the build tool, the following sequence of commands can be used to compile the source code.

$ cd libvot
$ git submodule init & git submodule update  
$ mkdir build && cd build
$ cmake ..
$ make && make test

Optional dependencies include OpenCV, but it is not required to run the core functions in libvot.

First try

libvot now also has a feature extractor in development. You can use ./libvot_feature <image_list> to first generate a set of descriptor files and use them as inputs to image_search.

libvot supports two types of feature formats, one feature format we use internally and the other one generated by openMVG. One way to run libvot is to first generate descriptor files using openMVG, then run image_search in src/example. The usage is simply “Usage: ./image_search <sift_list> <output_dir> [depth] [branch_num] [sift_type] [num_matches] [thread_num]”. We also add a small image dataset fountain-P11 to illustrate this process. test_data folder only contains the desc files generated by openMVG, while the original images are not included in order to save space. If you use the out-of-source build as shown in the installation section and in the build directory, the following command should work smoothly and generate several output files in build/bin/vocab_out directory.

$ cd bin
$ ./image_search <sift_list> <output_folder> [depth] [branch_num] [sift_type] [num_matches] [thread_num]  
$ (e.g.) ./image_search ../../test_data/list ./vocab_out 6 8 1

Each line in match.out contains three numbers “first_index second_index similarity score”. Since the library is multi-threaded, the rank is unordered with respect to the first index (they are ordered w.r.t the second index). match_pairs saves the ordered similarity ranks, from *0*th image to *n-1*th image.

Contributing

We are working toward the next major release (0.2.0). If you are interested in contributing, please have a look at Roadmap.md. All types of contributions, including documentation, testing, and new features are welcomed and appreciated.

License

The BSD 3-Clause License

Contact and Donation

For inquiries and suggestions, please send your emails to tshen.nosp@m.aa@u.nosp@m.st.hk.

If you would like to support this project, you can contribute to this project, or make a donation via pledgie. Thanks