Scene image clustering based on boosting and GMM
Khiem Ngoc Doan, Toan Thanh, Thái Hoàng Lê · 2011
Gaussian Mixture Model (GMM) is widely used in unsupervised learning tasks. In this paper, we propose the boost-GMM algorithm which uses GMMs to cluster real world scenes. At first, images will be extracted with gist-feature to get the data set. At each boosting iteration, a new training set is constructed by using weighted sampling from the original dataset and GMM is used to provide a new data partitioning. The final clustering solution is produced by aggregating the multiple clustering results. Experiments on real-world scene sets indicate that boost-GMM has higher result than other algorithms.