Evaluation of sets of oriented and non-oriented receptive fields as local descriptors
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. We propose a performance criterion for a local descriptor based on the tradeoff between selectivity and invariance. In t...
Main Authors: | Yokono, Jerry Jun, Poggio, Tomaso |
---|---|
Language: | en_US |
Published: |
2004
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/7284 |
Similar Items
-
Evaluation of sets of oriented and non-oriented receptive fields as local descriptors
by: Yokono, Jerry Jun, et al.
Published: (2005) -
Rotation Invariant Object Recognition from One Training Example
by: Yokono, Jerry Jun, et al.
Published: (2004) -
Rotation Invariant Object Recognition from One Training Example
by: Yokono, Jerry Jun, et al.
Published: (2005) -
Boosting a Biologically Inspired Local Descriptor for Geometry-free Face and Full Multi-view 3D Object Recognition
by: Yokono, Jerry Jun, et al.
Published: (2005) -
Matching Interest Points Using Projective Invariant Concentric Circles
by: Chiu, Han-Pang, et al.
Published: (2004)