Please use this identifier to cite or link to this item:
Title: Panoramic image stitching using SIFT
Authors: Nar, Soon Keong
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
Issue Date: 2009
Abstract: This report describes how SIFT keypoints are obtained by using Difference-of-Gaussian for detecting local maxima and minima and methods to filter detected local features in order to obtain stable keypoints. The magnitudes of gradient and orientations are added to each keypoint before creating each keypoint descriptor. These highly distinctive SIFT features are matched against each other to find k nearest-neighbors for each feature. These correspondences are then used to find m candidate matching images for each image. Based on the extracted local features, image transformation matrices are built, images are to be processed based on the transformation matrices. This report also discussed methods for blending images to create seamless panorama.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
1.74 MBAdobe PDFView/Open

Page view(s) 50

Updated on Dec 1, 2020


Updated on Dec 1, 2020

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.