Skip to content

An implementation of a parallel Gaussian blur algorithm written in CUDA C++. OpenCV is used solely for reading/writing images and converting between image formats.

License

Notifications You must be signed in to change notification settings

jIdle/GaussianBlur-CUDA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CUDA Parallel Gaussian Blur

This program will apply a Gaussian blur to the specified image. This is accomplished by convolving the target image with the Gaussian function. To the user, the resulting image will have been uniformly blurred, which can be helpful in many other algorithms such as blob detection and downsampling.

OpenCV is necessary for this program to work. While all image processing is done by standard C++ and CUDA libraries, retrieving image properties is made significantly easier by OpenCV.

This implementation was used in my performance analysis:

Comparing 2D Convolution Performance

Example

Initial Image

Image of Pikachu before convolution

Convolved Image

Image of Pikachu after convolution

About

An implementation of a parallel Gaussian blur algorithm written in CUDA C++. OpenCV is used solely for reading/writing images and converting between image formats.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages