Stochastic models for generic images
Quarterly of Applied Mathematics
Introduction to Modern Information Retrieval
Introduction to Modern Information Retrieval
Surface Coding Based on Morse Theory
IEEE Computer Graphics and Applications
International Journal of Computer Vision
Tales of Shape and Radiance in Multi-view Stereo
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Multi-View Stereo Reconstruction of Dense Shape and Complex Appearance
International Journal of Computer Vision
Histograms of Oriented Gradients for Human Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Scalable Recognition with a Vocabulary Tree
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Keypoint Recognition Using Randomized Trees
IEEE Transactions on Pattern Analysis and Machine Intelligence
Evaluation of Features Detectors and Descriptors based on 3D Objects
International Journal of Computer Vision
Stability of Persistence Diagrams
Discrete & Computational Geometry
Dynamic Shape and Appearance Modeling via Moving and Deforming Layers
International Journal of Computer Vision
Region matching with missing parts
Image and Vision Computing
Controlled Recognition Bounds for Scaling and Occlusion Channels
DCC '11 Proceedings of the 2011 Data Compression Conference
Hi-index | 0.00 |
We describe a visual recognition system operating on a hand-held device, based on a video-based feature descriptor, and characterize its invariance and discriminative properties. Feature selection and tracking are performed in real-time, and used to train a template-based classifier during a capture phase prompted by the user. During normal operation, the system recognizes objects in the field of view based on their ranking. Severe resource constraints have prompted a re-evaluation of existing algorithms improving their performance (accuracy and robustness) as well as computational efficiency. We motivate the design choices in the implementation with a characterization of the stability properties of local invariant detectors, and of the conditions under which a template-based descriptor is optimal. The analysis also highlights the role of time as ''weak supervisor'' during training, which we exploit in our implementation.