关键词: 深度图像, dense尺度不变特征变化（SIFT）特征, Gist特征, K-means算法, 局部约束线性编码（LLC）稀疏编码

Abstract: The classic image classification algorithms are mostly based on RGB or grayscale images, and the depth information of the object or scene has not been utilized?effectively. To solve this problem, this paper proposes an image classification method based on RGB-D fusion feature. Firstly, the dense SIFT feature of color image is fused with the global Gist feature of the depth image to generate a combined vector. Secondly, the improved K-means algorithm is used to build the visual dictionary of the fusion feature, overcoming the dependence on the initial point selection of traditional K-means algorithm. Moreover, in the stage of image representation, the approximate LLC feature coding method is introduced to operate sparse coding on feature base and its corresponding visual dictionary. Finally, the linear SVM is used for image classification. The experimental results show that the proposed algorithm can effectively improve the classification accuracy.

Key words: depth image, dense Scale Invariant Feature Transform（SIFT） feature, Gist feature, K-means, Locality-constrained Linear Coding（LLC） sparse coding