谷歌云视觉中使用python的逐行文本检测

Question

这是我使用的代码：

from http import client
import os, io
from google.cloud import vision
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = r'ServiceAccountToken.json'
client = vision.ImageAnnotatorClient()

def detectText(img):
with io.open(img,'rb') as image_file:
content = image_file.read()
image = vision.Image(content=content)
response = client.text_detection(image=image)
texts = response.text_annotations
texts = response.text_annotations[0].description
print(texts)

FILE_NAME = 'Scan_20220819.png'
FOLDER_NAME = r'C:UsersRafiAbrarDownloadsvision ai'
detectText(os.path.join(FOLDER_NAME, FILE_NAME))

输出为：

A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
Haemoglobin
ESR (Capillary Method - Alifax)
Total Count
Red Blood Cells
Platelets
White Blood Cells
Differential Count
Neutrophil
Lymphocyte
Monocyte
Eosinophil
Basophil
Red Cell Indices
P.C.V. (Hct)
M.C.V.
M.C.H.
M.C.H.C.
R.D.W.-C.V.
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
Result
11.5 g/dL
12 mm in 1st hour
3.7 X 10^12/L
257 X 10^9/L
8.0 X 10^9/L
62%
32 %
04%
02 %
00%
33%
88 fL
31 pg
35 g/dL
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
12.3%
+
Reference Value
F 11.5 - 15.5, M 13.5 - 18.0 g/dL
< 30 mm in 1st hour
F 3.8-4.8, M 4.5-5.5 X 0^12/L
150-450 X 10^9/L
04.00 11.00 X 10^9/L
40 - 75%
20 - 50 %
02-10%
01-06 %
<01 %
F: 36-46 %, M: 40 - 50 %
82 - 100 fl
27-32 pg
30-35 g/dL
11.60 14.00 %
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs
A lot of extra stuffs

未逐行检测到文本。

我期待着这样的结果："；参数"；(空格("；值"；(空格("；单位"；

类似：

Haemoglobin 11.5 g/dL
ESR 12 mm in 1st hour
RBC 3.7 X 10^12/L
..... and the list goes on

所以我要问的是：

1. 或者帮助我使用python逐行ocr文本
2. 或者帮助我为给定的输出找到一个合适的LOGIC(切片/循环/解析/任何东西(，在那里我可以将每个特定的测试报告参数与其相应的值合并

Answer 1

经过两天的努力，我使用字符串方法和列表制作了自己的版本。将我的GCV输出(带坐标(保存在一个文本文件中，并使用txt文件逐行对齐。

GCV代码：

from http import client
import os, io
from google.cloud import vision
import cv2
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = r'ServiceAccountToken.json'
client = vision.ImageAnnotatorClient()

def Detect_Text(img):
with io.open(img,'rb') as image_file:
content = image_file.read()
image = vision.Image(content=content)
# image2 = cv2.resize(image, (1080, 1920), interpolation=cv2.INTER_LINEAR)
response = client.text_detection(image=image)
# texts = response.text_annotations
texts = response.text_annotations
# print(texts)
for text in texts:
# print('=' * 30)
# print(text.description)
vertices = ['(%s,%s)' % (v.x, v.y) for v in text.bounding_poly.vertices]
# print('bounds:', ",".join(vertices), text.description)
print(" ".join(vertices), text.description, "*")

FILE_NAME = 'complex.png'
FOLDER_NAME = r'C:UsersRafiAbrarDownloadsvision ai'
Detect_Text(os.path.join(FOLDER_NAME, FILE_NAME))

逐行字符串对齐代码：

txt_file = open("test_str.txt", "r")
file_content = txt_file.read().upper()
# print(file_content)
for i in file_content[:]:
if "(" in i:
file_content = file_content.replace("(", "")
if ")" in i:
file_content = file_content.replace(")", "")
if "," in i:
file_content = file_content.replace(",", " ")
clean1 = file_content.split(" *n")
del clean1[0]
# print(clean1)
empty_list = []
for i in clean1[:]:
# print(i)
clean2 = i.split(" ")
# print(clean2)
empty_list.append(clean2)
for i in empty_list[:]:
del i[2:8]
for i in empty_list[:]:
if i[0].lstrip("-").isdigit():
i[0] = int(i[0])
if i[1].lstrip("-").isdigit():
i[1] = int(i[1])
empty_list.sort(key=lambda x:x[1])
# for i in empty_list:
#     print(i)
list1 = []
# # for k in range(200):
while len(empty_list) > 0:
list2 = []
for i in empty_list[:]:
if len(list2) == 0:
list2.append(i)
if i in empty_list[:]:
empty_list.remove(i)
else:
for j in list2[:]:
if abs(i[1] - j[1]) <= 15: # change this "15" if output not correct
list2.append(i)
list2[:] = list(map(list, set(map(tuple, list2))))
if i in empty_list[:]:
empty_list.remove(i)
list2.sort()
# empty_list.sort(key=lambda x: x[0])
list1.append(list2)
del list2
print(list1)
# full_txt = []
# full_txt2 = []
for i in list1[:]:
for j in i:
print("".join(j[2:]), end=" ")

只要图像不太歪斜，输出对我来说就行。图像分辨率可能会导致一些问题，最好将分辨率转换为1700*2350 px