融合显著信息的LDA极光图像分类

Aurora Image Classification Based on LDA Combining with Saliency Information

美丽的极光形态各异,不同形态的极光蕴含不同的物理意义,所以研究极光图像的分类具有重要的科学价值.在LDA(latent Dirichlet allocation)模型基础上提出了一种融合显著信息的LDA方法(LDA with saliency information,简称SI-LDA),利用极光图像的谱残差(spectral residual,简称SR)显著信息生成视觉字典,加强极光图像的语义信息,并将其用于极光图像的特征表示.最后,利用SVM分类器对极光图像进行分类.实验结果表明,所提出的算法获得了良好的分类结果.

There are different shapes of auroras in the sky around the arctic pole and the antarctic pole and there are different physical meaning and significance for different auroras. Therefore, the research on classification of aurora images has significant scientific value. In this paper, an aurora image classification method based on LDA with saliency information （SI-LDA） is proposed. First, the salience information of aurora images is used to generate visual dictionary which enhances the semantic information of aurora images. Next, the aurora images are represented by SI-LDA. Finally, SVM is applied to classify aurora images. Experimental results show that the proposed method achieves high performance over other algorithms available.