A kernel-based method for very high spatial resolution remote sensing image classification is proposed in this article. The new kernel method is based on spectral-spatial information and structure information as well, which is acquired from topic model, Latent Dirichlet Allocation model. The final kernel function is defined as <i>K</i> = <i>u<sub>1</sub></i><i>K</i><sup>spec</sup> + <i>u<sub>2</sub></i><i>K</i><sup>spat</sup> + <i>u<sub>3</sub></i><i>K</i><sup>stru</sup>, in which <i>K</i><sup>spec</sup>, <i>K</i><sup>spat</sup>, <i>K</i><sup>stru</sup> are radial basis function (RBF) and <i>u<sub>1</sub></i> + <i>u<sub>2</sub></i> + <i>u<sub>3</sub></i> = 1. In the experiment, comparison with three other kernel methods, including the spectral-based, the spectral- and spatial-based and the spectral- and structure-based method, is provided for a panchromatic QuickBird image of a suburban area with a size of 900 × 900 pixels and spatial resolution of 0.6 m. The result shows that the overall accuracy of the spectral- and structure-based kernel method is 80 %, which is higher than the spectral-based kernel method, as well as the spectral- and spatial-based which accuracy respectively is 67 % and 74 %. What's more, the accuracy of the proposed composite kernel method that jointly uses the spectral, spatial, and structure information is highest among the four methods which is increased to 83 %. On the other hand, the result of the experiment also verifies the validity of the expression of structure information about the remote sensing image.