Unsupervised Category Modeling, Recognition, and Segmentation in Images
- 2 February 2008
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 30 (12), 2158-2174
- https://doi.org/10.1109/tpami.2008.24
Abstract
Suppose a set of arbitrary (unlabeled) images contains frequent occurrences of 2D objects from an unknown category. This paper is aimed at simultaneously solving the following related problems: 1) unsupervised identification of photometric, geometric, and topological properties of multiscale regions comprising instances of the 2D category, 2) learning a region-based structural model of the category in terms of these properties, and 3) detection, recognition, and segmentation of objects from the category in new images. To this end, each image is represented by a tree that captures a multiscale image segmentation. The trees are matched to extract the maximally matching subtrees across the set, which are taken as instances of the target category. The extracted subtrees are then fused into a tree union that represents the canonical category model. Detection, recognition, and segmentation of objects from the learned category are achieved simultaneously by finding matches of the category model with the segmentation tree of a new image. Experimental validation on benchmark data sets demonstrates the robustness and high accuracy of the learned category models when only a few training examples are used for learning without any human supervision.Keywords
This publication has 57 references indexed in Scilit:
- Learning to detect objects in images via a sparse, part-based representationIeee Transactions On Pattern Analysis and Machine Intelligence, 2004
- Recognition of shapes by editing their shock graphsIeee Transactions On Pattern Analysis and Machine Intelligence, 2004
- Spectral embedding of graphsPattern Recognition, 2003
- Image modeling with position-encoding dynamic treesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2003
- Using relaxation technique for region-based object recognitionImage and Vision Computing, 2002
- View-based object recognition using saliency mapsImage and Vision Computing, 1999
- Multiscale image segmentation by integrated edge and region detectionIEEE Transactions on Image Processing, 1997
- A transform for multiscale image segmentation by integrated edge and region detectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- A multiscale random field model for Bayesian image segmentationIEEE Transactions on Image Processing, 1994
- Mode detection by relaxationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1988