关键词: 分层视觉表示, 计算机视觉, 潜在狄利克雷分配, 递归, 反馈

Abstract: Image layer visual representation has been currently used in computer vision field, but it is difficult for feed-forward image multilayer visual representation methods to deal with local ambiguities. An image multilayer visual representation method based on Latent Dirichlet Allocation (LDA) named LDA-IMVR was proposed. It derived a recursive generative model of LDA by implementing recursive probabilistic decomposition process. Meanwhile, it learned and deduced all layers of the hierarchy together, and improved classification and learning performance by using feed-back style. The approach was tested on Caltech 101 dataset. The experimental results show that the proposed method improves classification performance of objects compared with related hierarchical approaches, and it achieves better results in learned components and image patches visualization.

Key words: layer visual representation, computer vision, Latent Dirichlet Allocation (LDA), recursive, feed-back