CUDA-based hybrid intuitionistic fuzzy edge detection algorithm

Abstract

Intuitionistic fuzzy edge detection algorithm has been used for the signification or characterization of images. It has been designed by experts and the algorithm provides to aim to minimize errors. However, it has a fixed value for thresholding. In this paper, a hybrid algorithm has been developed using the Otsu method which is calculated a threshold value depending on the images. To be applicable in parallel of intuitionistic fuzzy edge algorithm is pave the way for accelerating of algorithm by performing in the graphics card. Intuitionistic fuzzy logic edge detection algorithm has been tested by transferring different size images to graphics cards which has different computing capacity via Compute Unified Device Architecture (CUDA) programming environment which is manufactured by NVIDIA. Parallel model of the algorithm adapted to CUDA platform, compared to serial application running on processor, and has seen that shortened runtime at least 67 times, most 639 times.