RPA中房产证的 OCR 识别
客户需求,识别一些证件内容,包括身份证、户口本、营业执照、银行卡以及房产证,前四个比较容易实现,不管是艺赛旗的 RPA 还是百度的 OCR 都有接口,直接调用即可,但是都没有房产证的 OCR 识别,只能自己使用其他 OCR 接口来进行相关操作了。
房产证如下图所示:
如果使用通用文字识别所有的文字都可以识别出来,但是顺序是乱的,所以我选择了使用通用文字识别(高精度含位置版),这样的话,我不仅可以识别到文字,还能知道文字所在的位置,然后根据文字位置进行区域划分,划分后的效果如下:
代码如下:
import base64
import copy
import re
import requests
class OCR(object):
# client_id 为官网获取的AK, client_secret 为官网获取的SK
client_id = ""
client_secret = ""
def get_token(self):
"""获取 access_token"""
host = 'https://aip.baidubce.com/oauth/2.0/token'
# 请求头
headers = {'Content-Type': 'application/json; charset=UTF-8'}
# 请求参数
params = {
"grant_type": "client_credentials",
"client_id": self.client_id,
"client_secret": self.client_secret
}
# get 请求
response = requests.get(host, headers=headers, params=params)
# 获取 json 内容
content = response.json()
# 获取 access_token
access_token = content["access_token"]
return access_token
def encode_img(self, img_path):
"""对图片进行编码"""
with open(img_path, "rb") as f:
img_content = f.read()
# 对图片进行 base64 编码
img_content = base64.b64encode(img_content)
return img_content
def img_to_str(self, img_path):
"""对图片文字进行识别"""
access_token = self.get_token()
# 请求 URL
URL = "https://aip.baidubce.com/rest/2.0/ocr/v1/accurate?access_token=" + access_token
# post 请求头
headers = {"Content-Type": "application/x-www-form-urlencoded"}
# post 参数
data = {
"image": self.encode_img(img_path),
"recognize_granularity": "big"
}
# post 请求
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 = ["证明权利或事项", "权利人(申请人)", "义务人", "坐落", "不动产单元号", "其他", "附记"]
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 "不动产证明" in words:
top_01 = top
height_01 = height
if "证明权利或事项" 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 处理
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 处理
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])
# 其他处理
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)
运行效果如下:
冀(2019)**市不动产证明第00***19号
{'证明权利或事项': '抵押权', '权利人(申请人)': '中国**************分行', '义务人': '***', '坐落': '路南区*************号', '不动产单元号': '130202*************0118', '附记': '业务编号:20190**20', '其他': '产权证书号:冀(2019)**市不动产权第00****2号;抵押物类型:土地和房屋;抵押方式:一般抵押;担保债权数额:60.00万元;债权起止时间:2019年10月24日起2049年10月24日止'}