원문정보
보안공학연구지원센터(IJUNESST)
International Journal of u- and e- Service, Science and Technology
Vol.8 No.6
2015.06
pp.299-304
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
Stable local feature and representation is a fundamental component of many image registration, 3D reconstruction and object recognition algorithms. SIFT is a good descriptor that encodes the salient aspects of the image gradient in the feature point’s neighborhood. This paper improved SIFT- based local image descriptor and proposed a SIFT feature matching algorithm based on improved 2DPCA which can eliminate both rows and columns of relevance. Experimental results show that improved 2DPCA-SIFT algorithm is relatively stable, accurate and fast.
목차
Abstract
1. Introduction
2. Traditional SIFT Feature Matching Algorithm
2.1. Establishment of Scale-Space
2.2. Computation the Feature Direction of Key Points
2.3. SIFT Feature Descriptor Vectors
2.4. Improved 2DPCA-SIFT Feature Matching Algorithm
3. Experimental Results and Analysis
4. Summary
References
1. Introduction
2. Traditional SIFT Feature Matching Algorithm
2.1. Establishment of Scale-Space
2.2. Computation the Feature Direction of Key Points
2.3. SIFT Feature Descriptor Vectors
2.4. Improved 2DPCA-SIFT Feature Matching Algorithm
3. Experimental Results and Analysis
4. Summary
References
키워드
저자정보
참고문헌
자료제공 : 네이버학술정보