Spline Interpolation Sub Pixel Edge Detection Method Based on Improved Morphological Gradient

Abstract

In order to improve the accuracy of image edge detection.A spline interpolation sub pixel edge detection method based on improved morphological gradient is proposed in the thesis.Firstly,using improved morphological gradient filter operator for image coarse positioning;Then,the cubic spline interpolation method is carried out for pixel-level edge of the image interpolation so that the image edge locates in sub-pixel level.Have a simulation experiment to improved methods by Matlab, results show that the improved method can accurately detect the edge of the image, edge detection is fine, the precision of positioning is hight and the result of detection is good.

A Sub‐pixel Disparity Refinement Algorithm Based on Lagrange Interpolation

“…[7], Ref. [8] and SDRL algorithm. The calculated elevation is obtained by mean sub-pixel deviation result of five target buildings.…”

“…The cost volume calculated with two high-speed Semi-Global matching can obtain dense sub-pixel disparity maps, but the matching speed is slower because of using the global algorithm, and the original interpolation function cannot apply to image with non-corrective epipolar line. Nan proposes a cubic spline interpolation method to obtain sub-pixel result [8] . The cubic spline interpolation method has a simple operation process and a good convergence.…”

Moving edge detection with sub pixel accuracy in 1-D images

“…Algorithms from first group reach the sub pixel precision by pixels interpolation to get a finer picture and then apply conventional edge operators, such as LoG operator [3] or Canny [4]. The algorithms from second group use continuous function to fit either gradient profile of the edge [5] or image function [6][7][8][9]. Algorithms from third group search unknown parameters of edge model using spatial moments [10,11], gray level moments [12,13], Zernike moments [14,15] or Fourier-Mellin moments [16].…”