客戶需求,識別一些證件內容,包括身份證、戶口本、營業執照、銀行卡以及房產證,前四個比較容易實現,無論是藝賽旗的 RPA 仍是百度的 OCR 都有接口,直接調用便可,可是都沒有房產證的 OCR 識別,只能本身使用其餘 OCR 接口來進行相關操做了。
房產證以下圖所示:
json
若是使用通用文字識別全部的文字均可以識別出來,可是順序是亂的,因此我選擇了使用通用文字識別(高精度含位置版),這樣的話,我不只能夠識別到文字,還能知道文字所在的位置,而後根據文字位置進行區域劃分,劃分後的效果以下:app
代碼以下:
import base64
import copy
import re
import requests
class OCR(object):
# client_id 爲官網獲取的AK, client_secret 爲官網獲取的SK
client_id = ""
client_secret = ""
def get_token(self):
"""獲取 access_token"""
host = 'https://aip.baidubce.com/oauth/2.0/token'
# 請求頭
headers = {'Content-Type': 'application/json; charset=UTF-8'}
# 請求參數
params = {
"grant_type": "client_credentials",
"client_id": self.client_id,
"client_secret": self.client_secret
}
# get 請求
response = requests.get(host, headers=headers, params=params)
# 獲取 json 內容
content = response.json()
# 獲取 access_token
access_token = content["access_token"]
return access_token
def encode_img(self, img_path):
"""對圖片進行編碼"""
with open(img_path, "rb") as f:
img_content = f.read()
# 對圖片進行 base64 編碼
img_content = base64.b64encode(img_content)
return img_content
def img_to_str(self, img_path):
"""對圖片文字進行識別"""
access_token = self.get_token()
# 請求 URL
URL = "https://aip.baidubce.com/rest/2.0/ocr/v1/accurate?access_token=" + access_token
# post 請求頭
headers = {"Content-Type": "application/x-www-form-urlencoded"}
# post 參數
data = {
"image": self.encode_img(img_path),
"recognize_granularity": "big"
}
# post 請求
response = requests.post(URL, headers=headers, data=data)
return response.json()
if __name__ == '__main__':
ocr = OCR()
img = "./imgs/fcz_01.jpg"
str_json = ocr.img_to_str(img)
my_str_list = str_json["words_result"]
my_title = ["證實權利或事項", "權利人(申請人)", "義務人", "坐落", "不動產單元號", "其餘", "附記"]
column_line = 999999999
my_word_list = []
for data in my_str_list:
my_list = []
words = data["words"]
width = data["location"]["width"]
top = data["location"]["top"]
left = data["location"]["left"]
height = data["location"]["height"]
my_list.append(words)
my_list.append(width)
my_list.append(top)
my_list.append(left)
my_list.append(height)
my_word_list.append(my_list)
if "不動產證實" in words:
top_01 = top
height_01 = height
if "證實權利或事項" in words:
top_02 = top
if words in my_title:
column_line = left + width if left + width < column_line else column_line
row_line = (top_01 + top_02 + height) / 2
head_list = []
left_list = []
right_list = []
for data in my_word_list:
if data[0] in my_title:
continue
if data[2] < row_line:
head_list.append(data)
elif data[3] < column_line:
for i in my_title:
data[0] = re.sub(i, "", data[0])
right_list.append(data)
else:
right_list.append(data)
# head 處理
head_dict = {}
left = 0
for data in head_list:
head_dict[data[3]] = data[0]
# 排序
head_dict = sorted(head_dict.items(), key=lambda x: x[0])
head_str = ""
for data in head_dict:
head_str += data[1]
print(head_str)
# right 處理
right_dict = {}
other_list = copy.deepcopy(right_list)
for i in range(len(my_title) - 2):
right_dict[my_title[i]] = right_list[i][0]
other_list.remove(right_list[i])
right_dict[my_title[-1]] = right_list[-1][0]
other_list.remove(right_list[-1])
# 其餘處理
other_str = ""
for data in other_list:
if ":" in data[0]:
other_str += ";"
other_str += data[0]
right_dict[my_title[-2]] = other_str[1:]
print(right_dict)
運行效果以下:
冀(2019)**市不動產證實第00***19號
{'證實權利或事項': '抵押權', '權利人(申請人)': '中國**************分行', '義務人': '***', '坐落': '路南區*************號', '不動產單元號': '130202*************0118', '附記': '業務編號:20190**20', '其餘': '產權證書號:冀(2019)**市不動產權第00****2號;抵押物類型:土地和房屋;抵押方式:通常抵押;擔保債權數額:60.00萬元;債權起止時間:2019年10月24日起2049年10月24日止'}post