A list,

Image edge detection is a system for locating the edges of objects in 2d or 3D images (especially medical images). The set of data elements representing the values of each element of the image is received through the input terminal (310). The data set is stored in a storage device (320). The processor (340) determines the edges of the objects in the image. The processor computes at least first and/or second derivatives of the data element and computes an isobarance line curvature of the image, identified by κ. The processor also determines a correction factor, a positive factor, which corrects for edge dislocations caused by the curvature of the object and/or blurring of said data. The positive factor α depends on the isilluminance line curvature κ. The processor then determines the zero crossing of the operator depending on the calculated derivative and the curvature of the isobarance line. The output (330) of the system provides an indication of the position of the edges in the image.

1. Basic steps of image edge detection (1) filtering. Edge detection is mainly based on derivative calculation, but it is affected by noise. But the filter reduces the noise and also causes the loss of edge strength. (2) enhancement. The enhancement algorithm highlights the points with significant gray changes in the field. This is usually done by calculating the gradient amplitude. (3) Detection. However, in some images, the larger gradient amplitude is not the edge point. (4) Positioning. Determine the exact position of the edges.

2. Edge algorithm: Smoothed by Sobel Prewitt, it has certain ability to suppress noise, but it is prone to multiple pixel widths.

3. Edge algorithm: Robert has a high precision in edge positioning and a good effect on images with steep edges and low noise. However, it has no smoothing processing and no ability to suppress noise.

Ii. Source code

function varargout = aaa(varargin)
% AAA MATLAB code for aaa.fig
%      AAA, by itself, creates a new AAA or raises the existing
%      singleton*.
%
%      H = AAA returns the handle to a new AAA or the handle to
%      the existing singleton*.
%
%      AAA('CALLBACK',hObject,eventData,handles,...) calls the local
%      function named CALLBACK in AAA.M with the given input arguments.
%
%      AAA('Property'.'Value',...). creates anew AAA or raises the
%      existing singleton*.  Starting from the left, property value pairs are
%      applied to the GUI before aaa_OpeningFcn gets called.  An
%      unrecognized property name or invalid value makes property application
%      stop.  All inputs are passed to aaa_OpeningFcn via varargin.
%
%      *See GUI Options on GUIDE's Tools menu.  Choose "GUI allows only one % instance to run (singleton)".
%
% See also: GUIDE, GUIDATA, GUIHANDLES

% Edit the above text to modify the response to help aaa

% Last Modified by GUIDE v2. 5 10-Jul- 2016. 21:47:39

% Begin initialization code - DO NOT EDIT
gui_Singleton = 1;
gui_State = struct('gui_Name',       mfilename, ...
                   'gui_Singleton',  gui_Singleton, ...
                   'gui_OpeningFcn', @aaa_OpeningFcn, ...
                   'gui_OutputFcn',  @aaa_OutputFcn, ...
                   'gui_LayoutFcn', [],...'gui_Callback'[]);if nargin && ischar(varargin{1})
    gui_State.gui_Callback = str2func(varargin{1});
end

if nargout
    [varargout{1:nargout}] = gui_mainfcn(gui_State, varargin{:});
else
    gui_mainfcn(gui_State, varargin{:});
end
% End initialization code - DO NOT EDIT
Copy the code

3. Operation results







Fourth, note

Version: 2014 a