Rotation Invariant Object Recognition from One Training Example
Citable URI:
http://hdl.handle.net/1721.1/7285
| Title: | Rotation Invariant Object Recognition from One Training Example |
| Author: | Yokono, Jerry Jun; Poggio, Tomaso |
| Issue Date: | 2004-04-27 |
| Abstract: | 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. |
| URI: | http://hdl.handle.net/1721.1/7285 |
| Other Identifiers: | AIM-2004-010 CBCL-238 |
| Series/Report no.: | AIM-2004-010, CBCL-238 |
| Keywords: | AI, object recognition, local descriptor, rotation invariant |
Files in this item
| Files | Size | Format |
|---|---|---|
| AIM-2004-010.pdf | 968.0Kb | application/pdf |
| AIM-2004-010.ps | 5.162Mb | application/postscript |
This item appears in the following Collection(s)
All Items in DSpace@MIT are protected by original copyright, with all rights reserved, unless otherwise indicated.
|
|
Contact
MIT Libraries
|