这是一种确定两个图像之间旋转偏移的方法（以度为单位）。这个想法是找到每个图像相对于水平线的倾斜角度。如果我们能找到这个倾斜的角度，那么我们就可以计算出两幅图像之间的角度差。这里有一些示例图片来说明这个概念
原始未旋转图像
逆时针旋转 10 度 (neg_10) 和逆时针旋转 35 度 (neg_35)
顺时针旋转 7.9 度 (pos_7_9) 和顺时针旋转 21 度 (pos_21)
对于每张图像，我们想要确定相对于水平线的倾斜角度，负值逆时针旋转，正值顺时针旋转
这是确定倾斜角度的辅助函数
def compute_angle(image):
# Convert to grayscale, invert, and Otsu's threshold
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = 255 - gray
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
# Find coordinates of all pixel values greater than zero
# then compute minimum rotated bounding box of all coordinates
coords = np.column_stack(np.where(thresh > 0))
angle = cv2.minAreaRect(coords)[-1]
# The cv2.minAreaRect() function returns values in the range
# [-90, 0) so need to correct angle
if angle < -45:
angle = -(90 + angle)
else:
angle = -angle
# Rotate image to horizontal position
(h, w) = image.shape[:2]
center = (w // 2, h // 2)
M = cv2.getRotationMatrix2D(center, angle, 1.0)
rotated = cv2.warpAffine(image, M, (w, h), flags=cv2.INTER_CUBIC, \
borderMode=cv2.BORDER_REPLICATE)
return (angle, rotated)
确定每张图像的倾斜角度后，我们可以简单地计算差异
angle1, rotated1 = compute_angle(image1)
angle2, rotated2 = compute_angle(image2)
# Both angles are positive
if angle1 >= 0 and angle2 >= 0:
difference_angle = abs(angle1 - angle2)
# One positive, one negative
elif (angle1 < 0 and angle2 > 0) or (angle1 > 0 and angle2 < 0):
difference_angle = abs(angle1) + abs(angle2)
# Both negative
elif angle1 < 0 and angle2 < 0:
angle1 = abs(angle1)
angle2 = abs(angle2)
difference_angle = max(angle1, angle2) - min(angle1, angle2)
这是正在发生的事情的分步介绍。使用pos_21 和neg_10，compute_angle() 函数将返回倾斜角度和归一化图像
对于pos_21，我们对图像进行归一化并确定倾斜角度。左（前）->右（后）
20.99871826171875
与neg_10 类似，我们也对图像进行归一化并确定倾斜角度。左（前）->右（后）
-10.007980346679688
现在我们有两个角度，我们可以计算差角。这是结果
31.006698608398438
这是其他组合的结果。使用neg_10 和neg_35 我们得到
24.984039306640625
使用pos_7_9 和pos_21，
13.09155559539795
最后是pos_7_9和neg_35，
42.89918231964111
这是完整的代码
import cv2
import numpy as np
def rotational_shift(image1, image2):
def compute_angle(image):
# Convert to grayscale, invert, and Otsu's threshold
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = 255 - gray
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
# Find coordinates of all pixel values greater than zero
# then compute minimum rotated bounding box of all coordinates
coords = np.column_stack(np.where(thresh > 0))
angle = cv2.minAreaRect(coords)[-1]
# The cv2.minAreaRect() function returns values in the range
# [-90, 0) so need to correct angle
if angle < -45:
angle = -(90 + angle)
else:
angle = -angle
# Rotate image to horizontal position
(h, w) = image.shape[:2]
center = (w // 2, h // 2)
M = cv2.getRotationMatrix2D(center, angle, 1.0)
rotated = cv2.warpAffine(image, M, (w, h), flags=cv2.INTER_CUBIC, \
borderMode=cv2.BORDER_REPLICATE)
return (angle, rotated)
angle1, rotated1 = compute_angle(image1)
angle2, rotated2 = compute_angle(image2)
# Both angles are positive
if angle1 >= 0 and angle2 >= 0:
difference_angle = abs(angle1 - angle2)
# One positive, one negative
elif (angle1 < 0 and angle2 > 0) or (angle1 > 0 and angle2 < 0):
difference_angle = abs(angle1) + abs(angle2)
# Both negative
elif angle1 < 0 and angle2 < 0:
angle1 = abs(angle1)
angle2 = abs(angle2)
difference_angle = max(angle1, angle2) - min(angle1, angle2)
return (difference_angle, rotated1, rotated2)
if __name__ == '__main__':
image1 = cv2.imread('pos_7_9.png')
image2 = cv2.imread('neg_35.png')
angle, rotated1, rotated2 = rotational_shift(image1, image2)
print(angle)