Gaussian mixture model for relevance feedback in image retrieval

Fang Qian1, Mingjing Li2, Lei Zhang2, Hong-Jiang Zhang2, Bo Zhang1
1Department of Computer Science and Technology, Tsinghua University, Beijing, China
2Microsoft Research Asia, Beijing, China

Tóm tắt

Relevance feedback (RF) has become a powerful technique in content-based image retrieval. Most RF methods assume that positive images follow the single Gaussian distribution, which is not sufficient to model the actual distribution of images due to the gap between the semantic concept and low-level features. In this paper, the Gaussian mixture model (GMM) is applied to represent the distribution of positive images in relevance feedback, and a novel method is proposed to estimate the parameters of the GMM. Both positive and negative examples are used to estimate the number of Gaussian components. Furthermore, due to the lack of training samples, unlabeled data are also incorporated to estimate the covariance matrices. Experimental results show that our GMM-based RF method outperforms that based on a single Gaussian model.

Từ khóa

#Feedback #Image retrieval #Radio frequency #Asia #Content based retrieval #Gaussian distribution #Parameter estimation #Covariance matrix #Computer science #Data mining

Tài liệu tham khảo

joachims, 1999, Transduc�ve inference for text classification using support vector machines, Proc I6th International Conf on Machine Learning, 200 ishikawa, 1998, MindReader: Query databases through multiple examples, Proceedings of the 26 th VLDB Conference bilmes, 1997, A gentle tutorial of the em algorithm and its application to parameter estimation for gaussian mixture and hidden markov models, Technical Report University of Berkeley ICSI-TR-97-021 10.1109/CVPR.2000.855823 vasconcelos, 1998, Embedded mixture modeling for efficient probabilistic content-based indexing and retrieval, Proc SPIE Multimedia Storage and Archiving Sys III, 10.1117/12.325807 10.1145/500141.500158 rui, 1998, Relevance feedback: A power tool in interactive content-based image retrieval, IEEE Transaction on Circuits and Systems for Video Technology Special Issue on Segmentation Description and Retrieval of Video Content, 8, 644 zhang, 2001, A neural network based self-learning algorithm of image retrieval, Chinese Journal of Software, 12, 1479