A Bayesian approach integrating regional and global features for image semantic learning

Luong-Dong Nguyen, Ghim-Eng Yap, Ying Liu, Ah-Hwee Tan, Liang-Tien Chia, Joo-Hwee Lim
2009 2009 IEEE International Conference on Multimedia and Expo  
In content-based image retrieval, the "semantic gap" between visual image features and user semantics makes it hard to predict abstract image categories from low-level features. We present a hybrid system that integrates global features (Gfeatures) and region features (R-features) for predicting image semantics. As an intermediary between image features and categories, we introduce the notion of mid-level concepts, which enables us to predict an image's category in three steps. First, a
more » ... tion system uses G-features to predict the probability of each category for an image. Simultaneously, a R-prediction system analyzes R-features to identify the probabilities of mid-level concepts in that image. Finally, our hybrid H-prediction system based on a Bayesian network reconciles the predictions from both R-prediction and G-prediction to produce the final classifications. Results of experimental validations show that this hybrid system outperforms both Gprediction and R-prediction significantly.
doi:10.1109/icme.2009.5202554 dblp:conf/icmcs/NguyenYLTCL09 fatcat:hj5aqunen5df5ee4vbhy5zj6jq