International Journal of Scientific Engineering and Technology

Open Access Open Access  Restricted Access Subscription Access

Image Registration Using Scale Invariant Feature Transform


Affiliations
1 Department of Electronics and Communication Engineering, Institute of Aeronautical Engineering, Dundigal, Hyderabad, Andhra Pradesh, India
2 Department of Electronics and Communication Engineering, Jawaharlal Nehru Technological University, Hyderabad, Andhra Pradesh, India
3 Department of Electronics and Communication Engineering, Marri Laxman Reddy Institute of Technology and Management, Dundigal, Hyderabad, Andhra Pradesh, India
 

Image registration is a key operation to spatially align two or more images for comparing the difference between them or exploiting complementary information from those images. The main objective regarding automatic registration of satellite images is to obtain an accurate set of tie points and then apply the transformation function which is most suitable to the pair of images to be registered. An efficient method for AIR (Automatic Image Registration) is proposed, which combines image segmentation and scale invariant feature transform (SIFT), complemented by an outlier removal stage. The reference and unregistered images may differ in translation, rotation, and scale and may present distortions. The performance of this method is evaluated through measures such as Nred, RMSall, RMSloo, Pquad, Bad Point Proportion: BPP(r), Scat, Cost Function (φ).

Keywords

Automatic Image Registration (AIR), Image Segmentation, Optical Images, Scale Invariant Feature Transform (SIFT), Principle Component Analysis (PCA).
User
Notifications
Font Size

Abstract Views: 112

PDF Views: 0




  • Image Registration Using Scale Invariant Feature Transform

Abstract Views: 112  |  PDF Views: 0

Authors

N. NagaRaju
Department of Electronics and Communication Engineering, Institute of Aeronautical Engineering, Dundigal, Hyderabad, Andhra Pradesh, India
T. Satya Savitri
Department of Electronics and Communication Engineering, Jawaharlal Nehru Technological University, Hyderabad, Andhra Pradesh, India
A. Swamy
Department of Electronics and Communication Engineering, Marri Laxman Reddy Institute of Technology and Management, Dundigal, Hyderabad, Andhra Pradesh, India

Abstract


Image registration is a key operation to spatially align two or more images for comparing the difference between them or exploiting complementary information from those images. The main objective regarding automatic registration of satellite images is to obtain an accurate set of tie points and then apply the transformation function which is most suitable to the pair of images to be registered. An efficient method for AIR (Automatic Image Registration) is proposed, which combines image segmentation and scale invariant feature transform (SIFT), complemented by an outlier removal stage. The reference and unregistered images may differ in translation, rotation, and scale and may present distortions. The performance of this method is evaluated through measures such as Nred, RMSall, RMSloo, Pquad, Bad Point Proportion: BPP(r), Scat, Cost Function (φ).

Keywords


Automatic Image Registration (AIR), Image Segmentation, Optical Images, Scale Invariant Feature Transform (SIFT), Principle Component Analysis (PCA).