105 lines
3.2 KiB
Python
105 lines
3.2 KiB
Python
import cv2
|
|
import numpy as np
|
|
from pdf2image import pdf2image
|
|
|
|
from vidocp.utils import show_mpl, draw_rectangles, remove_included
|
|
|
|
|
|
def is_large_enough(cont, min_area=10000):
|
|
return cv2.contourArea(cont, False) > min_area
|
|
|
|
|
|
def has_acceptable_format(cont, max_width_to_hight_ratio=6):
|
|
_, _, w, h = cv2.boundingRect(cont)
|
|
return max_width_to_hight_ratio >= w / h >= (1 / max_width_to_hight_ratio)
|
|
|
|
|
|
def is_likely_figure(cont, min_area=5000, max_width_to_hight_ratio=6):
|
|
return is_large_enough(cont, min_area) and has_acceptable_format(cont, max_width_to_hight_ratio)
|
|
|
|
|
|
def remove_primary_text_regions(image):
|
|
"""Removes regions of primary text, meaning no figure descriptions for example, but main text body paragraphs.
|
|
|
|
Args:
|
|
image: Image to remove primary text from.
|
|
|
|
Returns:
|
|
Image with primary text removed.
|
|
|
|
References:
|
|
https://stackoverflow.com/questions/58349726/opencv-how-to-remove-text-from-background
|
|
"""
|
|
|
|
def filter_likely_primary_text_segments(cnts):
|
|
for c in cnts:
|
|
area = cv2.contourArea(c)
|
|
if 800 < area < 15000:
|
|
yield cv2.boundingRect(c)
|
|
|
|
image = image.copy()
|
|
|
|
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
|
|
|
|
thresh = cv2.threshold(gray, 253, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
|
|
|
|
close_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (20, 3))
|
|
close = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, close_kernel, iterations=1)
|
|
|
|
dilate_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (5, 3))
|
|
dilate = cv2.dilate(close, dilate_kernel, iterations=1)
|
|
|
|
cnts, _ = cv2.findContours(dilate, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
|
|
|
|
for rect in filter_likely_primary_text_segments(cnts):
|
|
x, y, w, h = rect
|
|
cv2.rectangle(image, (x, y), (x + w, y + h), (255, 255, 255), -1)
|
|
|
|
return image
|
|
|
|
|
|
def __detect_large_coherent_structures(image: np.array):
|
|
"""Detects large coherent structures on an image.
|
|
|
|
References:
|
|
https://stackoverflow.com/questions/60259169/how-to-group-nearby-contours-in-opencv-python-zebra-crossing-detection
|
|
"""
|
|
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
|
|
|
|
thresh = cv2.threshold(gray, 253, 255, cv2.THRESH_BINARY)[1]
|
|
|
|
dilate_kernel = cv2.getStructuringElement(cv2.MORPH_OPEN, (5, 5))
|
|
dilate = cv2.dilate(~thresh, dilate_kernel, iterations=4)
|
|
|
|
close_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (20, 20))
|
|
close = cv2.morphologyEx(dilate, cv2.MORPH_CLOSE, close_kernel, iterations=1)
|
|
|
|
cnts, _ = cv2.findContours(close, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
|
|
|
|
return cnts
|
|
|
|
|
|
def detect_figures(image: np.array):
|
|
|
|
image = image.copy()
|
|
|
|
image = remove_primary_text_regions(image)
|
|
cnts = __detect_large_coherent_structures(image)
|
|
|
|
cnts = filter(is_likely_figure, cnts)
|
|
rects = map(cv2.boundingRect, cnts)
|
|
rects = remove_included(rects)
|
|
|
|
return rects
|
|
|
|
|
|
def detect_figures_in_pdf(pdf_path, page_index=1):
|
|
|
|
page = pdf2image.convert_from_path(pdf_path, first_page=page_index + 1, last_page=page_index + 1)[0]
|
|
page = np.array(page)
|
|
|
|
redaction_contours = detect_figures(page)
|
|
page = draw_rectangles(page, redaction_contours)
|
|
|
|
show_mpl(page)
|