python - 如何在保留顺序的同时从图表图像中获取数据？

Question

我很少有这样的图片，

图 1:

图 2:

我可以使用像 Python 中的 tesseract 这样的 ocr 工具从这些图像中提取名称和角色，但我想在整个过程中保留层次结构。

请提供一些有趣的方法来解决这个问题。我想不出一种正确的方法来解决这个问题。

print(pytesseract.image_to_string(Image.open('test.png'))) 
import pytesseract# This returns the strings to me.

我想要任何数据类型的结构化形式的信息，比如，

For example, in chart 1, Erica is the CEO, and under Erica are Russell, David Work, and so on. 

Answer 1

结果可视化:

方法:

• 框边框和连接线(“网”)具有一定的颜色/亮度
• 使用蒙版、轮廓列表、标签图
• 计算重叠/交叉点
• 在重叠处，勾选哪些方框和哪些网络参与

为您提供的一张特定图片而写。另一个分辨率太低。

对于不太有利的输入数据，这需要进行调整。不过这应该不难。只是不同的阈值等等。

这也应该适用于非框节点(例如圆/椭圆)。

OCR部分你可以搞清楚。这种方法和代码为您提供了可以传递给 OCR 的各个框。

输出:

net 1 connects boxes [1, 2]
net 2 connects boxes [2, 3, 4, 5]
net 3 connects boxes [4, 6, 7, 8, 9, 10]
net 4 connects boxes [6, 11, 16, 21]
net 5 connects boxes [7, 12, 17, 22]
net 6 connects boxes [8, 13, 18, 23]
net 7 connects boxes [9, 14, 19, 24]
net 8 connects boxes [10, 15, 20, 25]

代码:

#!/usr/bin/env python3

import os
import sys
from math import *
import numpy as np
import cv2 as cv
import pprint
import collections

np.set_printoptions(suppress=True, linewidth=120)

########################################################################

im = cv.imread("9Rsju.jpg", cv.IMREAD_GRAYSCALE) / np.float32(255)

# optional downscale. easier to display.
im = cv.resize(im, fx=0.5, fy=0.5, dsize=None, interpolation=cv.INTER_AREA)

# generally, indices are 0..(N-1) and labels are 1..N and always (index+1) == label

########################################################################
# boxes

# select box borders
boxes_mask = (im <= 0.50) * np.uint8(255)
boxes_mask = cv.dilate(boxes_mask, kernel=None, iterations=1) # cover marginal pixels

(boxes_contours, _) = cv.findContours(
    image=boxes_mask,
    mode=cv.RETR_EXTERNAL,
    method=cv.CHAIN_APPROX_SIMPLE)

numboxes = len(boxes_contours)

# sort contours vertically
def valuation(contour):
    (x,y,w,h) = cv.boundingRect(contour)
    return y + x / 10 # "objective function"

# not vital, just pretty
boxes_contours.sort(key=valuation)

boxes_rects = [ cv.boundingRect(c) for c in boxes_contours ]

def bottom_of_rect(rect):
    (x,y,w,h) = rect
    return (x + w//2, y + h)

def top_of_rect(rect):
    (x,y,w,h) = rect
    return (x + w//2, y)

# boxes mask (fill inside of box)
cv.drawContours(
    boxes_mask,
    boxes_contours,
    contourIdx=-1,
    color=255,
    thickness=cv.FILLED)

# label map for boxes
boxes_labels = np.zeros_like(boxes_mask, dtype=np.uint8)
for (i, contour) in enumerate(boxes_contours):
    box_label = i+1
    cv.drawContours(
        boxes_labels,
        boxes_contours,
        contourIdx=i,
        color=box_label,
        thickness=cv.FILLED)


########################################################################
# connecting lines ("nets")

# select
nets_mask = (im >= 0.7) & (im <= 0.9) # 0.8 + margin
nets_mask = nets_mask * np.uint8(255)
nets_mask &= ~boxes_mask

# create slight overlap
nets_mask = cv.dilate(nets_mask, kernel=None, iterations=1)

# label map
(numnets, nets_labels) = cv.connectedComponents(nets_mask)


########################################################################
# connectivity

overlap = nets_mask & boxes_mask
(y,x) = overlap.nonzero() # pixel coordinates
relations = set(zip(nets_labels[y,x], boxes_labels[y,x]))

by_net = collections.defaultdict(lambda: set())
for (net,box) in relations:
    by_net[net].add(box)

for net_label, boxes in sorted(by_net.items()):
    print(f"net {net_label} connects boxes", sorted(boxes))


########################################################################
# visualization

canvas = cv.cvtColor(im * 0.5, cv.COLOR_GRAY2BGR)

for net_label, boxes in sorted(by_net.items()):
    boxes = sorted(boxes)

    headbox_label = boxes.pop(0)
    headbox_center = bottom_of_rect(boxes_rects[headbox_label-1])

    for box_label in boxes:
        box_center = top_of_rect(boxes_rects[box_label-1])

        cv.line(canvas,
            pt1=headbox_center,
            pt2=box_center,
            color=(0,0,255),
            thickness=2)

for (i, contour) in enumerate(boxes_contours):
    (x,y,w,h) = boxes_rects[i]

    cv.rectangle(canvas,
        pt1=(x,y), pt2=(x+w,y+h),
        color=(255,255,255),
        thickness=2)

    cv.putText(canvas,
        text=f"Box {i + 1}",
        org=(x+10, y+40),
        fontFace=cv.FONT_HERSHEY_SIMPLEX,
        fontScale=1,
        color=(255,255,255),
        thickness=2)


########################################################################
# display

cv.namedWindow("canvas", cv.WINDOW_NORMAL)
cv.imshow("canvas", canvas)

cv.waitKey(-1)
cv.destroyAllWindows()