Title :
Image pattern discovery by using the spatial closeness of visual code words
Author :
Sun, Meng ; Van hamme, Hugo
Author_Institution :
Dept. of Electr. Eng., Katholieke Univ. Leuven, Leuven, Belgium
Abstract :
A graph regularized non-negative matrix factorization (NMF) model is proposed for image pattern discovery. Each image is represented by its histogram of visual words (i.e. bag-of-words) and the image contents are discovered by the NMF model. The graph regularization preserves the spatial closeness of visual code words in the obtained patterns, thus improving the bag-of-words representation against its main shortcoming: the loss of spatial information. Experiments on a subset of the Caltech256 database show the efficacy of the proposed model.
Keywords :
graph theory; image representation; matrix decomposition; Caltech256 database; bag-of-words representation; graph regularized nonnegative matrix factorization; image pattern discovery; spatial closeness; visual code words; Entropy; Equations; Error analysis; Mathematical model; Training; Training data; Visualization; Image representation; graph regularization; non-negative matrix factorization; spatial information;
Conference_Titel :
Image Processing (ICIP), 2011 18th IEEE International Conference on
Conference_Location :
Brussels
Print_ISBN :
978-1-4577-1304-0
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2011.6115885