A Theory for Multiresolution Signal Decomposition: The Wavelet Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Contextual Priming for Object Detection
International Journal of Computer Vision
Introduction to MPEG-7: Multimedia Content Description Interface
Introduction to MPEG-7: Multimedia Content Description Interface
Multi-level annotation of natural scenes using dominant image components and semantic concepts
Proceedings of the 12th annual ACM international conference on Multimedia
Classification of user image descriptions
International Journal of Human-Computer Studies
Exploiting spatial context constraints for automatic image region annotation
Proceedings of the 15th international conference on Multimedia
Multimedia Reasoning with Natural Language Support
ICSC '07 Proceedings of the International Conference on Semantic Computing
Evaluation of Localized Semantics: Data, Methodology, and Experiments
International Journal of Computer Vision
Exploiting Spatial Context in Image Region Labelling Using Fuzzy Constraint Reasoning
WIAMIS '08 Proceedings of the 2008 Ninth International Workshop on Image Analysis for Multimedia Interactive Services
An energy-based model for region-labeling
Computer Vision and Image Understanding
Local image tagging via graph regularized joint group sparsity
Pattern Recognition
Hi-index | 0.00 |
In this paper we present an approach for image region classification that combines low-level processing with high-level scene understanding. For the low-level training, predefined image concepts are statistically modelled using wavelet features extracted directly from image pixels. For classification, features of a given test region compared with these statistical models provide probabilistic evaluations for all possible image concepts. Maximising these values themselves already leads to a classification result (label). However, in our paper they are used as an input for the high-level approach exploiting explicitly represented spatial arrangements of labels, so called spatial prototypes. We formalise the problem using Fuzzy Constraint Satisfaction Problems and Linear Programming. They provide a model with explicit knowledge that is suitable to aid the task of region labelling. Experiments performed for nearly 6000 test image regions show that combining low-level and high-level image analysis increases the labelling accuracy significantly.