作者: Lihua Wang , Zhiwu Lu , Horace H. S. Ip
DOI: 10.1007/978-3-642-03767-2_93
关键词:
摘要: In this paper, we propose a Hierarchical Spatial Markov Model (HSMM) for image categorization. We adopt the Bag-of-Words (BoW) model to represent features with visual words, thus avoiding heavy work of manual annotation in most based approaches. Our HSMM is designed describe spatial relations these words by modeling distribution transitions between adjacent over each category. A novel idea semantic hierarchy exerted composition relationship at level. Experiments demonstrate that our approach outperforms Bayesian hierarchical categorization 12.5% and it also performs better than previous 11.8% on average.