A wide baseline matching method based on scale invariant feature descriptor

2009 ◽  
Author(s):  
Jun Miao ◽  
Jun Chu ◽  
Guimei Zhang ◽  
Ruina Feng
Keyword(s):  
Feature Descriptor ◽  
Matching Method ◽  
Scale Invariant ◽  
Invariant Feature ◽  
Wide Baseline Matching ◽  
Scale Invariant Feature

An Improved SIFT Matching Algorithm

2012 ◽  
Vol 239-240 ◽  
pp. 1232-1237 ◽  
Author(s):  
Can Ding ◽  
Chang Wen Qu ◽  
Feng Su
Keyword(s):  
High Dimension ◽  
Gradient Method ◽  
Feature Matching ◽  
Feature Descriptor ◽  
Scale Invariant ◽  
Matching Algorithm ◽  
Invariant Feature ◽  
Feature Transform ◽  
New Feature ◽  
Scale Invariant Feature

The high dimension and complexity of feature descriptor of Scale Invariant Feature Transform (SIFT), not only occupy the memory spaces, but also influence the speed of feature matching. We adopt the statistic feature point’s neighbor gradient method, the local statistic area is constructed by 8 concentric square ring feature of points-centered, compute gradient of these pixels, and statistic gradient accumulated value of 8 directions, and then descending sort them, at last normalize them. The new feature descriptor descend dimension of feature from 128 to 64, the proposed method can improve matching speed and keep matching precision at the same time.

Distance-Scale Restricted SIFT Matching Method for Complicated Content & Different Scales Image Pairs

2014 ◽  
Vol 526 ◽  
pp. 292-296
Author(s):  
Zhen Yu Wu ◽  
Hu Hong
Keyword(s):  
Scale Invariant Feature Transform ◽  
Matching Method ◽  
Matching Accuracy ◽  
Scale Invariant ◽  
Simple Method ◽  
Invariant Feature ◽  
Matching Performance ◽  
Feature Transform ◽  
Image Pairs ◽  
Scale Invariant Feature

Scale invariant feature transform (SIFT) matching performance decreases greatly when images are in different scales with complicated content and wide-baseline. In this paper, we address this problem, and propose a simple method to improve SIFT matching. The proposed method restricts the matching searching area into much smaller and more likely region to improve matching performance. Experiments shows that the proposed method has saved up to 90% matching time and increased up to 4% in the accuracy, compared with SIFT and previously solutions which only improve the matching accuracy.

Sign in / Sign up

Export Citation Format

Share Document