Skip to content

Latest commit

 

History

History
16 lines (10 loc) · 984 Bytes

README.md

File metadata and controls

16 lines (10 loc) · 984 Bytes

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