Author Search Result

[Author] Jinjun KUANG(1hit)

1-1hit
  • Robust Scene Categorization via Scale-Rotation Invariant Generative Model and Kernel Sparse Representation Classification

    Jinjun KUANG  Yi CHAI  

     
    LETTER-Image Recognition, Computer Vision

      Vol:
    E96-D No:3
      Page(s):
    758-761

    This paper presents a novel scale-rotation invariant generative model (SRIGM) and a kernel sparse representation classification (KSRC) method for scene categorization. Recently the sparse representation classification (SRC) methods have been highly successful in a number of image processing tasks. Despite its popularity, the SRC framework lucks the abilities to handle multi-class data with high inter-class similarity or high intra-class variation. The kernel random coordinate descent (KRCD) algorithm is proposed for 1 minimization in the kernel space under the KSRC framework. It allows the proposed method to obtain satisfactory classification accuracy when inter-class similarity is high. The training samples are partitioned in multiple scales and rotated in different resolutions to create a generative model that is invariant to scale and rotation changes. This model enables the KSRC framework to overcome the high intra-class variation problem for scene categorization. The experimental results show the proposed method obtains more stable performances than other existing state-of-art scene categorization methods.

FlyerIEICE has prepared a flyer regarding multilingual services. Please use the one in your native language.