问题
I’d like to rotate fingerprint image from skew to vertical center
By python with opencv
I’m beginner.
From this
To this
回答1:
Given an image containing a rotated blob at an unknown angle, the skew can be corrected with this approach
- Detect blob in the image
- Compute angle of rotated blob
- Rotate the image to correct skew
To detect the blob in the image, we convert to grayscale and adaptive threshold to obtain a binary image
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = 255 - gray
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
Next we compute the angle of the rotated blob using cv2.minAreaRect() and calculate the skew angle
# Compute rotated bounding box
coords = np.column_stack(np.where(thresh > 0))
angle = cv2.minAreaRect(coords)[-1]
if angle < -45:
angle = -(90 + angle)
else:
angle = -angle
print(angle)
43.72697067260742
Finally we apply an affine transformation to correct the skew
# Rotate image to deskew
(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)
Here's the result
import cv2
import numpy as np
image = cv2.imread('1.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = 255 - gray
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
# Compute rotated bounding box
coords = np.column_stack(np.where(thresh > 0))
angle = cv2.minAreaRect(coords)[-1]
if angle < -45:
angle = -(90 + angle)
else:
angle = -angle
print(angle)
# Rotate image to deskew
(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)
cv2.imshow('thresh', thresh)
cv2.imshow('rotated', rotated)
cv2.waitKey()
来源：https://stackoverflow.com/questions/57713358/how-to-rotate-skewed-fingerprint-image-to-vertical-upright-position