摘要
提出一种基于分块过完备稀疏表示的多聚焦图像融合算法。该方法将多聚焦源图像对应分块,采用稀疏模型进行分解,得到每个块的稀疏表示系数。考虑到稀疏系数向量的l1范数越大,带的信息量就越多,采用此因子对稀疏系数加权,求得融合系数,结合过完备字典重构融合图像。实验结果表明该图像融合方法取得较好的融合效果且优于传统小波分解融合方法。同时探讨了字典维数对所提出方法的影响。
A multi-focus image fusion scheme based on blocked sparse representation is presented in the paper. Firstly, the original images are divided into patches and then sparsely represented with learned dictionaries. Secondly, the coefficients are fused using the weighted average rules in which the weighted factors are calculated with l1 norm of the sparse coefficient vector. Finally, the fused image is constructed by the fused coefficients with the learned dictionary. The experiments show that the fusion algorithm is effective and superior to the traditional method based wavelet decomposition. Mean- while we have discussed the effects the over-complete dictionary has taken to the quality of the final fusion image.
出处
《电视技术》
北大核心
2012年第13期48-51,63,共5页
Video Engineering
关键词
稀疏表示
过完备字典
多聚焦图像
融合规则
sparse representation
over-complete dictionary
multi-focus images
fusion rules