Multi-level Ground Glass Nodule Detection and Segmentation in CT Lung Images
MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Analysis of Crohn's disease lesions in capsule endoscopy images
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Range segmentation of large building exteriors: A hierarchical robust approach
Computer Vision and Image Understanding
Scene parsing using a prior world model
International Journal of Robotics Research
Improving spatiotemporal inpainting with layer appearance models
ISVC'06 Proceedings of the Second international conference on Advances in Visual Computing - Volume Part II
A benchmark for indoor/outdoor scene classification
ICAPR'05 Proceedings of the Third international conference on Pattern Recognition and Image Analysis - Volume Part II
| Hi-index | 0.00 |
Classifying pictures into one of several semantic categories is a classical image understanding problem. In this paper, we present a stratified approach to both binary (outdoor-indoor) and multiple category of scene classification. We first learn mixture models for 20 basic classes of local image content based on color and texture information. Once trained, these models are applied to a test image, and produce 20 probability density response maps (PDRM) indicating the likelihood that each image region was produced by each class. We then extract some very simple features from those PDRMs, and use them to train a bagged LDA classifier for 10 scene categories. For this process, no explicit region segmentation or spatial context model are computed. To test this classification system, we created a labeled database of 1500 photos taken under very different environment and lighting conditions, using different cameras, and from 43 persons over 5 years. The classification rate of outdoor-indoor classification is 93.8%, and theclassification rate for 10 scene categories is 90.1%. As a byproduct, local image patches can be contextually labeled into the 20 basic material classes by using Loopy Belief Propagation [33] as an anisotropic filter on PDRMs, producing an image-level segmentation if desired.