The Community for Technology Leaders
Green Image
Issue No. 01 - January (2010 vol. 32)
ISSN: 0162-8828
pp: 148-164
Sven Dickinson , University of Toronto, Toronto
Afsaneh Fazly , University of Toronto, Toronto
Michael Jamieson , University of Toronto, Toronto
Sven Wachsmuth , Bielefeld University, Bielefeld
Suzanne Stevenson , University of Toronto, Toronto
ABSTRACT
Given an unstructured collection of captioned images of cluttered scenes featuring a variety of objects, our goal is to simultaneously learn the names and appearances of the objects. Only a small fraction of local features within any given image are associated with a particular caption word, and captions may contain irrelevant words not associated with any image object. We propose a novel algorithm that uses the repetition of feature neighborhoods across training images and a measure of correspondence with caption words to learn meaningful feature configurations (representing named objects). We also introduce a graph-based appearance model that captures some of the structure of an object by encoding the spatial relationships among the local visual features. In an iterative procedure, we use language (the words) to drive a perceptual grouping process that assembles an appearance model for a named object. Results of applying our method to three data sets in a variety of conditions demonstrate that, from complex, cluttered, real-world scenes with noisy captions, we can learn both the names and appearances of objects, resulting in a set of models invariant to translation, scale, orientation, occlusion, and minor changes in viewpoint or articulation. These named models, in turn, are used to automatically annotate new, uncaptioned images, thereby facilitating keyword-based image retrieval.
INDEX TERMS
Language-vision integration, image annotation, perceptual grouping, appearance models, object recognition.
CITATION
Sven Dickinson, Afsaneh Fazly, Michael Jamieson, Sven Wachsmuth, Suzanne Stevenson, "Using Language to Learn Structured Appearance Models for Image Annotation", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 32, no. , pp. 148-164, January 2010, doi:10.1109/TPAMI.2008.283
107 ms
(Ver 3.1 (10032016))