Abstract
We propose a local region descriptor based on connected pattern spectra, and combined with normalized central moments. The descriptors are calculated for MSER regions of the image, and their performance compared against SIFT. The MSER regions were chosen because they can be efficiently selected by constructing a max-tree, a structure used to calculate both descriptors and region moments. Experiments on the UCID database show an improvement over SIFT in two out of five experimental setups, and comparable performance in two other experiments. The new descriptors are only half the size of SIFT, resulting in 4 times faster query times when performing exact search on descriptor index built from 262 images.
| Original language | English |
|---|---|
| Title of host publication | Image Processing (ICIP), 2015 IEEE International Conference on |
| Publisher | IEEE (The Institute of Electrical and Electronics Engineers) |
| Pages | 1548-1552 |
| Number of pages | 5 |
| ISBN (Print) | 978-1-4799-8339-1 |
| DOIs | |
| Publication status | Published - 1-Sept-2015 |
Keywords
- content-based retrieval
- image retrieval
- trees (mathematics)
- 2D connected pattern spectra
- UCID database
- content-based image retrieval
- image MSER regions
- max-tree structure
- normalized central moments
- short local region descriptors
- Detectors
- Global Positioning System
- Histograms
- Indexes
- Level set
- Shape
- CBIR
- local region descriptors
- max-tree
- pattern spectra