基于递推算法的Krawthcouk矩的局部图像重建

Reconstruction of ROI Algorithm Based on Krawtchouk Moments and Recursive Arithmetic

图像局部特征提取在图像处理领域中有着重要的应用,Zernike等其他正交矩,一般用来表达图像的整体特征;而Krawtchouk矩则可以用来表达图像的局部特征。本文在Krawtchouk不变矩定义的基础上,讨论了基于递推算法的Krawtchouk不变矩的图像局部重建问题。最后给出了基于上述算法的实验结果。实验结果表明,该算法不仅可以有效地提取图像的局部特征,而且提取特征和图像重建时间与原始算法相比都有显著减少。

Local feature extraction of an image is the most important application in the research field of image processing, it is shown that the Krawtchouk moments can be employed to extract local features of an image, unlike Zenike moments other orthogonal moments, which generally capture the global features. This paper briefly introduces the concept of the Krawtehouk moments and then discusses the Reconstruction of ROI algorithm based on Krawtchouk Moments and Rccursive Arithmetic. The experiment of Reconstruction of ROI based on the improved invariant Krawtchouk moments has proven the feasibility of the approach.