Return to search

Rotation Invariant Object Recognition from One Training Example

Local descriptors are increasingly used for the task of object recognition because of their perceived robustness with respect to occlusions and to global geometrical deformations. Such a descriptor--based on a set of oriented Gaussian derivative filters-- is used in our recognition system. We report here an evaluation of several techniques for orientation estimation to achieve rotation invariance of the descriptor. We also describe feature selection based on a single training image. Virtual images are generated by rotating and rescaling the image and robust features are selected. The results confirm robust performance in cluttered scenes, in the presence of partial occlusions, and when the object is embedded in different backgrounds.

Identiferoai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/7285
Date27 April 2004
CreatorsYokono, Jerry Jun, Poggio, Tomaso
Source SetsM.I.T. Theses and Dissertation
Languageen_US
Detected LanguageEnglish
Format15 p., 5162833 bytes, 968095 bytes, application/postscript, application/pdf
RelationAIM-2004-010, CBCL-238

Page generated in 0.0021 seconds