Spaces:
Sleeping
Sleeping
File size: 2,821 Bytes
1f72938 9312707 e029c8d 1f72938 9312707 1f72938 9312707 1f72938 9312707 1f72938 e029c8d 1f72938 e029c8d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 |
from model1 import model1
from model2 import model2
import checkTool as ct
import extract_pdf as pf
import extraction_data as ed
import get_chinese_name as cn
import search_engine as se
# get info from hkid card
def string_similarity(s1, s2): # Levenshtein distance algorithm
s1 = s1.replace(' ', '')
s1 = s1.lower()
s2 = s2.replace(' ', '')
s2 = s2.lower()
if s1 == s2:
return 100.0
len1 = len(s1)
len2 = len(s2)
matrix = [[0] * (len2 + 1) for _ in range(len1 + 1)]
for i in range(len1 + 1):
matrix[i][0] = i
for j in range(len2 + 1):
matrix[0][j] = j
for i in range(1, len1 + 1):
for j in range(1, len2 + 1):
if s1[i - 1] == s2[j - 1]:
cost = 0
else:
cost = 1
matrix[i][j] = min(matrix[i - 1][j] + 1, # deletion
matrix[i][j - 1] + 1, # insertion
matrix[i - 1][j - 1] + cost) # substitution
similarity = (1 - matrix[len1][len2] / max(len1, len2)) * 100
return round(similarity, 1)
def get_data(img1_path, img2_path):
# img_fp = 'IMG_4495.jpg'
info1 = model1(img1_path)
info2 = model2(img1_path)
def print_info(name, valid_hkid, hkid, issuedate):
print(f'Name: {name}') # name is without space
print(f'HKID: {hkid} and validity: {valid_hkid}')
print(f'Date of issue: {issuedate}')
cinfo = ct.combine_info(info1, info2)
# get info from bank
# images = r'hangseng_page-0001.jpg'
# bank_list = ['bankofchina','hangsengbank','hsbc','sc']
# image_path = 'hangseng_page-0001.jpg'
# post_url = r''
# name = pf.get_info_from_bank(img2_path)
# name = pf.check_mr(name)
# name = name.replace(' ', '')
# name = name.lower()
# data = pf.get_info_from_bank(img2_path, file_name)
data = ed.get_info_from_bank(img2_path)
name = data["nameStatement"]
############# Similarity check ##############
# img_fp = 'IMG_1234.jpg'
name1 = cinfo[0]
threshold = 85
# print(f'Name in HKID: {name1}')
# print(f'Nmae in bank statement: {name}')
similarity_score = string_similarity(name,name1)
# print(f'Similarity: {similarity_score}')
# if (similarity_score >= threshold): # Above threshold
# print('It is the same person')
# else: # Below threshold
# print('It is not the same person')
data["similarity_score"] = similarity_score
data["name_on_id"] = name1
data["hkid"] = cinfo[2]
data["validity"] = cinfo[1]
data["issue_date"] = cinfo[3]
# Search Engine
# chi_name = cn.get_chiname(img1_path)["Chinese Name"]
chi_name = "allen lau"
data["chi_name_id"] = chi_name
return data
|