Interactive Relevance Visual Learning for Image Retrieval
This paper proposes mixture Gaussian neural networks (MGNN) to learn visual features from user specified query image objects or regions for relevance image retrieval. Instead of segmenting query image regions from sample images, relevance feedback feature learning is performed by the proposed MGNN to extract query visual features. After feature learning, the MGNN can be used to measure the appearance difference between the query features and images for image retrieval. The proposed methods were tested on COREL image gallery and the WWW image collections, and testing results were compared with currently leading approaches. From the experimental results, that the extracted and learned query visual features by MGNN can be very close to users’ mind and/or desire, and the closeness is somewhat related to the number of feature leaning iterations. Since any dimensional data can be approximated by mixture Gaussian distributions, thus using MGNN to query and to retrieve similar and/or relevance high dimensional data or images will be a new area of research for future works.
KeywordsContent-based image retrieval Visual keywords Mixture gaussian distribution Reinforced and anti-reinforced learning Decision-based neural network
Unable to display preview. Download preview PDF.
- 1.Shen, H.T., Ooi, B.C., Tan, K.-L.: Giving meanings to www images. In: MULTIMEDIA 2000: Proceedings of the Eighth ACM International Conference on Multimedia, New York, NY, USA, pp. 39–47 (2000)Google Scholar
- 2.Eakins, J., Graham, M.: Content-based image retrieval. In: Technical Report. University of Northumbria at Newcastle (1999)Google Scholar
- 3.Sethi, I.K., Coman, I.L.: Mining association rules between low-level image features and high-level concepts. In: Proceedings of the SPIE Data Mining and Knowledge Discovery, vol. III, pp. 279–290 (2001)Google Scholar
- 8.Smith, J.R., Chang, S.F.: VisualSeek: a fully automatic content based query system. In: Proceedings of the Fourth ACM International Conference on Multimedia, pp. 87–98 (1996)Google Scholar
- 9.Ma, W.Y., Manjunath, B.: Netra: a toolbox for navigating large image databases. In: Proceedings of the IEEE International Conference on Image Processing, pp. 568–571 (1997)Google Scholar
- 16.Xu, Y.-Y., Tseng, C.-L., Fu, H.-C.: Texture Recognition by Generalized Probabilistic Decision-Based Neural Networks. Expert Systems with Applications: An International Journal (0957-4174) 38(5) (May 2011) Google Scholar
- 17.Fu, H.-C., Xu, Y.-Y., Pao, H.-T.: Multimodal search for effective image retrieval. In: Proceedings of 15th International Conference on Systems, Signals and Image Processing (IWSSIP 2008), Bratislava, Slovakia, June 25–28, pp. 233–236 (2008)Google Scholar
- 18.Xu, Y.Y., Chuang, S.C., Tseng, C.L., Fu, H.-C.: Generalized probabilistic decision-based neural networks for texture classification and retrieval. In: The 2010 International Conference on Modelling, Identification and Control (ICMIC), Okayama, Japan, pp. 500–504 (2010)Google Scholar
- 19.Xu, Y.-Y., Fu, H.-C.: Visual Keyword Based Image Retrieval. in IJCSI 9(3), No 2 (May 2012)Google Scholar