总目录
图像处理总目录←点击这里
七、图像梯度
7.1、图像梯度-Sobel算子
原图
直接计算
不建议这么算
sobelxy=cv2.Sobel(img,cv2.CV_64F,1,1,ksize=3)
sobelxy = cv2.convertScaleAbs(sobelxy)
cv_show(sobelxy,'sobelxy')
分别计算——合并
当前位置的像素值等于sobel算子与(当前位置与周边位置8个点)进行对应位置相乘并相加操作,作为当前位置的像素点
G
x
=
(
−
1
0
+
1
−
2
0
+
2
−
1
0
+
1
)
∗
(
p
1
p
2
p
3
p
4
p
5
p
6
p
7
p
8
p
9
)
=
(
p
3
−
p
1
)
+
(
2
p
6
−
2
p
4
)
+
(
p
9
−
p
7
)
G_x=\left( \begin{matrix} -1& 0& +1\\ -2& 0& +2\\ -1& 0& +1\\ \end{matrix} \right) *\left( \begin{matrix} p_1& p_2& p_3\\ p_4& p_5& p_6\\ p_7& p_8& p_9\\ \end{matrix} \right) =\left( p_3-p_1 \right) +\left( 2p_6-2p_4 \right) +\left( p_9-p_7 \right)
Gx=⎝⎛−1−2−1000+1+2+1⎠⎞∗⎝⎛p1p4p7p2p5p8p3p6p9⎠⎞=(p3−p1)+(2p6−2p4)+(p9−p7)
dst = cv2.Sobel(src, ddepth, dx, dy, ksize)
- ddepth:图像的深度(有可能负数,
cv2.convertScaleAbs
解决) - dx和dy分别表示水平和竖直方向
- ksize是Sobel算子的大小(一般3X3)
Gx (右边减左边)cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3)
中1,0为取Gx
deep可能有负值,白到黑是正数,黑到白就是负数了,所有的负数会被截断成0,效果如下
img = cv2.imread('./image/pie.png',cv2.IMREAD_GRAYSCALE)
def cv_show(img,name):
cv2.imshow(name,img)
cv2.waitKey()
cv2.destroyAllWindows()
sobelx = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3)
cv_show(sobelx,'sobelx')
deep的值要取绝对值cv2.convertScaleAbs
,效果如下
sobelx = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3)
sobelx = cv2.convertScaleAbs(sobelx)
cv_show(sobelx,'sobelx')
Gy(下面减上面)cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3)
中为0,1为
sobely = cv2.Sobel(img,cv2.CV_64F,0,1,ksize=3)
sobely = cv2.convertScaleAbs(sobely)
cv_show(sobely,'sobely')
Gx和Gy求和
sobelxy = cv2.addWeighted(sobelx,0.5,sobely,0.5,0)
cv_show(sobelxy,'sobelxy')
应用
原图
img = cv2.imread('./image/lena.jpg',cv2.IMREAD_GRAYSCALE)
cv_show(img,'img')
Sobel算子,轮廓效果
img = cv2.imread('./image/lena.jpg',cv2.IMREAD_GRAYSCALE)
sobelx = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3)
sobelx = cv2.convertScaleAbs(sobelx)
sobely = cv2.Sobel(img,cv2.CV_64F,0,1,ksize=3)
sobely = cv2.convertScaleAbs(sobely)
sobelxy = cv2.addWeighted(sobelx,0.5,sobely,0.5,0)
cv_show(sobelxy,'sobelxy')
7.2、图像梯度-Scharr算子
cv2.Scharr(src, ddepth, dx, dy, ksize)
- ddepth:图像的深度(有可能负数,
cv2.convertScaleAbs
解决) - dx和dy分别表示水平和竖直方向
- ksize是Sobel算子的大小(一般3X3)
img = cv2.imread('lena.jpg',cv2.IMREAD_GRAYSCALE)
scharrx = cv2.Scharr(img,cv2.CV_64F,1,0)
scharry = cv2.Scharr(img,cv2.CV_64F,0,1)
scharrx = cv2.convertScaleAbs(scharrx)
scharry = cv2.convertScaleAbs(scharry)
scharrxy = cv2.addWeighted(scharrx,0.5,scharry,0.5,0)
cv_show(scharrxy,'scharrxy')
7.3、图像梯度-laplacian算子
cv2.Scharr(src, ddepth, ksize)
- ddepth:图像的深度(有可能负数,
cv2.convertScaleAbs
解决) - ksize是Sobel算子的大小(一般3X3)
laplacian = cv2.Laplacian(img,cv2.CV_64F)
laplacian = cv2.convertScaleAbs(laplacian)
cv_show(laplacian,'laplacian')
7.4、图像梯度-对比
#不同算子的差异
img = cv2.imread('./image/lena.jpg',cv2.IMREAD_GRAYSCALE)
sobelx = cv2.Sobel(img,cv2.CV_64F,1,0,ksize=3)
sobely = cv2.Sobel(img,cv2.CV_64F,0,1,ksize=3)
sobelx = cv2.convertScaleAbs(sobelx)
sobely = cv2.convertScaleAbs(sobely)
sobelxy = cv2.addWeighted(sobelx,0.5,sobely,0.5,0)
scharrx = cv2.Scharr(img,cv2.CV_64F,1,0)
scharry = cv2.Scharr(img,cv2.CV_64F,0,1)
scharrx = cv2.convertScaleAbs(scharrx)
scharry = cv2.convertScaleAbs(scharry)
scharrxy = cv2.addWeighted(scharrx,0.5,scharry,0.5,0)
laplacian = cv2.Laplacian(img,cv2.CV_64F)
laplacian = cv2.convertScaleAbs(laplacian)
res = np.hstack((sobelxy,scharrxy,laplacian))
cv_show(res,'res')