Generic object recognition with boosting
Top Cited Papers
- 23 January 2006
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 28 (3) , 416-431
- https://doi.org/10.1109/tpami.2006.54
Abstract
This paper explores the power and the limitations of weakly supervised categorization. We present a complete framework that starts with the extraction of various local regions of either discontinuity or homogeneity. A variety of local descriptors can be applied to form a set of feature vectors for each local region. Boosting is used to learn a subset of such feature vectors (weak hypotheses) and to combine them into one final hypothesis for each visual category. This combination of individual extractors and descriptors leads to recognition rates that are superior to other approaches which use only one specific extractor/descriptor setting. To explore the limitation of our system, we had to set up new, highly complex image databases that show the objects of interest at varying scales and poses, in cluttered background, and under considerable occlusion. We obtain classification results up to 81 percent ROC-equal error rate on the most complex of our databases. Our approach outperforms all comparable solutions on common databases.Keywords
This publication has 30 references indexed in Scilit:
- Rapid object detection using a boosted cascade of simple featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- The effects of segmentation and feature choice in a translation model of object recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Detecting pedestrians using patterns of motion and appearancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Selection of scale-invariant parts for object class recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Ridge's corner detection and correspondencePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Improving appearance-based object recognition in cluttered backgroundsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Blobworld: image segmentation using expectation-maximization and its application to image queryingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Mean shift: a robust approach toward feature space analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Normalized cuts and image segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2000
- The design and use of steerable filtersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991