摘要
针对现有稀疏表示算法存在字典单一、编码冗余的缺点,从人类视觉感知系统层次处理特性出发,依据神经元侧抑制与竞争机理,构建了基于卷积稀疏编码和K-奇异值分解(K-singular value decomposition,K-SVD)的联合字典。在此基础上提出结合卷积匹配追踪和正交匹配追踪算法对图像进行分层稀疏表示。实验结果表明联合字典能够自适应匹配图像中的边缘、斑块、纹理等特征,与单独的卷积字典和K-SVD冗余字典相比,稀疏表示能力更强。
Aiming at the deficiency of existed algorithm with single dictionary and redundant coding, the dictionary combined convolutional sparse coding and K-SVD is constructed in terms of the hierarchical properties of human visual perception systems and the lateral inhibition and competition mechanism of neurons. Further- more, an effective algorithm based on convolutional matching pursuit and orthogonal matching pursuit is pro- posed to obtain sparse image representation with the combined dictionary. The experimental results indicate that the combined dictionary can adaptively match up image geometric structures such as edge, blob, texture. In comparision with convolutional dictionary and redundancy dictionary based on K-SVD, the combined dictionary has sparser image representation.
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2012年第7期1493-1498,共6页
Systems Engineering and Electronics
基金
国家自然科学基金(60772079
61071200)
河北省自然科学基金(F2010001294)资助课题
关键词
稀疏表示
视觉感知
侧抑制与竞争
联合字典
卷积匹配追踪
sparse representation
visual perception
lateral inhibition and competition~ combined dictiona- ry
convolutional matching pursuit
