Journal
IEEE TRANSACTIONS ON IMAGE PROCESSING
Volume 20, Issue 8, Pages 2301-2314Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2010.2103081
Keywords
Image classification; image decomposition; multilabel context
Funding
- NRF/IDM [NRF2008IDM-IDM004-029]
- Ministry of Public Safety & Security (MPSS), Republic of Korea [C1080-1101-0001] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
- National Research Foundation of Korea [220-2008-1-D00096] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
Ask authors/readers for more resources
Most research on image decomposition, e. g., image segmentation and image parsing, has predominantly focused on the low-level visual clues within a single image and neglected the contextual information across images. In this paper, we present a new perspective to image decomposition piloted by the multilabel context associated with each individual image. Observing that the contextual information (i.e., local label representations of the same label are similar while those from different labels are dissimilar) exists across images, we propose to perform image decomposition in a collective way and obtain an optimal representation for each label from a set of multilabeled images. We formulate the problem as an optimization problem which maximizes inter-label difference while minimizing the intra-label difference of the target label representations and propose two ways to solve this problem. Such a contextual image decomposition has a wide variety of applications, among which two exemplary ones-multilabel image annotation and label ranking, are presented and evaluated with different classification techniques. Extensive experiments on two benchmark datasets demonstrate promising results.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available