Browse > Article
http://dx.doi.org/10.9717/kmms.2018.21.8.960

Keyword Selection for Visual Search based on Wikipedia  

Kim, Jongwoo (Dept, of Computer Science and Engineering., Inha University)
Cho, Soosun (Dept. of Computer Science & Information Eng., Korea National University of Transportation)
Publication Information
Journal of Korea Multimedia Society / v.21, no.8, 2018 , pp. 960-968 More about this Journal
Abstract
The mobile visual search service uses a query image to acquire linkage information through pre-constructed DB search. From the standpoint of this purpose, it would be more useful if you could perform a search on a web-based keyword search system instead of a pre-built DB search. In this paper, we propose a representative query extraction algorithm to be used as a keyword on a web-based search system. To do this, we use image classification labels generated by the CNN (Convolutional Neural Network) algorithm based on Deep Learning, which has a remarkable performance in image recognition. In the query extraction algorithm, dictionary meaningful words are extracted using Wikipedia, and hierarchical categories are constructed using WordNet. The performance of the proposed algorithm is evaluated by measuring the system response time.
Keywords
Mobile Visual Search; Keyword Generation; Wikipedia; WordNet; Convolutional Neural Network; Tag Classification;
Citations & Related Records
연도 인용수 순위
  • Reference
1 J. Bughin, L. Corb, O. Nottebohm, M. Chui, B.D.M. Barbatet, R. Said, et al., The Impact of Internet Technologies: Search, McKinsey and Company, New York, 2011.
2 S.J. Lee, K.D. Lee, S.I. Na, S.K. Je, D.U. Jung, W.G. Oh, et al., "Technology and Standardization Trend of Mobile Visual Search," Electronics and Telecommunications Trends, Vol. 29, No. 1, pp. 61-71, 2014
3 P. Fischer, A. Dosovitskiy, and T. Brox, "Descriptor Matching with Convolutional Neural Networks: a Comparison to SIFT," eprint arXiv:1405.5769, 2014.
4 J. Wu, Y. Yu, C. Huang, and K. Yu, "Deep Multiple Instance Learning for Image Classification and Auto-Annotation," Proceeding of 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3460-3469, 2015.
5 A. Krizhevsky, I. Sutskever, and G.E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," Proceedings of the 25th International Conference on Neural Information Processing Systems, Vol. 1, pp. 1097-1105, 2012.
6 N.W. Jeong and S.S. Cho, "Instagram Image Classification with Convolution Neural Networks," Proceeding of Korean Society for Internet Information The 8th International Conference on Internet, pp. 2249-2252, 2016.
7 S.H. Kim, S.J. Bae, and Y.J. Ko, "Word Sense Disambiguation and Feature Extraction for Query Expansion Method Based on Korean Wikipedia," Journal of Korean Institute of Scientists and Engineers : Computing Practices and Letters, Vol. 17, No. 3, pp. 185-189, 2011.
8 S.J. Lee and S.S. Cho, "Tagged Web Image Retrieval Re-ranking with Wikipedia-based Semantic Relatedness," Journal of Korea Multimedia Society, Vol. 14, No. 11, pp. 1491-1499, 2011.   DOI
9 Y.K. Song, S.W. Jeong, and H.S. Kim, "A Semi-automatic Construction Method of a Named Entity Dictionary Based on Wikipedia," Journal of Korean Institute of Scientists and Engineers, Vol. 42, No. 11, pp. 1397-1403, 2015.