基于离散余弦/样条字典的稀疏图像表示
Sparse image representation by discrete cosine/spline based dictionaries
Aston University(阿斯顿大学)
AI总结:
本文考虑由余弦和B样条函数生成的混合字典,通过正交匹配追踪等高非线性方法,证明所提字典的离散版本能显著提高图像表示的稀疏性。
摘要:
考虑了由余弦和B样条函数生成的混合字典。结果表明,通过高度非线性的方法(如正交匹配追踪),所提字典的离散版本在图像表示的稀疏性上获得了显著提升。
英文摘要:
Mixed dictionaries generated by cosine and B-spline functions are considered. It is shown that, by highly nonlinear approaches such as Orthogonal Matching Pursuit, the discrete version of the proposed dictionaries yields a significant gain in the sparsity of an image representation.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。