Stel component analysis: Modeling spatial correlations in image class structure
- 1 June 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2044-2051
- https://doi.org/10.1109/cvpr.2009.5206581
Abstract
As a useful concept in the study of the low level image class structure, we introduce the notion of a structure element - `stel.' The notion is related to the notions of a pixel, superpixel, segment or a part, but instead of referring to an element or a region of a single image, stel is a probabilistic element of an entire image class. Stels often define clear object or scene parts as a consequence of the modeling constraint which forces the regions belonging to a single stel to have a tight distribution over local measurements, such as color or texture. This self-similarity within a region in a single image is typical of most meaningful image parts, even when in different images of similar objects the corresponding parts may not have similar local measurements. The stel itself is expected to be consistent within a class, yet flexible, which we accomplish using a novel approach we dubbed stel component analysis. Experimental results show how stel component analysis can assist in image/video segmentation and object recognition where, in particular, it can be used as an alternative of, or in conjunction with, bag-of-features and related classifiers, where stel inference provides a meaningful spatial partition of features.Keywords
This publication has 10 references indexed in Scilit:
- Learning The Discriminative Power-Invariance Trade-OffPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- An Experimental Study on Pedestrian ClassificationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Escaping local minima through hierarchical model selection: Automatic object discovery, segmentation, and tracking in videoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene CategoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Spatial Weighting for Bag-of-FeaturesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Geometric blur for template matchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- LOCUS: learning object classes with unsupervised segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Capturing image structure with probabilistic index mapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Characterising Virtual Eigensignatures for General Purpose Face RecognitionPublished by Springer Nature ,1998