Revert "replace usages of `imutils` with opencv equivalents"

pull/147/head
vahidrezanezhad 4 days ago committed by GitHub
parent c9de578d4d
commit f756b08c9b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

@ -4,6 +4,7 @@ import matplotlib.pyplot as plt
import numpy as np
from shapely import geometry
import cv2
import imutils
from scipy.signal import find_peaks
from scipy.ndimage import gaussian_filter1d
import time

@ -1,5 +1,6 @@
import math
import numpy as np
import imutils
import cv2
def rotatedRectWithMaxArea(w, h, angle):
@ -10,11 +11,11 @@ def rotatedRectWithMaxArea(w, h, angle):
side_long, side_short = (w, h) if width_is_longer else (h, w)
# since the solutions for angle, -angle and 180-angle are all the same,
# it suffices to look at the first quadrant and the absolute values of sin,cos:
# if suffices to look at the first quadrant and the absolute values of sin,cos:
sin_a, cos_a = abs(math.sin(angle)), abs(math.cos(angle))
if side_short <= 2.0 * sin_a * cos_a * side_long or abs(sin_a - cos_a) < 1e-10:
# half constrained case: two crop corners touch the longer side,
# the other two corners are on the mid-line parallel to the longer line
# half constrained case: two crop corners touch the longer side,
# the other two corners are on the mid-line parallel to the longer line
x = 0.5 * side_short
wr, hr = (x / sin_a, x / cos_a) if width_is_longer else (x / cos_a, x / sin_a)
else:
@ -24,45 +25,6 @@ def rotatedRectWithMaxArea(w, h, angle):
return wr, hr
def rotate_image_opencv(image, angle):
# Calculate the original image dimensions (h, w) and the center point (cx, cy)
h, w = image.shape[:2]
cx, cy = (w // 2, h // 2)
# Compute the rotation matrix
M = cv2.getRotationMatrix2D((cx, cy), angle, 1.0)
# Calculate the new bounding box
corners = np.array([
[0, 0],
[w, 0],
[w, h],
[0, h]
])
# Apply rotation matrix to the corner points
ones = np.ones(shape=(len(corners), 1))
corners_ones = np.hstack([corners, ones])
transformed_corners = M @ corners_ones.T
transformed_corners = transformed_corners.T
# Calculate the new bounding box dimensions
min_x, min_y = np.min(transformed_corners, axis=0)
max_x, max_y = np.max(transformed_corners, axis=0)
newW = int(np.ceil(max_x - min_x))
newH = int(np.ceil(max_y - min_y))
# Adjust the rotation matrix to account for translation
M[0, 2] += (newW / 2) - cx
M[1, 2] += (newH / 2) - cy
# Perform the affine transformation (rotation)
rotated_image = cv2.warpAffine(image, M, (newW, newH))
return rotated_image
def rotate_max_area_new(image, rotated, angle):
wr, hr = rotatedRectWithMaxArea(image.shape[1], image.shape[0], math.radians(angle))
h, w, _ = rotated.shape
@ -73,7 +35,7 @@ def rotate_max_area_new(image, rotated, angle):
return rotated[y1:y2, x1:x2]
def rotation_image_new(img, thetha):
rotated = rotate_image_opencv(img, thetha)
rotated = imutils.rotate(img, thetha)
return rotate_max_area_new(img, rotated, thetha)
def rotate_image(img_patch, slope):
@ -82,10 +44,13 @@ def rotate_image(img_patch, slope):
M = cv2.getRotationMatrix2D(center, slope, 1.0)
return cv2.warpAffine(img_patch, M, (w, h), flags=cv2.INTER_CUBIC, borderMode=cv2.BORDER_REPLICATE)
def rotate_image_different(img, slope):
def rotate_image_different( img, slope):
# img = cv2.imread('images/input.jpg')
num_rows, num_cols = img.shape[:2]
rotation_matrix = cv2.getRotationMatrix2D((num_cols / 2, num_rows / 2), slope, 1)
return cv2.warpAffine(img, rotation_matrix, (num_cols, num_rows))
img_rotation = cv2.warpAffine(img, rotation_matrix, (num_cols, num_rows))
return img_rotation
def rotate_max_area(image, rotated, rotated_textline, rotated_layout, rotated_table_prediction, angle):
wr, hr = rotatedRectWithMaxArea(image.shape[1], image.shape[0], math.radians(angle))
@ -97,17 +62,17 @@ def rotate_max_area(image, rotated, rotated_textline, rotated_layout, rotated_ta
return rotated[y1:y2, x1:x2], rotated_textline[y1:y2, x1:x2], rotated_layout[y1:y2, x1:x2], rotated_table_prediction[y1:y2, x1:x2]
def rotation_not_90_func(img, textline, text_regions_p_1, table_prediction, thetha):
rotated = rotate_image_opencv(img, thetha)
rotated_textline = rotate_image_opencv(textline, thetha)
rotated_layout = rotate_image_opencv(text_regions_p_1, thetha)
rotated_table_prediction = rotate_image_opencv(table_prediction, thetha)
rotated = imutils.rotate(img, thetha)
rotated_textline = imutils.rotate(textline, thetha)
rotated_layout = imutils.rotate(text_regions_p_1, thetha)
rotated_table_prediction = imutils.rotate(table_prediction, thetha)
return rotate_max_area(img, rotated, rotated_textline, rotated_layout, rotated_table_prediction, thetha)
def rotation_not_90_func_full_layout(img, textline, text_regions_p_1, text_regions_p_fully, thetha):
rotated = rotate_image_opencv(img, thetha)
rotated_textline = rotate_image_opencv(textline, thetha)
rotated_layout = rotate_image_opencv(text_regions_p_1, thetha)
rotated_layout_full = rotate_image_opencv(text_regions_p_fully, thetha)
rotated = imutils.rotate(img, thetha)
rotated_textline = imutils.rotate(textline, thetha)
rotated_layout = imutils.rotate(text_regions_p_1, thetha)
rotated_layout_full = imutils.rotate(text_regions_p_fully, thetha)
return rotate_max_area_full_layout(img, rotated, rotated_textline, rotated_layout, rotated_layout_full, thetha)
def rotate_max_area_full_layout(image, rotated, rotated_textline, rotated_layout, rotated_layout_full, angle):
@ -118,3 +83,4 @@ def rotate_max_area_full_layout(image, rotated, rotated_textline, rotated_layout
x1 = w // 2 - int(wr / 2)
x2 = x1 + int(wr)
return rotated[y1:y2, x1:x2], rotated_textline[y1:y2, x1:x2], rotated_layout[y1:y2, x1:x2], rotated_layout_full[y1:y2, x1:x2]

Loading…
Cancel
Save