Beyond visual word ambiguity: Weighted local feature encoding with governing region |
| |
| Affiliation: | 1. School of Computer and Control Engineering, University of Chinese Academy of Sciences, 100049 Beijing, China;2. Institute of Automation, Chinese Academy of Sciences, Beijing, China;3. College of Computer Science and Technology, Beijing University of Technology, 100124 Beijing, China;4. National Engineering Research Center for Multimedia Software, School of Computer, Wuhan University, 430072 Wuhan, China;5. National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, P.O. Box 2728, Beijing, China;6. Key Lab of Intell. Info. Process, Institute of Computing Technology, Chinese Academy of Sciences, 100190 Beijing, China;1. Faculty of Information Science and Technology, Multimedia University, Jalan Ayer Keroh Lama, 75450 Melaka, Malaysia;2. Faculty of Engineering and Technology, Multimedia University, Jalan Ayer Keroh Lama, 75450 Melaka, Malaysia;1. School of Mathematics, Georgia Institute of Technology, 686 Cherry Street NW, Atlanta, GA 30332, USA;2. Istituto per le Applicazioni del Calcolo, CNR, Via dei Taurini 19, 00185 Roma, Italy;1. Institute of Computer and Communication Engineering, National Cheng Kung University, No. 1, University Road, Tainan City 701, Taiwan, ROC;2. Department of Electrical Engineering, National Cheng Kung University, No. 1, University Road, Tainan City 701, Taiwan, ROC;3. Department of Computer Science and Information Engineering, Da-Yeh University, No. 168, University Road, Da-Tsuen, Changhua County 515, Taiwan, ROC;1. School of Computer and Information Technology, Liaoning Normal University, Dalian 116029, PR China;2. Jiangsu Key Laboratory of Image and Video Understanding for Social Safety, Nanjing University of Science and Technology, Nanjing 210094, PR China |
| |
| Abstract: | Typically, k-means clustering or sparse coding is used for codebook generation in the bag-of-visual words (BoW) model. Local features are then encoded by calculating their similarities with visual words. However, some useful information is lost during this process. To make use of this information, in this paper, we propose a novel image representation method by going one step beyond visual word ambiguity and consider the governing regions of visual words. For each visual application, the weights of local features are determined by the corresponding visual application classifiers. Each weighted local feature is then encoded not only by considering its similarities with visual words, but also by visual words’ governing regions. Besides, locality constraint is also imposed for efficient encoding. A weighted feature sign search algorithm is proposed to solve the problem. We conduct image classification experiments on several public datasets to demonstrate the effectiveness of the proposed method. |
| |
| Keywords: | Visual word ambiguity Governing region Weighted encoding Image classification Sparse Bag-of-visual words Object categorization Locality constraint |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
