稀疏编码在动态纹理识别中的应用 - 中国图象图形学报.DOCVIP

中图法分类号：TP391.4 文献标识码：A 文章编号：1006-8961(200 ) - - 论文引用格式： 基于双重L2稀疏编码的高光谱图像分类 刘洋，姬晓飞，王杨扬 沈阳航空航天大学，沈阳 110136 摘 要：目的：为了有效提高高光谱图像分类的精度，提出了双重L2稀疏编码的高光谱图像分类方法。方法：首先对高光谱图像进行预处理，充分结合图像的空间信息和光谱信息，利用像元的空间连续性，用L2稀疏编码重建图像中每个像元。针对重建的图像数据，依据L2稀疏编码的最小误差和编码系数实现分类。结果：在公开的数据库AVIRIS 高光谱图像上进行验证，分类精度为99.44%，与SVM、KNN和L1稀疏编码方法比较有效地提高了分类的准确性。结论：实验结果表明，提出的方法应用于高光谱图像分类具有较好的分类效果lassification of hyperspectral image based on double L2 sparse coding Liu Yang, Ji Xiaofei, Wang Yangyang Shenyang Aerospace University，Shenyang 110136, China Abstract: Objective: To improve the classification accuracy of a hyperspectral image, double L2 sparse coding is proposed in this paper. Method: Pre-processing work was conducted on the hyperspectral image. In this process, the spatial and spectral information of the image were integrated adequately. Based on spatial continuity, the L2 sparse coding was introduced to reconstruct each pixel of the hyperspectral image. A pixel was represented by linear combination of all pixels in its neighborhood. This representation integrated spatial and spectral information, which benefited classification. The L2 sparse coding was used to achieve hyperspectral image classification according to construction error. Moreover, a coding coefficient was introduced into classification principles because of its distinguishable information. Result: Experiments were conducted on a publicly available hyperspectral image database called AVIRIS. To validate the?effectiveness?of the proposed method,?the comparison with SVM, KNN, and L1 sparse coding was carried out using both original and reconstructed images. The proposed method outperformed earlier approaches and improved the accuracy of classification of the hyperspectral image effectively, and then 99.44% classification accuracy was obtained. Conclusion: The method proposed in this paper can be effectively applied to the classification of hyperspectral images. Key words ：sparse coding; L2 sparse regularization; hypersp