An Image Mosaic Method Based on SIFT Feature Matching

被引：1

作者：

Cao Lijing ^{[1
]}

Lv Ming ^{[1
]}

机构：

[1] Natl Univ Def Technol, Dept Automat Control, Coll Mechatron Engn & Automat, Chang Sha 410073, Peoples R China

来源：

MATERIALS SCIENCE AND INFORMATION TECHNOLOGY, PTS 1-8 | 2012年 / 433-440卷

关键词：

image mosaic; SIFT; RANSAC; Hat function; global intensity revise;

D O I：

10.4028/www.scientific.net/AMR.433-440.5420

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

This paper concerns the problem of image mosaic. An image matching method based on SIFT features and an image blending method of improved Hat function are proposed in the paper. SIFT feature is local feature and keeps invariant to scale zoom, rotation and illumination. It is also insensitive to noise, view point changing and so on. Because of this our method is insensitive to orientation, scale and illumination of input images, so it's possible to accomplish image mosaic between arbitrary matching images and the Hat function blending algorithm with global intensity revise makes the mosaic image accepted by human eyes.

引用

页码：5420 / 5424

页数：5

共 10 条

[1] Shape indexing using approximate nearest-neighbour search in high-dimensional spaces [J].