Skip to content

In this project I used SIFT, a feature detection algorithm in computer vision to detect and describe local features in images, and camera calibration to determine the location of the camera in the scene. Using these techniques I was able to replace the Steve Jobs book with Mona Liza image.

Notifications You must be signed in to change notification settings

Razg93/Feature-detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 

Repository files navigation

Feature detection

Feature detection

In this project I used SIFT, a feature detection algorithm in computer vision to detect and describe local features in images, and camera calibration to determine the location of the camera in the scene. Using these techniques I was able to replace the Steve Jobs book with Mona Liza image. After finding the camera parameters with chessboard images processing I implemented the following steps:

1.Dividing the image to frames and finding the same tamplate as the replacement object in the frame.

image image

2.Finding the similar features in the template image and original image using SIFT function and draw the matches.

image

3.Using perspective projection matrix to transforms from the camera coordinate system to the normalized image coordinate system and warping the replacement image so that the features in the two images line up perfectly.

image

4.Build binary inverted mask from the original image.

image image

5.Finally merge the two images.

image

About

In this project I used SIFT, a feature detection algorithm in computer vision to detect and describe local features in images, and camera calibration to determine the location of the camera in the scene. Using these techniques I was able to replace the Steve Jobs book with Mona Liza image.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages