资源简介
这个css代码是我下载别人的,是非常好的一个角点检测算法。
代码片段和文件信息
function [coutmarked_img]=corner(varargin)
% CORNER Find corners in intensity image.
%
% CORNER works by the following step:
% 1. Apply the Canny edge detector to the gray level image and obtain a
% binary edge-map.
% 2. Extract the edge contours from the edge-map fill the gaps in the
% contours.
% 3. Compute curvature at a low scale for each contour to retain all
% true corners.
% 4. All of the curvature local maxima are considered as corner
% candidates then rounded corners and false corners due to boundary
% noise and details were eliminated.
% 5. End points of line mode curve were added as corner if they are not
% close to the above detected corners.
%
% Syntax :
% [coutmarked_img]=corner(ICT_anglesigHLEndpiontGap_size)
%
% Input :
% I - the input image it could be gray color or binary image. If I is
% empty([]) input image can be get from a open file dialog box.
% C - denotes the minimum ratio of major axis to minor axis of an ellipse
% whose vertex could be detected as a corner by proposed detector.
% The default value is 1.5.
% T_angle - denotes the maximum obtuse angle that a corner can have when
% it is detected as a true corner default value is 162.
% Sig - denotes the standard deviation of the Gaussian filter when
% computeing curvature. The default sig is 3.
% HL - high and low threshold of Canny edge detector. The default value
% is 0.35 and 0.
% Endpoint - a flag to control whether add the end points of a curve
% as corner 1 means Yes and 0 means No. The default value is 1.
% Gap_size - a paremeter use to fill the gaps in the contours the gap
% not more than gap_size were filled in this stage. The default
% Gap_size is 1 pixels.
%
% Output :
% cout - a position pair list of detected corners in the input image.
% marked_image - image with detected corner marked.
%
% Examples
% -------
% I = imread(‘alumgrns.tif‘);
% cout = corner(I[][][]0.2);
%
% [cout marked_image] = corner;
%
% cout = corner([]1.6155);
%
%
% Composed by He Xiaochen
% HKU EEE Dept. ITSR Apr. 2005
%
% Algorithm is derived from :
% X.C. He and N.H.C. Yung “Curvature Scale Space Corner Detector with
% Adaptive Threshold and Dynamic Region of Support” Proceedings of the
% 17th International Conference on Pattern Recognition 2:791-794 August 2004.
% Improved algorithm is included in “A Corner Detector based on Global and Local
% Curvature Properties”and submitted to Pattern Recognition.
[ICT_anglesigHLEndpointGap_size] = parse_inputs(varargin{:});
if size(I3)==3
I=rgb2gray(I); % Transform RGB image to a Gray one.
end
tic
BW
属性 大小 日期 时间 名称
----------- --------- ---------- ----- ----
文件 1707 2000-01-22 12:00 Corner\b.gif
文件 1745 2000-01-22 12:00 Corner\c.gif
文件 13922 2006-01-24 14:24 Corner\corner.m
文件 1426 2000-01-22 12:00 Corner\d.gif
文件 1759 2000-01-22 12:00 Corner\e.gif
文件 1879 2000-01-22 12:00 Corner\f.gif
文件 1916 2000-01-22 12:00 Corner\g.gif
文件 19024 2005-05-10 16:46 Corner\gui_corner.fig
文件 8565 2005-05-10 16:54 Corner\gui_corner.m
文件 66568 2003-10-17 05:43 Corner\house.bmp
文件 2182 2006-01-17 17:45 Corner\h.gif
文件 2139 2000-01-22 12:00 Corner\a.gif
文件 1196 2007-10-12 19:02 Corner\readme.txt
文件 9603 2007-10-12 19:03 Corner\edge.jpg
文件 10900 2007-10-12 19:03 Corner\corner.jpg
文件 336 2007-10-12 19:03 Corner\cout.mat
..A.SH. 40448 2008-06-17 20:22 Corner\Thumbs.db
目录 0 2007-10-12 19:01 Corner
----------- --------- ---------- ----- ----
185315 18
评论
共有 条评论