取消装箱 opencv 矩形

Question

我正在对一堆 pdf 文件进行 OCR。这工作正常，但部分 pdf 是黑线的。其实，他们并不是真正的黑线而是'rectangled with some text within the rectangels'。即使在使用单词列表来定位“(10)(2e)”的各种组合时，这段文字也弄乱了我的 OCR。

我正在使用 .jpg 文件，它是从包含机器人文本和图像（其中包含文本）的 pdf 文件转换而来的。这是一个示例：

由于“(10)(2e)”的许多变体扰乱了我的 OCR，我的目标是找到所有矩形 - 最有可能包含“(10)(2e)”并填充它们。为了找到矩形，我遵循了 nathancy:

的这个很好的答案

但是 - 正如您在上面的绿色矩形中看到的 - 有时绿色矩形会与我需要的部分数据重叠。在这种情况下，第二行中的“@leiden.nl”和“@”。

我已经尝试了 (a) 图像处理的其他设置 (erode/dilate/blur/thershold) 和 (b) Nathancy 的答案中建议的其他设置的许多组合（内核 settings/number 迭代).

找到较小矩形的最佳做法是什么？

仅供参考：我查找矩形的代码或多或少类似于 Nathancy 的回答：

# 
import cv2

import os
path = os.getcwd()
print(path+'/test_ocr3/_stuff_IN/')

# Load iamge, grayscale, adaptive threshold
# image = cv2.imread(path+'/test_ocr3/_stuff_OUT/'+'1.png')
# image = cv2.imread(path+'/test_ocr3/_stuff_OUT/'+'page_1.jpg')
image = cv2.imread(path+'/test_ocr3/_stuff_OUT/'+'page_1_opt.jpg')
# image = cv2.imread(path+'/test_ocr3/_stuff_OUT/'+'page_1_A_erode_551.jpg')
# image = cv2.imread(path+'/test_ocr3/_stuff_OUT/'+'page_1_B_dilate_551.jpg')
# image = cv2.imread(path+'/test_ocr3/_stuff_OUT/'+'page_1_D_threshold_177255.jpg')
result = image.copy()
gray = cv2.cvtColor(image,cv2.COLOR_BGR2GRAY)
thresh = cv2.adaptiveThreshold(gray,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV,51,9)

# Fill rectangular contours
# CHECK OTHER CONTOUR SETTINGS ? TO EXLCUDE OUTER ?
# https://docs.opencv.org/master/d9/d8b/tutorial_py_contours_hierarchy.html
# https://medium.com/analytics-vidhya/opencv-findcontours-detailed-guide-692ee19eeb18
# cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cv2.findContours(thresh, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    cv2.drawContours(thresh, [c], -1, (255,255,255), -1)

# Morph open
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (30,4))
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=4)
# opening = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=4)

# Draw rectangles
# cnts = cv2.findContours(opening, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cv2.findContours(opening, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    x,y,w,h = cv2.boundingRect(c)
    cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), 3)
    # filled
    # cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), -1)
    
# cv2.imwrite(path+'/test_ocr3/_stuff_OUT/'+'1_OUT.png', image)
cv2.imwrite(path+'/test_ocr3/_stuff_OUT/'+'page_1_0_TST_OUT.jpg', image)

Answer 1

# 
import cv2
import os

path = os.getcwd()
print(path + '/test_ocr3/_stuff_IN/')

# Load iamge, grayscale, adaptive threshold
# image = cv2.imread(path+'/test_ocr3/_stuff_OUT/'+'1.png')
# image = cv2.imread(path+'/test_ocr3/_stuff_OUT/'+'page_1.jpg')
image = cv2.imread(path+'/test_ocr3/_stuff_OUT/'+'page_1_opt.jpg')
# image = cv2.imread(path+'/test_ocr3/_stuff_OUT/'+'page_1_A_erode_551.jpg')
# image = cv2.imread(path+'/test_ocr3/_stuff_OUT/'+'page_1_B_dilate_551.jpg')
# image = cv2.imread(path+'/test_ocr3/_stuff_OUT/'+'page_1_D_threshold_177255.jpg')
result = image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.adaptiveThreshold(gray, 255, cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY_INV, 51, 9)

# Fill rectangular contours
# CHECK OTHER CONTOUR SETTINGS ? TO EXLCUDE OUTER ?
# https://docs.opencv.org/master/d9/d8b/tutorial_py_contours_hierarchy.html
# https://medium.com/analytics-vidhya/opencv-findcontours-detailed-guide-692ee19eeb18
# cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cv2.findContours(thresh, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    cv2.drawContours(thresh, [c], -1, (255, 255, 255), -1)
    cv2.drawContours(thresh, [c], -1, (0, 0, 0), 1)

# Morph open
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (7, 4))
opening = cv2.morphologyEx(thresh, cv2.MORPH_OPEN, kernel, iterations=4)
# opening = cv2.morphologyEx(thresh, cv2.MORPH_CLOSE, kernel, iterations=4)

# Draw rectangles
# cnts = cv2.findContours(opening, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cv2.findContours(opening, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    x, y, w, h = cv2.boundingRect(c)
    cv2.rectangle(image, (x, y), (x + w, y + h), (36, 255, 12), 3)
    # filled
    # cv2.rectangle(image, (x, y), (x + w, y + h), (36,255,12), -1)

# cv2.imwrite(path+'/test_ocr3/_stuff_OUT/'+'1_OUT.png', image)
cv2.imwrite(path+'/test_ocr3/_stuff_OUT/'+'page_1_0_TST_OUT.jpg', image)

Modified binary 因为我没有更高分辨率的图像，所以我修改了图像。我用手擦掉了大框，并将边缘锐化为 1px（如果此图像不等于您的原始图像，请上传更高分辨率并更正。）。

重点是 cv2.drawContours(阈值, [c], -1, (0, 0, 0), 1) .这将一个大盒子（您想删除的盒子）分成小盒子。否则，连接区域将被识别为一个大框，这将删除不需要的信息。

image 2 compares Your question and My answer of large box. image 3 shows My answer.

取消装箱 opencv 矩形

Unboxing opencv rectangles

python

opencv

image-processing

hierarchical

contour