Skew detection and correction in images containing text
Project description
Deskew
Note: Skew is measured in degrees. Deskewing is a process whereby skew is removed by rotating an image by the same amount as its skew but in the opposite direction. This results in a horizontally and vertically aligned image where the text runs across the page rather than at an angle.
The return angle is between -45 and 45 degrees to don't arbitrary change the image orientation.
By using the library you can set the argument angle_pm_90 to True to have an angle between -90 and 90 degrees.
Skew detection and correction in images containing text
Image with skew
Image after deskew
Cli usage
Get the skew angle:
deskew input.png
Deskew an image:
deskew --output output.png input.png
Lib usage
scikit-image:
import numpy as np
from skimage import io
from skimage.color import rgb2gray
from skimage.transform import rotate
from deskew import determine_skew
image = io.imread('input.png')
grayscale = rgb2gray(image)
angle = determine_skew(grayscale)
rotated = rotate(image, angle, resize=True) * 255
io.imsave('output.png', rotated.astype(np.uint8))
OpenCV:
import math
from typing import Tuple, Union
import cv2
import numpy as np
from deskew import determine_skew
def rotate(
image: np.ndarray, angle: float, background: Union[int, Tuple[int, int, int]]
) -> np.ndarray:
old_width, old_height = image.shape[:2]
angle_radian = math.radians(angle)
width = abs(np.sin(angle_radian) * old_height) + abs(np.cos(angle_radian) * old_width)
height = abs(np.sin(angle_radian) * old_width) + abs(np.cos(angle_radian) * old_height)
image_center = tuple(np.array(image.shape[1::-1]) / 2)
rot_mat = cv2.getRotationMatrix2D(image_center, angle, 1.0)
rot_mat[1, 2] += (width - old_width) / 2
rot_mat[0, 2] += (height - old_height) / 2
return cv2.warpAffine(image, rot_mat, (int(round(height)), int(round(width))), borderValue=background)
image = cv2.imread('input.png')
grayscale = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
angle = determine_skew(grayscale)
rotated = rotate(image, angle, (0, 0, 0))
cv2.imwrite('output.png', rotated)
Debug images
If you get wrong skew angle you can generate debug images, that can help you to tune the skewing detection.
If you install deskew with pip install deskew[debug_images] you can get some debug images used for
the skew detection with the function determine_skew_debug_images.
To start the investigation you should first increase the num_peaks (default 20) and use
the determine_skew_debug_images function.
Then you can try to tune the following arguments num_peaks, angle_pm_90, min_angle, max_angle,
min_deviation and eventually sigma.
Inspired by Alyn: https://github.com/kakul/Alyn
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file deskew-1.4.0.tar.gz.
File metadata
- Download URL: deskew-1.4.0.tar.gz
- Upload date:
- Size: 6.8 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.8.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 922b778fd1fd232bb1995130aafc45ee89725298d64dcc5cde647650c3ebbf65 |
|
| MD5 | 57d61a355960edc26149fa181f226982 |
|
| BLAKE2b-256 | 88ef4dce581d823bbfe440c7b759e54927c8f70697e2b377a1dd3fd6c0dfccf6 |
Provenance
File details
Details for the file deskew-1.4.0-py3-none-any.whl.
File metadata
- Download URL: deskew-1.4.0-py3-none-any.whl
- Upload date:
- Size: 7.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.8.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | a68b9125251680ee9f95dd769dd8a01d199c6c5f8627331e0c617ee2933f63ae |
|
| MD5 | f0f649de880556c1ec127427b46eb27a |
|
| BLAKE2b-256 | 7ed974a6a9432fb27f838bc7c7aba5e2611c7df0e2d5b5f032059f0cba0920de |
