Region Contextual Visual Words for scene categorization |
| |
| Authors: | Shuoyan Liu De Xu Songhe Feng |
| |
| Affiliation: | 1. Institute of Computer & Information Technology, Beijing Jiaotong University, Beijing 100044, China;2. Beijing Key Lab of Intelligent Telecommunications Software and Multimedia, Beijing University of Posts and Telecommunications, Beijing 100876, China;1. Faculty of Life and Social Sciences, Swinburne University of Technology, Australia;2. Aix-Marseille Université, Centre National de la Recherche Scientifique, France;3. Dipartimento di Psicologia Generale, Università di Padova, Italy;4. IRCCS San Camillo Neurorehabilitation Hospital, Venice-Lido, Italy;1. Department of Psychology, University of Macau, Taipa, Macau;2. School of Psychology, Beijing Normal University, Beijing, People’s Republic of China;3. Department of Psychology, University of Potsdam, Potsdam, Germany;1. Center for Neural and Cognitive Sciences (CNCS), University of Hyderabad, Hyderabad 500046, India;2. Center for Mind/Brain Sciences (CiMEC), University of Trento, Trento 38068, Italy;3. School of Computer and Information Sciences, University of Hyderabad, Gachibowli, Hyderabad 500046, India;1. University of Iowa, United States;2. Postdam University, Germany |
| |
| Abstract: | This paper proposes a method for scene categorization by integrating region contextual information into the popular Bag-of-Visual-Words approach. The Bag-of-Visual-Words approach describes an image as a bag of discrete visual words, where the frequency distributions of these words are used for image categorization. However, the traditional visual words suffer from the problem when faced these patches with similar appearances but distinct semantic concepts. The drawback stems from the independently construction each visual word. This paper introduces Region-Conditional Random Fields model to learn each visual word depending on the rest of the visual words in the same region. Comparison with the traditional Conditional Random Fields model, there are two areas of novelty. First, the initial label of each patch is automatically defined based on its visual feature rather than manually labeling with semantic labels. Furthermore, the novel potential function is built under the region contextual constraint. The experimental results on the three well-known datasets show that Region Contextual Visual Words indeed improves categorization performance compared to traditional visual words. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
