A framework for learning query concepts in image classification
- 20 January 2003
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (10636919), 423-429 Vol. 1
- https://doi.org/10.1109/cvpr.1999.786973
Abstract
In this paper, we adapt the Multiple Instance Learning paradigm using the Diverse Density algorithm as a way of modeling the ambiguity in images in order to learn "visual concepts" that can be used to classify new images. In this framework, a user labels an image as positive if the image contains the concept. Each example image is a bag of instances (sub-images) where only the bag is labeled-not the individual instances (sub-images). From a small collection of positive and negative examples, the system learns the concept and uses it to retrieve images that contain the concept from a large database. The learned "concepts" are simple templates that capture the color, texture and spatial properties of the class of images. We introduced this method earlier in the domain of natural scene classification using simple, low resolution sub-images as instances. In this paper, we extend the bag generator (the mechanism which takes an image and generates a set of instances) to generate more complex instances using multiple cues on segmented high resolution images. We show that this method can be used to learn certain object class concepts (e.g. cars) in addition, to natural scenes.Keywords
This publication has 12 references indexed in Scilit:
- Image segmentation using local variationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- An optimized interaction strategy for Bayesian relevance feedbackPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Color- and texture-based image segmentation using EM and its application to content-based image retrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Body plansPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Locating objects using the Hausdorff distancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Approximating Hyper-Rectangles: Learning and Pseudorandom SetsJournal of Computer and System Sciences, 1998
- A Note on Learning from Multiple-Instance ExamplesMachine Learning, 1998
- Solving the multiple instance problem with axis-parallel rectanglesArtificial Intelligence, 1997
- PAC learning axis-aligned rectangles with respect to product distributions from multiple-instance examplesPublished by Association for Computing Machinery (ACM) ,1996
- Comparing images using the Hausdorff distanceIeee Transactions On Pattern Analysis and Machine Intelligence, 1993