The Hierarchy-of-Visual-Words (HoVW) is a trademark image retrieval method that decomposes images into simpler geometric shapes and defines a descriptor for trademark image representation by encoding the hierarchical arrangement of component shapes. The proposed hierarchical organization of visual data stores each component shape as a visual word. It is capable of representing the geometry of individual elements and the topology of the trademark image, making the descriptor robust against linear as well as to some level of nonlinear transformation.
Check out our paper at arXiv.
 |
🏆 Best Undergraduate Work Award 🏆 Best Computer Vision/Image Processing/Pattern Recognition Main Track Paper Award at the 32nd Conference on Graphics, Patterns and Images (SIBGRAPI) 2019 |
|---|
@inproceedings{lourenco2019,
title = {{Hierarchy-of-Visual-Words: a Learning-based Approach for Trademark Image Retrieval}},
author = {Louren\c{c}o, V\'{i}tor N. and Silva, Gabriela G. and Fernandes, Leandro A. F.},
booktitle = {Proceedings of the 32nd Conference on Graphics, Patterns and Images (SIBGRAPI)},
year={2019},
}
To evaluate the HoVW framework follow the HoVW/pipeline.sh (Linux or MacOS) or HoVW/pipeline.sh (Windows).
All code is released under the GNU General Public License, version 3, or (at your option) any later version.