• 中国精品科技期刊
  • CCF推荐A类中文期刊
  • 计算领域高质量科技期刊T1类
Advanced Search
Xie Zhao, Ling Ran, and Wu Kewei. Incremental Learning Towards Scene Features in Independent Subspace[J]. Journal of Computer Research and Development, 2013, 50(11): 2287-2294.
Citation: Xie Zhao, Ling Ran, and Wu Kewei. Incremental Learning Towards Scene Features in Independent Subspace[J]. Journal of Computer Research and Development, 2013, 50(11): 2287-2294.

Incremental Learning Towards Scene Features in Independent Subspace

More Information
  • Published Date: November 14, 2013
  • Scene classification is not an easy task owing to the variability, ambiguity, and the wide range of illumination and scale conditions the scenes may apply. Since feature extraction and scene representation play important roles in classification tasks, this paper presents an approach for unsupervised feature learning based on independent subspace analysis. The proposed method could automatically learn structural feature bases organized in a grouped fashion from randomly sampled natural image patches in independent subspaces. Optimization process of feature bases is implemented under an incremental learning framework to cope with the learning difficulty with large or dynamic samples. Patch-based image descriptors are computed over regularly divided grids using nonlinear combination coefficients of the learned feature bases. These descriptors are then taken into the spatial pyramid matching model, which incorporates spatial layout information and global geometric correspondence for recognizing scene categories, to build hierarchical scene representations. Experiment reveals how the related parameters influence objective optimization process and the final classification performance. Compared with several typical models in classification task on OT scene dataset, the proposed method could form low-dimensional but efficient image patch descriptors and achieve high classification accuracy with stability.
  • Related Articles

    [1]Liu Lei, Shi Zhiguo, Su Haoru, and Li Hong. Image Segmentation Based on Higher Order Markov Random Field[J]. Journal of Computer Research and Development, 2013, 50(9): 1933-1942.
    [2]Du Yi, Zhang Ting, Lu Detang, Li Daolun. An Interpolation Method Using an Improved Markov Model[J]. Journal of Computer Research and Development, 2012, 49(3): 565-571.
    [3]Dong Yongquan, Li Qingzhong, Ding Yanhui, Peng Zhaohui. Constrained Conditional Random Fields for Semantic Annotation of Web Data[J]. Journal of Computer Research and Development, 2012, 49(2): 361-371.
    [4]Chen Yarui and Liao Shizhong. A Normalized Structure Selection Algorithm Based on Coupling for Gaussian Mean Fields[J]. Journal of Computer Research and Development, 2010, 47(9): 1497-1503.
    [5]Li Guochen, Wang Ruibo, Li Jihong. Automatic Labeling of Chinese Functional Chunks Based on Conditional Random Fields Model[J]. Journal of Computer Research and Development, 2010, 47(2): 336-343.
    [6]Wang Wenhui, Feng Qianjin, Chen Wufan. Segmentation of Brain MR Images Based on the Measurement of Difference of Mutual Information and Gauss-Markov Random Field Model[J]. Journal of Computer Research and Development, 2009, 46(3): 521-527.
    [7]Ge Hongwei and Liang Yanchun. A Multiple Sequence Alignment Algorithm Based on a Hidden Markov Model and Immune Particle Swarm Optimization[J]. Journal of Computer Research and Development, 2006, 43(8): 1330-1336.
    [8]Huang Chenrong, Zhang Zhengjun, Wu Huizhong. A Multi-Scale Images Edge Detection Model Based on Gap Statistic of Order Wilcoxon Rank Sum[J]. Journal of Computer Research and Development, 2005, 42(12): 2111-2117.
    [9]Shi Rui and Yang Xiaozong. Research on the Node Spatial Probabilistic Distribution of the Random Waypoint Mobility Model for Ad Hoc Network[J]. Journal of Computer Research and Development, 2005, 42(12): 2056-2062.
    [10]Tang Min, Wang Yuanquan, Pheng Ann Heng, Xia Deshen. Tracking Cardiac MRI Tag by Markov Random Field Theory[J]. Journal of Computer Research and Development, 2005, 42(10): 1740-1745.

Catalog

    Article views (1035) PDF downloads (647) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return