Sciweavers

425 search results - page 26 / 85
» Robustness of Classifiers to Changing Environments
Sort
View
ICASSP
2011
IEEE
12 years 11 months ago
A robust feature extraction algorithm based on class-Modular Image Principal Component Analysis for face verification
Face verification systems reach good performance on ideal environmental conditions. Conversely, they are very sensitive to non-controlled environments. This work proposes the cla...
Jose Francisco Pereira, Rafael M. Barreto, George ...
ICIP
2008
IEEE
14 years 9 months ago
Omnidirectional tracking and recognition of persons in planar views
In this paper a view-independent head tracking system applying an Active Shape Model based particle filter is used to find precise image sections. DCTmod2 feature sequences are ex...
Andre Störmer, Gerhard Rigoll, Sascha Schreib...
IROS
2008
IEEE
155views Robotics» more  IROS 2008»
14 years 2 months ago
Performance evaluation of a vertical line descriptor for omnidirectional images
— In robotics, vertical lines have been always very useful for autonomous robot localization and navigation in structured environments. This paper presents a robust method for ma...
Davide Scaramuzza, Cédric Pradalier, Roland...
ML
2008
ACM
13 years 7 months ago
Incremental exemplar learning schemes for classification on embedded devices
Although memory-based classifiers offer robust classification performance, their widespread usage on embedded devices is hindered due to the device's limited memory resources...
Ankur Jain, Daniel Nikovski
ATAL
2009
Springer
14 years 2 months ago
Decommitting in multi-agent execution in non-deterministic environment: experimental approach
The process of planning in complex, multi-actor environment depends strongly on the ability of the individual actors to perform intelligent decommitment upon specific changes in ...
Jirí Vokrínek, Antonín Komend...