Abstract: Weak edges are similar to the background in intensity which causes small gradient value.The previous edge extraction algorithms are difficult in detecting weak edges with tight threshold,while with loose threshold will lead to lots of false edges caused by noise and interference.An edge extraction algorithm based on linear features perception is proposed.The visual mode of linear perception is used as reference;and weak edges are selected according to their linear distribution.The experiment results show that the proposed algorithm has a significant enhanced ability to extract weak edges and inhibit false edges comparing with Edison edge extraction algorithm.