arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 0909.1310math.NAcs.CVcs.NA
收藏

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)

James Bowley, Laura Rebollo-Neira

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。

↑