Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random Fields
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Pattern Analysis and Machine Intelligence
Optimal Estimation of Contour Properties by Cross-Validated Regularization
IEEE Transactions on Pattern Analysis and Machine Intelligence
Recognizing 3-D Objects Using Surface Descriptions
IEEE Transactions on Pattern Analysis and Machine Intelligence
Object recognition by computer: the role of geometric constraints
Object recognition by computer: the role of geometric constraints
A Study of Methods of Choosing the Smoothing Parameter in Image Restoration by Regularization
IEEE Transactions on Pattern Analysis and Machine Intelligence
A training algorithm for optimal margin classifiers
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
Matching Two Perspective Views
IEEE Transactions on Pattern Analysis and Machine Intelligence
Markov random field modeling in computer vision
Markov random field modeling in computer vision
Learning Compatibility Coefficients for Relaxation Labeling Processes
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics)
IEEE Transactions on Pattern Analysis and Machine Intelligence
Adaptive Pixel-Based Data Fusion for Boundary Detection
EMMCVPR '99 Proceedings of the Second International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition
Learning-based robot vision: principles and applications
Learning-based robot vision: principles and applications
Hi-index | 0.00 |
Object recognition systems involve parameters such asthresholds, bounds and weights. These parameters have to be tunedbefore the system can perform successfully. A common practice is tochoose such parameters manually on an {\it add\ hoc} basis, which is adisadvantage. This paper presents a novel theory of parameterestimation for optimization-based object recognition where the optimalsolution is defined as the global minimum of an energy function. Thetheory is based on supervised learning from examples. {\it Correctness} and {\it instability} are established as criteria for evaluating theestimated parameters. A correct estimate enables the labeling impliedin each exemplary configuration to be encoded in a unique global energyminimum. The instability is the ease with which the minimum is replacedby a non-exemplary configuration after a perturbation. The optimalestimate minimizes the instability. Algorithms are presented forcomputing correct and minimal-instability estimates. The theory isapplied to the parameter estimation for MRF-based recognition andpromising results are obtained.