Edge detection algorithm for noisy remote sensing image using directional filter

Abstract Remote sensing image edge detection is the basis of remote registration and recognition. In view noise formed in process acquisition, a new algorithm based on directional filter proposed to improve accuracy The wavelet transform denoising, three main features including scale, direction shape wave are introduced. target can be identified more accurately noisy by filter, result obtained binarization segmentation non-maximum suppression. Through experimental comparison with other denoising algorithms, accurate results obtained, there obvious advantages operation efficiency.