An intelligent metadata extraction approach based on programming by demonstration

Authors:
Binge Cui;Jie Zhang
Affiliations:
The First Institute of Oceanography. SOA, Qingdao, Shandong, P.R. China,College of Information Science and Engineering, Shandong University of Science and Technology, Qingdao, Shandong, P.R. China;The First Institute of Oceanography. SOA, Qingdao, Shandong, P.R. China
Venue:
WISM'12 Proceedings of the 2012 international conference on Web Information Systems and Mining
Year:
2012

Citing 6
Cited 0

Developing services for open eprint archives: globalisation, integration and the impact of links

DL '00 Proceedings of the fifth ACM conference on Digital libraries
Wrapping Web Information Providers by Transducer Induction

EMCL '01 Proceedings of the 12th European Conference on Machine Learning
Maximum Entropy Markov Models for Information Extraction and Segmentation

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
CoScripter: automating & sharing how-to knowledge in the enterprise

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
Building Mashups by example

Proceedings of the 13th international conference on Intelligent user interfaces
Mashroom: end-user mashup programming using nested tables

Proceedings of the 18th international conference on World wide web

Quantified Score

Hi-index	0.00

Visualization

Abstract

Metadata extraction is an important prerequisite for remote sensing images management and sharing. Business users urgently need to extract metadata automatically and quickly. However, existing metadata extraction applications extract only one single type of image metadata. In this paper, we proposed a generic and extensible metadata extraction approach based on Programming by Demonstration (PbD). Data owners can specify the metadata items to be extracted and the extraction methods in an interactive and visual user interface. Such knowledge will be stored in the rule base in the form of rules. The advantage of this approach is that users do not need any programming knowledge, but they can handle new types of images themselves.