Python 使用 OpenCV 从扫描的 struct 化纸张表格的 jpg 中检测所有矩形和轮廓

我设法想出了如何捕获此表单中的所有矩形/框.正如塞姆贝在上面的 comments 中提到的那样，100，所以对于我的特殊挑战来说，图像配准可能不是最有效的方法.

我对这一挑战的解决方案是通过以下步骤得出的:

1. 对图像进行预处理，go 除灰度阴影区域. 这是在下面的代码段中实现的，其中图像首先被锐化，然后灰色背景被移除.

说

sharpen_kernel = np.array([[-1,-1,-1], [-1,9,-1], [-1,-1,-1]])
sharpened = cv2.filter2D(img, -1, sharpen_kernel)


hsv = cv2.cvtColor(sharpened.copy(), cv2.COLOR_BGR2HSV)
mask_grey = cv2.inRange(hsv, (0, 0, 100), (255, 5, 255))


# Build mask of non black pixels.
nzmask = cv2.inRange(hsv, (0, 0, 5), (255, 255, 255))

# Erode the mask - all pixels around a black pixels should not be masked.
nzmask = cv2.erode(nzmask, np.ones((3,3)))
mask_grey = mask_grey & nzmask


cleaned_bg_img = img.copy()
cleaned_bg_img[np.where(mask_grey)] = 255

cleaned_bg_img = cv2.cvtColor(cleaned_bg_img.copy(), cv2.COLOR_BGR2RGB)
gray = cv2.cvtColor(cleaned_bg_img, cv2.COLOR_BGR2GRAY) 

说

结果如下图所示(对比问题中的图1以对比差异)

2. 在遍历所识别的等高线时，假设并非所有所识别的等高线的形状都将变为矩形，因此，不是仅将循环限制为长度约为4的等高线，而是捕获长度为4或更大的所有等高线，然后使用cv2.boundingRect的等高线作为结果

说

epsilon = 0.01 * cv2.arcLength(contour, True)
x,y,w,h = cv2.boundingRect(contour) 
area = cv2.contourArea(contour)
approx = cv2.approxPolyDP(contour, epsilon, True)

if len(approx) > 3 and area > 3000 :
    #if the shape size is rectangular (or polygon: document not scanned perfectly)
    #if area is > 3000 to weed out small rectangles on characters/checkboxes.
    
    working_image = cv2.rectangle(cleaned_bg_img,(x,y),(x+w,y+h),(0,255,0),2) 

说

这些更改的最终结果如下图所示.虽然问题图2中的结果确定了88个字段/框，但这些更改使我能够确定100 102个字段/框.

下面提供了可能希望使用此方法从 struct 化纸质记录中识别字段/框的任何人的最终代码片段.我希望这个解决方案对任何有类似挑战的人都有帮助.此外，我们非常欢迎任何可用于表格 struct 化格式的变体！

import cv2
import imutils
import warnings
import numpy as np

warnings.filterwarnings('ignore')

import matplotlib.pyplot as plt

img = cv2.imread("example.jpg") 

sharpen_kernel = np.array([[-1,-1,-1], [-1,9,-1], [-1,-1,-1]])
sharpened = cv2.filter2D(img, -1, sharpen_kernel)


hsv = cv2.cvtColor(sharpened.copy(), cv2.COLOR_BGR2HSV)
mask_grey = cv2.inRange(hsv, (0, 0, 100), (255, 5, 255))


# Build mask of non black pixels.
nzmask = cv2.inRange(hsv, (0, 0, 5), (255, 255, 255))

# Erode the mask - all pixels around a black pixels should not be masked.
nzmask = cv2.erode(nzmask, np.ones((3,3)))
mask_grey = mask_grey & nzmask


cleaned_bg_img = img.copy()
cleaned_bg_img[np.where(mask_grey)] = 255

cleaned_bg_img = cv2.cvtColor(cleaned_bg_img.copy(), cv2.COLOR_BGR2RGB)
gray = cv2.cvtColor(cleaned_bg_img, cv2.COLOR_BGR2GRAY)


threshold = cv2.adaptiveThreshold(
    gray.copy(), 
    255, # maximum value assigned to pixel values exceeding the threshold
    cv2.ADAPTIVE_THRESH_GAUSSIAN_C,  # gaussian weighted sum of neighborhood
    cv2.THRESH_BINARY_INV,  # thresholding type 
    301, # block size (5x5 window)
    11) # constant


font = cv2.FONT_HERSHEY_COMPLEX
# find the largest bounded rectangle from the contours
keypoints = cv2.findContours(threshold.copy(), 
                             cv2.RETR_CCOMP, 
                             cv2.CHAIN_APPROX_SIMPLE)
contours = imutils.grab_contours(keypoints)
working_image = None
idx = 1
cropped_field_images = []

# the following code section ensures we read the rectangles from 
# the top of the page, not bottom

contour_list = list(contours)
contour_list.reverse()
rev_contours = tuple(contour_list)

for contour in rev_contours:   
    
    epsilon = 0.01 * cv2.arcLength(contour, True)
    
    x,y,w,h = cv2.boundingRect(contour) 
    area = cv2.contourArea(contour)
    approx = cv2.approxPolyDP(contour, epsilon, True)
    location = None
    if len(approx) > 3 and area > 3000 : 
        # if the shape size is rect/polygon: document not scanned perfectly)
        # if area is >3000 to weed out small rectangles on characters/checkboxes etc.
        working_image = cv2.rectangle(cleaned_bg_img,(x,y),(x+w,y+h),(0,255,0),2)    

        cv2.putText(cleaned_bg_img, str(idx), (x, y), font, 1, (0,0,255))
        
        location = approx
        mask = np.zeros(gray.shape, np.uint8) #Create a blank mask
        rect_img = cv2.drawContours(mask, [location], 0, 255, -1) #Draw our contours for the specific location
        rect_img = cv2.bitwise_and(cleaned_bg_img, cleaned_bg_img, mask = mask) #Overlay the mask with the image
        
        (x, y) = np.where(mask==255)
        (x1, y1) = (np.min(x), np.min(y))
        (x2, y2) = (np.max(x), np.max(y))
        cropped_rect = gray[x1:x2+1, y1:y2+1]
        
        cropped_field_images.append(cropped_rect)
        
        
        idx += 1
    
plt.figure(figsize = (11.69*2,8.27*2))
plt.axis('off')
plt.imshow(cv2.cvtColor(working_image, cv2.COLOR_BGR2RGB));