Publication: Learning Structural Element Patch Models with Hierarchical Palettes
Date
2012
Published Version
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers
The Harvard community has made this article openly available. Please share how this access benefits you.
Citation
Givoni, Inmar, Jeroen Chua, Ryan Prescott Adams, and Brendan Frey. 2012. Learning structural element patch models with hierarchical palettes. In 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2416-2423. Piscataway, NJ: Institute of Electrical and Electronics Engineers.
Research Data
Abstract
Image patches can be factorized into 'shapelets' that describe segmentation patterns called structural elements (stels), and palettes that describe how to paint the shapelets. We introduce local palettes for patches, global palettes for entire images and universal palettes for image collections. Using a learned shapelet library, patches from a test image can be analyzed using a variational technique to produce an image descriptor that represents local shapes and colors separately. We show that the shapelet model performs better than SIFT, Gist and the standard stel method on Caltech28 and is very competitive with other methods on Caltech101.
Description
Other Available Sources
Keywords
Terms of Use
Metadata Only