关键词: 图像基, 独立分量分析, 稀疏编码, 经验模态分解

Abstract:

Image base learning is one of the important ways of image feature extraction and image expression. Nonnegative sparse coding not only features  the adaptability of standard sparse coding, spatial localization, orientation, and bandpass in different spatial frequency bands, but also responds to mammal's visual mechanism well. On the basis of the nonnegative sparse coding, this paper  joins the image structure information using the experience modality decomposition technology, proposes a combination of EMD and the nonnegative sparse coding algorithm, and ensures the sparseness of the coefficient matrix and the structural characteristics of the image bases extracted. The learned image bases not only have the characteristic of nonnegative sparse coding, but express the image's structure information well.

Key words: image base;independent component analysis;sparse coding;experience modality decomposition