Title :
Content based image retrieval using Multiple Instance Decision Based Neural Networks
Author :
Yeong-Yuh Xu ; Chi-Huang Shih
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Hungkuang Univ., Taichung, Taiwan
Abstract :
This paper presents a Multiple-Instance Decision Based Neural Networks (MI-DBNN) based image retrieval system. Without precisely image segmentation, the image retrieval problem is considered as a Multiple-Instance Learning problem. A set of exemplar images are selected, each of which is labelled as conceptual related (positive) or conceptual unrelated (negative) image. Then, the MI-DBNN is trained to learn the user´s preferred image concept from the positive and negative examples. The proposed system is built and located on http://210.240.226.146/MIL/. Experimental results show that our method can significantly improve the retrieving performance from 68.4% to 80.7%, which outperforms to the results of some leading image retrieval methods.
Keywords :
content-based retrieval; image retrieval; learning (artificial intelligence); neural nets; MI-DBNN; content based image retrieval; image concept; multiple instance decision; multiple-instance learning problem; neural network; Artificial intelligence; Computers; Lead;
Conference_Titel :
Computational Intelligence and Cybernetics (CyberneticsCom), 2012 IEEE International Conference on
Conference_Location :
Bali
Print_ISBN :
978-1-4673-0891-5
DOI :
10.1109/CyberneticsCom.2012.6381641