Machine Learning
Normalized Cuts and Image Segmentation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Contour and Texture Analysis for Image Segmentation
International Journal of Computer Vision
Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns
IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic image annotation and retrieval using cross-media relevance models
Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Probability Estimates for Multi-class Classification by Pairwise Coupling
The Journal of Machine Learning Research
Boosting Color Saliency in Image Feature Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Bipartite graph reinforcement model for web image annotation
Proceedings of the 15th international conference on Multimedia
Exploiting spatial context constraints for automatic image region annotation
Proceedings of the 15th international conference on Multimedia
LabelMe: A Database and Web-Based Tool for Image Annotation
International Journal of Computer Vision
Content Aware Image Enhancement
AI*IA '07 Proceedings of the 10th Congress of the Italian Association for Artificial Intelligence on AI*IA 2007: Artificial Intelligence and Human-Oriented Computing
Semantic modeling of natural scenes based on contextual Bayesian networks
Pattern Recognition
Image annotation for adaptive enhancement of uncalibrated color images
VISUAL'05 Proceedings of the 8th international conference on Visual Information and Information Systems
| Hi-index | 0.00 |
We propose a region-based method for the annotation of outdoor photographs. First, images are oversegmented using the normalized cut algorithm. Each resulting region is described by color and texture features, and is then classified by a multi-class Support Vector Machine into seven classes: sky, vegetation, snow, water, ground, street, and sand. Finally, a rejection option is applied to discard those regions for which the classifier is not confident enough. For training and evaluation we used more than 12,000 images taken from the LabelMe project.