An Efficient Boosting Algorithm for Combining Preferences
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Ranking Prior Likelihood Distributions for Bayesian Shape Localization Framework
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Context-based vision system for place and object recognition
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
FloatBoost Learning and Statistical Face Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Detection using Background Context
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 3 - Volume 03
Database-Guided Segmentation of Anatomical Structures with Complex Appearance
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
IPMI'07 Proceedings of the 20th international conference on Information processing in medical imaging
BoostMap: a method for efficient approximate similarity rankings
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Example based non-rigid shape detection
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part IV
COLT'06 Proceedings of the 19th annual conference on Learning Theory
Hi-index | 0.00 |
In this paper, we exploit the context information embodied in an image to develop a machine learning method called context ranking machine (CRM). Specifically, we leverage two kinds of context information: identity context and metric context. The identity context of an image patch refers to its origin (e.g., from which image it is cropped), and the metric context refers to its distance to the exact surrounding box of the target object inside the image. We use these context information in two ways. First, for object localization, instead of learning classifiers to separate the whole negative pool from all positives, we separate each positive from its own negatives sharing the same identity context. Second, we rank image patches according to their resemblance to the ground truth by establishing a connection between appearance based features and metric properties of the image. The CRM learns an image-based ranking algorithm via boosting and achieves an improved localization accuracy. We performed tests on echocardiogram images to localize heart chambers, and face images for eye band localization.