high performance computing on graphics processing units: hgpu.org

This paper presents an approach the point to point processing of digital images using parallel computing, particularly for grayscale, brightening, darkening, thresholding and contrast change. The point to point technique applies a transformation to each pixel on image concurrently rather than sequentially. This approach used CUDA as parallel programming tool on a GPU in order to take advantage of all available cores. Preliminary results show that CUDA obtains better results in most of the used filters. Except in the negative filter with lower resolutions images OpenCV obtained better ones, but using images in high resolutions CUDA performance is better.