AN EFFICIENT REFINING IMAGE ANNOTATION TECHNIQUE BY COMBINING PROBABILISTIC LATENT SEMANTIC ANALYSIS AND RANDOM WALK MODEL

摘要

In this paper, we present a new method for refining image annotation based on a combination of probabilistic latent semantic analysis (PLSA) and random walk (RW). We first construct a PLSA model with asymmetric modalities to estimate the posterior probabilities of each annotation keywords for one image, and then a label similarity graph is constructed by a weighted linear combination of label similarity and visual similarity. Followed by a random walk process over a label graph is employed to further mine the correlation of the keywords so as to capture the refining annotation, which is very important for semantic-based image retrieval. The novelty of our method mainly lies in two aspects: exploiting PLSA to accomplish the initial semantic annotation task and implementing random walk process over the constructed label similarity graph to refine the candidate annotations generated by the PLSA. Compared with several state-of-the-art approaches on Corel5k and Mirflickr25k datasets, the experimental results show that our approach performs more efficiently and accurately.