A Single Threshold Edge Detection Algorithm Based on Multiscale Fusion

Edge detection based on multiscale wavelet transform is one of the important algorithms in images edge detection. In large scale it is strongly anti-noise, and in small scale it can accurately locate edge. In order to exploit both advantages, a new single threshold edge detection method based on edge fusion is developed using finite element method (FEM) multiscale wavelet transform. Firstly, edge effective envelope is developed, in the range of effective edge envelop, using FEM track algorithms for edge fusion and detection to local edge point according to FEM cell topology. Secondly, A single threshold is used for accurate locate edge of detection. The validly of the algorithm is proved by experiments on both synthetic and natural image