A novel method of edge detection with Gabor wavelet based on FFTW

Since remote sensing images´ features of substantial data and complex landmark, so it needs a higher requirement for edge detection operator. Using Gabor wavelet as the edge detection operator can get over the limitations of grads operator and Canny operator in edge detection. However, the method based on 2-D Gabor wavelet takes more time. In response to this lack of Gabor wavelet, this paper presents an edge detection method based on parallel processing of FFTW and Gabor wavelet and the experimental analysis shows this method can improve the processing speed of the algorithm greatly.