各向异性canny边缘检测matlab代码

以下是各向异性Canny边缘检测的MATLAB代码：

function [E] = anisotropic_canny(I, sigma, tlow, thigh)
% I: 输入图像
% sigma: 高斯滤波器的标准差
% tlow: 低阈值（可以根据具体情况调整）
% thigh: 高阈值（可以根据具体情况调整）

% 高斯滤波
G = fspecial('gaussian', max(1, fix(6*sigma)), sigma);
I_smooth = imfilter(I, G, 'replicate');

% 计算图像梯度
Ix = imfilter(I_smooth, [-1 0 1], 'replicate');
Iy = imfilter(I_smooth, [-1;0;1], 'replicate');

% 计算梯度的幅值和方向
G = sqrt(Ix.^2 + Iy.^2);
theta = atan2(Iy, Ix) * 180/pi;

% 非极大值抑制
Gnms = zeros(size(G));
for i = 2:size(G, 1)-1
    for j = 2:size(G, 2)-1
        if (theta(i,j) >= -22.5 && theta(i,j) < 22.5) || (theta(i,j) < -157.5 && theta(i,j) >= -180) || (theta(i,j) >= 157.5 && theta(i,j) < 180)
            if (G(i,j) > G(i,j-1)) && (G(i,j) > G(i,j+1))
                Gnms(i,j) = G(i,j);
            end
        elseif (theta(i,j) >= 22.5 && theta(i,j) < 67.5) || (theta(i,j) < -112.5 && theta(i,j) >= -157.5)
            if (G(i,j) > G(i-1,j+1)) && (G(i,j) > G(i+1,j-1))
                Gnms(i,j) = G(i,j);
            end
        elseif (theta(i,j) >= 67.5 && theta(i,j) < 112.5) || (theta(i,j) < -67.5 && theta(i,j) >= -112.5)
            if (G(i,j) > G(i-1,j)) && (G(i,j) > G(i+1,j))
                Gnms(i,j) = G(i,j);
            end
        elseif (theta(i,j) >= 112.5 && theta(i,j) < 157.5) || (theta(i,j) < -22.5 && theta(i,j) >= -67.5)
            if (G(i,j) > G(i-1,j-1)) && (G(i,j) > G(i+1,j+1))
                Gnms(i,j) = G(i,j);
            end
        end
    end
end

% 双阈值处理
E = zeros(size(Gnms));
E(Gnms > thigh) = 1;
E(Gnms > tlow & Gnms <= thigh) = 0.5;

% 边缘连接
for i = 2:size(E, 1)-1
    for j = 2:size(E, 2)-1
        if (E(i,j) == 0.5)
            if (E(i-1,j-1) == 1 || E(i-1,j) == 1 || E(i-1,j+1) == 1 || E(i,j-1) == 1 || E(i,j+1) == 1 || E(i+1,j-1) == 1 || E(i+1,j) == 1 || E(i+1,j+1) == 1)
                E(i,j) = 1;
            end
        end
    end
end

% 返回最终结果
E = logical(E);
end

该代码实现了各向异性Canny边缘检测算法，其中使用了高斯滤波器对输入图像进行平滑处理，计算了图像的梯度幅值和方向，进行了非极大值抑制和双阈值处理，并最后进行了边缘连接。可以根据具体情况调整高斯滤波器的标准差和阈值参数。