A decision-theoretic generalization of on-line learning and an application to boosting
Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Neural Network-Based Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Example-Based Learning for View-Based Human Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
A computational model for visual selection
Neural Computation
Improved Boosting Algorithms Using Confidence-rated Predictions
Machine Learning - The Eleventh Annual Conference on computational Learning Theory
Antifaces: A Novel, Fast Method for Image Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Machine Learning
Fast Face Detection with Precise Pose Estimation
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
An introduction to variable and feature selection
The Journal of Machine Learning Research
Boosting Chain Learning for Object Detection
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Object Recognition with Informative Features and Linear Classification
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Robust Real-Time Face Detection
International Journal of Computer Vision
Generalization Error Bounds for Threshold Decision Lists
The Journal of Machine Learning Research
FloatBoost Learning and Statistical Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Fast Binary Feature Selection with Conditional Mutual Information
The Journal of Machine Learning Research
Optimization Design of Cascaded Classifiers
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
WaldBoost " Learning for Time Constrained Sequential Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
A Time-Efficient Cascade for Real-Time Object Detection: With applications for the visually impaired
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03
Linear Asymmetric Classifier for cascade detectors
ICML '05 Proceedings of the 22nd international conference on Machine learning
A Design Principle for Coarse-to-Fine Classification
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Algorithms for Pattern Rejection
ICPR '96 Proceedings of the 13th International Conference on Pattern Recognition - Volume 2
Feature-centric evaluation for efficient cascaded object detection
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Learning object detection from a small number of examples: the importance of good features
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Automatic cascade training with perturbation bias
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Face detection with the modified census transform
FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Towards optimal training of cascaded detectors
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Learning Fast Emulators of Binary Decision Processes
International Journal of Computer Vision
Face Detection Using a Time-of-Flight Camera
Dyn3D '09 Proceedings of the DAGM 2009 Workshop on Dynamic 3D Imaging
CIARP '09 Proceedings of the 14th Iberoamerican Conference on Pattern Recognition: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Topology modeling for Adaboost-cascade based object detection
Pattern Recognition Letters
Automatic eye detection using intensity filtering and K-means clustering
Pattern Recognition Letters
A modular approach to training cascades of boosted ensembles
SSPR&SPR'10 Proceedings of the 2010 joint IAPR international conference on Structural, syntactic, and statistical pattern recognition
Journal of Real-Time Image Processing
Viola-Jones based detectors: how much affects the training set?
IbPRIA'11 Proceedings of the 5th Iberian conference on Pattern recognition and image analysis
Robust face detection using local gradient patterns and evidence accumulation
Pattern Recognition
A cascade face recognition system using hybrid feature extraction
Digital Signal Processing
ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume Part III
A biased selection strategy for information recycling in Boosting cascade visual-object detectors
Pattern Recognition Letters
Hi-index | 0.00 |
Cascades of boosted ensembles have become popular in the object detection community following their highly successful introduction in the face detector of Viola and Jones. Since then, researchers have sought to improve upon the original approach by incorporating new methods along a variety of axes (e.g. alternative boosting methods, feature sets, etc.). Nevertheless, key decisions about how many hypotheses to include in an ensemble and the appropriate balance of detection and false positive rates in the individual stages are often made by user intervention or by an automatic method that produces unnecessarily slow detectors. We propose a novel method for making these decisions, which exploits the shape of the stage ROC curves in ways that have been previously ignored. The result is a detector that is significantly faster than the one produced by the standard automatic method. When this algorithm is combined with a recycling method for reusing the outputs of early stages in later ones and with a retracing method that inserts new early rejection points in the cascade, the detection speed matches that of the best hand-crafted detector. We also exploit joint distributions over several features in weak learning to improve overall detector accuracy, and explore ways to improve training time by aggressively filtering features.