Title :
An Improved Image Registration Method Based on SIFT
Author :
Hou, Zhenjie ; Zhao, Lei ; Gu, Liguo ; Lv, Guoling ; Wang, Mei
Author_Institution :
Coll. of Comput. & Inf. Eng., Inner Mongolia Agric. Univ., Hohhot, China
Abstract :
The features of SIFT are widely used in image matching because of it´s invariantion to images scale and rotation, but 128-dimensional description of the feature point reduce the efficiency of the algorithm. This paper presents an improved algorithm of SIFT, using ring and sequence of each feature vector to ensure rotation invariance while reducing the description of operator dimension and using traversal search to find a sample of the nearest neighbor feature points and the next nearest neighbor feature points . The experimental results show that when there are different levels of image geometric distortion, radiation distortion and noise, the improved algorithm is more stable and faster.
Keywords :
image matching; image registration; transforms; SIFT; image geometric distortion; image matching; improved image registration method; nearest neighbor feature points; operator dimension description; radiation distortion; rotation invariance; scale invariant feature transform; traversal search; Agricultural engineering; Agriculture; Asia; Computer vision; Convolution; Educational institutions; Image matching; Image registration; Nearest neighbor searches; Object recognition; Image Matching; SIFT method; Scale invariant; feature descriptor;
Conference_Titel :
Intelligent Interaction and Affective Computing, 2009. ASIA '09. International Asia Symposium on
Conference_Location :
Wuhan
Print_ISBN :
978-0-7695-3910-2
Electronic_ISBN :
978-1-4244-5406-8
DOI :
10.1109/ASIA.2009.11
