A geometric correction method for projected images using SIFT feature points

Authors:
Toru Takahashi;Norihito Numa;Takafumi Aoki;Satoshi Kondo
Affiliations:
Tohoku University;Tohoku University;Tohoku University;Matsushita Electric Industrial
Venue:
PROCAMS '08 Proceedings of the 5th ACM/IEEE International Workshop on Projector camera systems
Year:
2008

Citing 5
Cited 0

Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Embedded Entertainment with Smart Projectors

Computer
Camera-Based Calibration Techniques for Seamless Multiprojector Displays

IEEE Transactions on Visualization and Computer Graphics
Spatial Augmented Reality: Merging Real and Virtual Worlds

Spatial Augmented Reality: Merging Real and Virtual Worlds

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a geometric correction method for projected images using SIFT feature points. A projected image correction method based on projector-camera system needs to obtain the correspondence between projector and camera images, which is obtained by projecting the special patterns on a screen. The special patterns must be re-projected when changing the environment, e.g., the projector or screen is moved. On the other hand, this paper proposes a geometric correction method using SIFT feature points on a projected image which does not employ any special patterns to obtain the correspondence between projector and camera images. Experimental result shows that the use of our proposed method makes it possible to correct distortion of projected images with only one snapshot.