The Similarity Search Tree is an efficient method for indexing high dimensional feature vectors. The main objective of this data structure is to obtain the nearest neighbors given a certain query vector in a reasonable amount of time. In this project, the k-NN algorithm was adapted for supporting image retrieval.
Dependencies
sudo pacman -S git-lfs
sudo pacman -S nlohmann-json
sudo pacman -S sfml
sudo pacman -S curl
Instructions to set the workspace
git clone https://github.com/ByJuanDiego/ss-tree.git
cd ss-tree
git lfs install
git lfs pull
unzip img.zip
Then, compile the interface
g++ -std=c++17 interface.cpp src/CortexAPI.cpp src/SStree.cpp src/tinyfiledialogs.c -o interface -lsfml-graphics -lsfml-window -lsfml-system -lcurl
Finally, call the executable
./interface
Search the K-NNs!
The Similarity Search Tree is an efficient method for indexing high dimensional feature vectors. The main objective of this data structure is to obtain the nearest neighbors given a certain query vector in a reasonable amount of time. In this project, the k-NN algorithm was adapted for supporting image retrieval.