Math @ Duke
|
Publications [#265090] of Guillermo Sapiro
Papers Published
- Bar, L; Sapiro, G, Hierarchical invariant sparse modeling for image analysis,
Proceedings - International Conference on Image Processing, ICIP
(December, 2011),
pp. 2397-2400, IEEE, ISSN 1522-4880 [doi]
(last updated on 2025/02/02)
Abstract: Sparse representation theory has been increasingly used in signal processing and machine learning. In this paper we introduce a hierarchical sparse modeling approach which integrates information from the image patch level to derive a mid-level invariant image and pattern representation. The proposed framework is based on a hierarchical architecture of dictionary learning for sparse coding in a cortical (log-polar) space, combined with a novel pooling operator which incorporates the Rapid transform and max pooling to attain rotation and scale invariance. The invariant sparse representation of patterns here presented - can be used in different object recognition tasks. Promising results are obtained for three applications - 2D shapes classification, texture recognition and object detection. © 2011 IEEE.
|
|
dept@math.duke.edu
ph: 919.660.2800
fax: 919.660.2821
| |
Mathematics Department
Duke University, Box 90320
Durham, NC 27708-0320
|
|