An Edge Detection Algorithm of Image Based on Empirical Mode Decomposition

The performance of image segmentation depends on the output quality of the edge detection process. Typical edge detecting method is based on detecting pixels in an image with high gradient values, and then applies a global threshold value to extract the edge points of the image. In this paper, a new edge detection method is presented. The main contribution of our approach is to apply empirical mode decomposition (EMD) to detect the image edge. The EMD algorithm can decompose any nonlinear and non-stationary data. By means of EMD, the data can be decomposed into a number of intrinsic mode functions (IMF). When the image is decomposed by bidimensional empirical mode decomposition (BEMD), the first IMF image has a very good characterization of edge. After extracting the edge pixels from the first IMF image by applying a suitable threshold value, the obtained edge image is as clear as the edge image by other methods.