Learning Structural Element Patch Models with Hierarchical Palettes

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, RI (2012)
PDF | Google Doc | Supplementary | Google Scholar | BibTex | EndNote


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.


computer vision