In this paper, we introduce a novel set of features for robust object recognition, which exhibits outstanding performances on a variety ofobject categories while being capable of learning from only a fewtraining examples. Each element of this set is a complex featureobtained by combining position- and scale-tolerant edge-detectors overneighboring positions and multiple orientations.Our system - motivated by a quantitative model of visual cortex -outperforms state-of-the-art systems on a variety of object imagedatasets from different groups. We also show that our system is ableto learn from very few examples with no prior category knowledge. Thesuccess of the approach is also a suggestive plausibility proof for aclass of feed-forward models of object recognition in cortex. Finally,we conjecture the existence of a universal overcompletedictionary of features that could handle the recognition of all objectcategories.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/30504 |
| Date | 14 November 2004 |
| Creators | Serre, Thomas, Wolf, Lior, Poggio, Tomaso |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 10 p., 17638397 bytes, 793841 bytes, application/postscript, application/pdf |
| Relation | Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory |
Page generated in 0.0021 seconds