TY - JOUR
T1 - Image interpretation using large corpus
T2 - Wikipedia
AU - Rahurkar, Mandar
AU - Tsai, Shen Fu
AU - Dagli, Charlie
AU - Huang, Thomas S.
N1 - Funding Information:
Dr. Huang is a member of the National Academy of Engineering, a Foreign Member of the Chinese Academies of Engineering and Sciences, and a Fellow of the International Association of Pattern Recognition and the Optical Society of America. He received a Guggenheim Fellowship, an A. V. Humboldt Foundation Senior U.S. Scientist Award, and a Fellowship from the Japan Association for the Promotion of Science. He also received the IEEE Signal Processing (SP) Society’s Technical Achievement Award in 1987, the SP Society Award in 1991, the IEEE Third Millennium Medal, the Honda Lifetime Achievement Award for ‘‘contributions to motion analysis,’’ and the IEEE Jack S. Kilby Medal, all in 2001. In 2002, he received the King-Sun Fu Prize, the International Association of Pattern Recognition, and the Pan Wen-Yuan Outstanding Research Award. In 2005, he received the Okawa Prize. In 2006, he was named by IS&T and SPIE as the Electronic Imaging Scientist of the Year. He is a Founding Editor of the International Journal Computer Vision, Graphics, and Image Processing and the Editor of the Springer Series in Information Sciences.
Funding Information:
Manuscript received April 7, 2009; revised December 7, 2009; accepted May 1, 2010. Date of publication June 14, 2010; date of current version July 21, 2010. The work of S.-F. Tsai was supported in part by the National Science Council, Taiwan under Contract NSC-095-SAF-I-564-035-TMS. M. Rahurkar was with the Beckman Institute, University of Illinois at Urbana-Champaign, Urbana, IL 61801 USA. He is now with A9.com, Palo Alto, CA 94301-1044 USA. S.-F. Tsai and T. S. Huang are with the Beckman Institute, University of Illinois at Urbana-Champaign, Urbana, IL 61801 USA (e-mail: [email protected]; [email protected]). C. Dagli was with the Beckman Institute, University of Illinois at Urbana-Champaign, Urbana, IL 61801 USA. He is now with Lincoln Laboratory, Massachusetts Institute of Technology, Lexington, MA 02420-9108 USA (e-mail: [email protected]).
PY - 2010/8
Y1 - 2010/8
N2 - Image is a powerful medium for expressing one's ideas and rightly confirms the adage, One picture is worth a thousand words. In this work, we explore the application of world knowledge in the form of Wikipedia to achieve this objectiveliterally. In the first part, we disambiguate and rank semantic concepts associated with ambiguous keywords by exploiting link structure of articles in Wikipedia. In the second part, we explore an image representation in terms of keywords which reflect the semantic content of an image. Our approach is inspired by the desire to augment low-level image representation with massive amounts of world knowledge, to facilitate computer vision tasks like image retrieval based on this information. We represent an image as a weighted mixture of a predetermined set of concrete concepts whose definition has been agreed upon by a wide variety of audience. To achieve this objective, we use concepts defined by Wikipedia articles, e.g., sky, building, or automobile. An important advantage of our approach is availability of vast amounts of highly organized human knowledge in Wikipedia. Wikipedia evolves rapidly steadily increasing its breadth and depth over time.
AB - Image is a powerful medium for expressing one's ideas and rightly confirms the adage, One picture is worth a thousand words. In this work, we explore the application of world knowledge in the form of Wikipedia to achieve this objectiveliterally. In the first part, we disambiguate and rank semantic concepts associated with ambiguous keywords by exploiting link structure of articles in Wikipedia. In the second part, we explore an image representation in terms of keywords which reflect the semantic content of an image. Our approach is inspired by the desire to augment low-level image representation with massive amounts of world knowledge, to facilitate computer vision tasks like image retrieval based on this information. We represent an image as a weighted mixture of a predetermined set of concrete concepts whose definition has been agreed upon by a wide variety of audience. To achieve this objective, we use concepts defined by Wikipedia articles, e.g., sky, building, or automobile. An important advantage of our approach is availability of vast amounts of highly organized human knowledge in Wikipedia. Wikipedia evolves rapidly steadily increasing its breadth and depth over time.
KW - Concepts
KW - Image understanding
KW - Wikipedia
UR - http://www.scopus.com/inward/record.url?scp=77954868497&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=77954868497&partnerID=8YFLogxK
U2 - 10.1109/JPROC.2010.2050410
DO - 10.1109/JPROC.2010.2050410
M3 - Article
AN - SCOPUS:77954868497
SN - 0018-9219
VL - 98
SP - 1509
EP - 1525
JO - Proceedings of the IEEE
JF - Proceedings of the IEEE
IS - 8
M1 - 5484723
ER -