NobleBlocks
Public

Improved SIFT Matching Algorithm

Published in Computer Science and Application • Jan 1, 2012
NobleIDNI2P51W87R96S03
Authors:
丁 灿

Abstract

SIFT特征描述子的高维性和复杂性,不但占用较大的内存空间,而且影响特征匹配的速度。文章采用基于特征点邻域梯度统计的思想,局部统计区域由以特征点为中心的8个同心方环分割出来的环形组成,并计算出其相应像素的梯度(模值和方向),统计出8个方向的梯度累加值,然后进行从大到小的排序,最后再进行规一化处理。建立新的描述子将原来的128维向量降低到64维,实验证明此方法在保持匹配精度的情况下提高了匹配速度。 The high dimension and complexity of feature descriptor of SIFT, not only occupy the memory space, b...

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!