- 前言
进行图片校正是将拍照倾斜的图片恢复水平状态，大致思路为：
- 用canny算子检测出图像中的边缘轮廓线；
- 用霍夫线变换检测出图像中的所有直线；
- 筛选出接近水平方向上的直线，求出他们偏移角度的平均值；
- 根据倾斜角旋转矫正；
- 输出图片。
这里设计到几个知识点：
canny算子
原理：数字图像处理(20): 边缘检测算子(Canny算子)
cv2.Canny函数：OpenCV-Python教程（8、Canny边缘检测）
edge = cv2.Canny(image, threshold1, threshold2[, edges[, apertureSize[, L2gradient ]]])
变量内容image要检测的图像
threshold1 和 threshold2 的值较小时，能够捕获更多的边缘信息，下文中canny_threshold(self, img_path)函数即可可视化不同threshold的效果。
霍夫变换
原理：霍夫变换——神奇的特征提取算法
cv2.HoughLines函数：每天一练P9-Python和OpenCV做图像处理(HoughLines)
其他
Python2 math.degrees() 函数
Python scipy.ndimage.rotate用法及代码示例（该函数是按逆时针旋转）
利用向量推导坐标旋转公式(方案一)
atctan
- 代码
在使用代码前，canny的阈值一定要根据实际情况修改！
import cv2
import math
import numpy as np
from scipy import ndimage
class HorizontalCorrection:
def __init__(self):
self.rotate_vector = np.array([0, 1])
self.rotate_theta = 0
def process(self, img):
img = cv2.imread(img)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray, 350, 400, apertureSize=3)
cv2.imwrite('./test result/edges.png', edges)
lines = cv2.HoughLines(edges, 1, np.pi / 180, 120)
sum = 0
count = 0
for i in range(len(lines)):
for rho, theta in lines[i]:
a = np.cos(theta)
b = np.sin(theta)
x0 = a * rho
y0 = b * rho
x1 = int(x0 + 1000 * (-b))
y1 = int(y0 + 1000 * (a))
x2 = int(x0 - 1000 * (-b))
y2 = int(y0 - 1000 * (a))
if x2 != x1:
t = float(y2 - y1) / (x2 - x1)
if t np.pi / 5 and t >= - np.pi / 5:
rotate_angle = math.degrees(math.atan(t))
sum += rotate_angle
count += 1
cv2.line(img, (x1, y1), (x2, y2), (0, 0, 255), 2)
if count == 0:
avg_rotate_angle = 0
else:
avg_rotate_angle = sum / count
self.rotate_img = ndimage.rotate(img, avg_rotate_angle)
self.rotate_theta = avg_rotate_angle
self.count_rotate_vector()
def count_rotate_vector(self):
v1_new = (self.rotate_vector[0] * np.cos(self.rotate_theta / 180)) - \
(self.rotate_vector[1] * np.sin(self.rotate_theta / 180))
v2_new = (self.rotate_vector[1] * np.cos(self.rotate_theta / 180)) + \
(self.rotate_vector[0] * np.sin(self.rotate_theta / 180))
self.rotate_vector = np.array([v1_new, v2_new])
def manual_set_rotate_vector(self, rotate_theta):
self.rotate_theta = rotate_theta
self.count_rotate_vector()
def canny_threshold(self, img_path):
img_original = cv2.imread(img_path)
cv2.namedWindow('Canny')
def nothing(x):
pass
cv2.createTrackbar('threshold1','Canny',50,400,nothing)
cv2.createTrackbar('threshold2','Canny',100,400,nothing)
while(1):
threshold1=cv2.getTrackbarPos('threshold1','Canny')
threshold2=cv2.getTrackbarPos('threshold2','Canny')
img_edges=cv2.Canny(img_original,threshold1,threshold2)
cv2.imshow('original',img_original)
cv2.imshow('Canny',img_edges)
if cv2.waitKey(1)==ord('q'):
break
cv2.destroyAllWindows()
if __name__ == '__main__':
horizontal_correction = HorizontalCorrection()
horizontal_correction.process(r'./test image/IMG_6386.JPG')
print(horizontal_correction.rotate_theta)
cv2.imwrite('./test result/1.png', horizontal_correction.rotate_img)
cv2.imshow('rotate', horizontal_correction.rotate_img)
cv2.waitKey()
- 效果图
从图中可以看出霍夫变换根据栏杆的水平线进行校正。
彩蛋：乾元的朋友，让我看见你们的双手。
; 补充——用滑动条调整canny阈值
之前在一个博客看到的，但是现在找不到了，先把代码放上。
def canny_threshold(self, img_path):
