Spatial Contezt for Visual Vocabulary Construction

摘要：

The bag-of-visual-words model has been widely used in many applications, such as object recognition, image categorization, and visual information retrieval. However, most existing approaches construct a visual vocabulary by simply clustering image regions represented with low-level visual features, where spatial context of image regions has not been well utilized. In this paper, we present two techniques to take such a context into account. One is based on the Self-Organizing Map for Adaptive Processing of Structured Data (SOM-SD), and the other is based on our proposed Hierarchical Fuzzy C-means with Spatial Constraints (FCM-HS). We have employed these two methods together with language modeling for image categorization. Experimental results obtained on Caltech dataset have demonstrated that these two methods can achieve better classification performance than those without considering spatial context. The comparison of these two methods is also discussed in this paper.

关键词： Image categorization bag-of-visual words spatial information FCM-HS SOM-SD

作者: Ge Zhou Zhiyong Wang Jiajun Wang Dagan Feng

作者单位: School of Electronics and Information Engineering, Soochow University Suzhou, China School of Electronics and Information Engineering,Soochow University Suzhou,China School of Informat School of Information Technologies,University of Sydney NSW,Australia Department of Electronic and I

会议类型: 国际会议

会议名称: 2010 International Conference on Image Analysis and Signal Processing(2010 图像分析与信号处理国际会议 IASP 10)

会议地点: 厦门

会议语种:英文

页码: 176-181

在线出版日期: 2010-04-12（万方平台首次上网日期，不代表论文的发表时间）