Rotation correction of image by detecting text box based on text detection model

1. Rotate the image by 0 degrees, 22.5 degrees, 45 degrees, 67.5 degrees, and 90 degrees, and save these 5 pictures.
2. Use a (lightweight) text detection model to perform text detection on these 5 pictures.
3. Then select the angle with the largest long text box and the largest aspect ratio, as the approximate rotation angle judgment, and get the angle $\theta 1\in (0,22.5,45,67.5,90)$。
4. Using the text box obtained in the previous step, count the largest long side inclination angles of the text box to obtain the angle $\theta 2$。
5. Through $\theta 1$ and$\theta 2$ to rotate the original image.

The original image on the left, the corrected image on the right, use 0 padding around, and the corrected image detection text box is drawn on the top.