img_original = cv2.imread(img_path)
cv2.namedWindow('Canny')
def nothing(x):
pass
cv2.createTrackbar('threshold1', 'Canny', 50, 400, nothing)
cv2.createTrackbar('threshold2', 'Canny', 100, 400, nothing)
while True:
threshold1 = cv2.getTrackbarPos('threshold1', 'Canny')
threshold2 = cv2.getTrackbarPos('threshold2', 'Canny')
img_edges = cv2.Canny(img_original, threshold1, threshold2)
cv2.imshow('original', img_original)
cv2.imshow('Canny', img_edges)
if cv2.waitKey(1) == ord('q'):
break
cv2.destroyAllWindows()
其他
对 cv2.HoughLines返回值的处理方式进行了修改。
import cv2
import math
import numpy as np
from scipy import ndimage
class HorizontalCorrection:
def __init__(self):
self.rotate_vector = np.array([0, 1])
self.rotate_theta = 0
def process(self, img):
img = cv2.imread(img)
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
edges = cv2.Canny(gray, 350, 400, apertureSize=3)
cv2.imwrite('./test result/edges.png', edges)
lines = cv2.HoughLines(edges, 1, np.pi / 180, 120)
sum = 0
count = 0
for r_theta in lines:
arr = np.array(r_theta[0], dtype=np.float64)
rho, theta = arr
a = np.cos(theta)
b = np.sin(theta)
x0 = a * rho
y0 = b * rho
x1 = int(x0 + 1000 * (-b))
y1 = int(y0 + 1000 * (a))
x2 = int(x0 - 1000 * (-b))
y2 = int(y0 - 1000 * (a))
if x2 != x1:
t = float(y2 - y1) / (x2 - x1)
if t np.pi / 5 and t >= - np.pi / 5:
rotate_angle = math.degrees(math.atan(t))
sum += rotate_angle
count += 1
cv2.line(img, (x1, y1), (x2, y2), (0, 0, 255), 2)
if count == 0:
avg_rotate_angle = 0
else:
avg_rotate_angle = sum / count
self.rotate_img = ndimage.rotate(img, avg_rotate_angle)
self.rotate_theta = avg_rotate_angle
self.count_rotate_vector()
def count_rotate_vector(self):
v1_new = (self.rotate_vector[0] * np.cos(self.rotate_theta / 180)) - \
(self.rotate_vector[1] * np.sin(self.rotate_theta / 180))
v2_new = (self.rotate_vector[1] * np.cos(self.rotate_theta / 180)) + \
(self.rotate_vector[0] * np.sin(self.rotate_theta / 180))
self.rotate_vector = np.array([v1_new, v2_new])
def manual_set_rotate_vector(self, rotate_theta):
self.rotate_theta = rotate_theta
self.count_rotate_vector()
def canny_threshold(self, img_path):
img_original = cv2.imread(img_path)
cv2.namedWindow('Canny')
def nothing(x):
pass
cv2.createTrackbar('threshold1','Canny',50,400,nothing)
cv2.createTrackbar('threshold2','Canny',100,400,nothing)
while(1):
threshold1=cv2.getTrackbarPos('threshold1','Canny')
threshold2=cv2.getTrackbarPos('threshold2','Canny')
img_edges=cv2.Canny(img_original,threshold1,threshold2)
cv2.imshow('original',img_original)
cv2.imshow('Canny',img_edges)
if cv2.waitKey(1)==ord('q'):
break
cv2.destroyAllWindows()
if __name__ == '__main__':
horizontal_correction = HorizontalCorrection()
horizontal_correction.process(r'./test image/IMG_6386.JPG')
print(horizontal_correction.rotate_theta)
cv2.imwrite('./test result/1.png', horizontal_correction.rotate_img)
cv2.imshow('rotate', horizontal_correction.rotate_img)
cv2.waitKey()
Original: https://blog.csdn.net/weixin_42442319/article/details/124596103
Author: 橙橙小狸猫
Title: python 图片倾斜校正
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/518367/
转载文章受原作者版权保护。转载请注明原作者出处！