diff --git a/.env b/.env
new file mode 100644
index 0000000000000000000000000000000000000000..0f0d13d37036fa844a11cb0489a07f41bafebcbe
--- /dev/null
+++ b/.env
@@ -0,0 +1,2 @@
+api_key = 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiJnb29nbGUtb2F1dGgyfDExNjY1NDE1MzQ0MDY1NjEzNTI5MSIsImVtYWlsIjoic2hhaHphaW5oYWlkZXJuYXF2aUBnbWFpbC5jb20iLCJlbWFpbF92ZXJpZmllZCI6dHJ1ZSwiaWF0IjoxNjg1MDAxMjgzMDExfQ.Fb5ODO7KUchlLnrK0KBvSR4pkfIAfYiECRVWXj44RTQ'
+queue_id = 'c0f9e6f8-73d0-42f9-bd4f-700bdf002c04'
\ No newline at end of file
diff --git a/.gitattributes b/.gitattributes
index c7d9f3332a950355d5a77d85000f05e6f45435ea..409be2039650102c902192e630dba5afc84b5cd7 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -32,3 +32,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+app/images/idcards/IMG_20221130_180809.jpg filter=lfs diff=lfs merge=lfs -text
+app/images/idcards/ShahzainCNIC.jpg filter=lfs diff=lfs merge=lfs -text
+app/images/idcards/aadhaar[[:space:]]backside[[:space:]]image .jpg filter=lfs diff=lfs merge=lfs -text
+app/images/idcards/aadhaar[[:space:]]frontside[[:space:]]image.jpg filter=lfs diff=lfs merge=lfs -text
+app/images/idcards/d.jpg filter=lfs diff=lfs merge=lfs -text
+app/images/idcards/driving[[:space:]]licence[[:space:]]backside[[:space:]]image.jpg filter=lfs diff=lfs merge=lfs -text
+app/images/idcards/driving[[:space:]]licence[[:space:]]frontside[[:space:]]image.jpg filter=lfs diff=lfs merge=lfs -text
+app/images/idcards/front.jpg filter=lfs diff=lfs merge=lfs -text
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..93de3958d909678c150c49292601ced1cbd17b5b
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+__pycache__/app.cpython-38.pyc
+*pyc
\ No newline at end of file
diff --git a/README.md b/README.md
index c585085a1790450c6a8792b01d1fac5ec35574a1..215dcbe0fddf6bc72bd94728c269ec18b3fee24c 100644
--- a/README.md
+++ b/README.md
@@ -1,12 +1,6 @@
 ---
 title: OCR
-emoji: 🌖
-colorFrom: yellow
-colorTo: pink
+app_file: deploy.py
 sdk: gradio
 sdk_version: 3.33.1
-app_file: app.py
-pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
diff --git a/__pycache__/gradio.cpython-38.pyc b/__pycache__/gradio.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..e51e36f9d521b4c3f38a96ba255fd1b23cae174f
Binary files /dev/null and b/__pycache__/gradio.cpython-38.pyc differ
diff --git a/app/.gitignore b/app/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..6043b92b0e9b7cb473b1928ca327a3f2bd8ae2c7
--- /dev/null
+++ b/app/.gitignore
@@ -0,0 +1,4 @@
+images/*
+output/*
+*.pyc
+.vscode
\ No newline at end of file
diff --git a/app/__pycache__/app.cpython-38.pyc b/app/__pycache__/app.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..cec0fdc52fd2b71e581bfcb2f26dcbd3b8b2de98
Binary files /dev/null and b/app/__pycache__/app.cpython-38.pyc differ
diff --git a/app/app.py b/app/app.py
new file mode 100644
index 0000000000000000000000000000000000000000..2be56149911e218f3df2e8f31f5f5f776a754123
--- /dev/null
+++ b/app/app.py
@@ -0,0 +1,64 @@
+from fastapi import FastAPI
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi import FastAPI, File, UploadFile
+from app.extract_country.country_dictionary import find_country
+from app.extract_dates.date_engine import date_extractor
+from app.extract_gender.gender_extractor import gender_extract
+from app.extract_identity_number.doc_number_extractor import doc_number
+from app.ocr_engine.ocr import OCR
+from paddleocr import PaddleOCR
+from app.layoutLM_api.api import custom_ocr
+
+app = FastAPI() 
+
+origins = ["*"] 
+
+
+@app.post('/extract_info')
+async def ocr(Id_card: UploadFile = File(...)):
+
+    ocr = PaddleOCR(use_angle_cls=True, lang='en') # need to run only once to download and load model into memory
+    
+    file_path = 'app/images/idcards/input.jpg'
+
+    with open(file_path, "wb+") as file_object:
+        file_object.write(Id_card.file.read())
+    
+    dictionary = custom_ocr(file_path)
+
+    if '' in list(dictionary.values()):
+        print("Missing value found in Dic")
+        
+        extract_text = []
+        result = ocr.ocr(file_path, cls=True)
+
+        extract_text = [line[1][0] for res in result for line in res]
+        print("extract_text", extract_text)
+
+        if len(dictionary['gender']) == 0:
+            print("Gender Missing")
+            gender_found, gender, ocr_list = gender_extract(extract_text)
+            
+            dictionary["gender"] = gender if gender_found else None
+
+        if len(dictionary['dob']) == 0:
+            print("Dob Missing")
+            dob_found, dob, ocr_list = date_extractor(extract_text)
+
+            dictionary["dob"] = dob if dob_found else None
+
+        if len(dictionary['country']) == 0:
+            print("Country Missing")
+            country_found, country, ocr_list = find_country(extract_text)
+            dictionary["country"] = country if country_found else None
+
+        if len(dictionary['document_number']) == 0:
+            print("document Number missing")
+
+            document_number_found, document_number, ocr_list = doc_number(extract_text)
+            dictionary["document_number"] = document_number if document_number_found else None
+
+
+    print("Updated Dict ",dictionary)
+    response = {"Status" : 200, "OCR" : dictionary}  
+    return response
\ No newline at end of file
diff --git a/app/constants/__pycache__/paths.cpython-38.pyc b/app/constants/__pycache__/paths.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..874239e8aa74f617e9e957f8d43f534f4cd2d5e1
Binary files /dev/null and b/app/constants/__pycache__/paths.cpython-38.pyc differ
diff --git a/app/constants/paths.py b/app/constants/paths.py
new file mode 100644
index 0000000000000000000000000000000000000000..3e7420f955f54a238e14ee3ea32ad533bba46a3d
--- /dev/null
+++ b/app/constants/paths.py
@@ -0,0 +1,2 @@
+IMAGE_PATH = 'app/images/idcards/front.jpg'
+EXTRACTED_MRZ_PATH = "output/mrz_image.jpg"
\ No newline at end of file
diff --git a/app/constants/regex_expressions.py b/app/constants/regex_expressions.py
new file mode 100644
index 0000000000000000000000000000000000000000..ba40e706001c52d49909e93ed65420d47ea6407a
--- /dev/null
+++ b/app/constants/regex_expressions.py
@@ -0,0 +1 @@
+DATA_PATTERN = r"\b\d{2}\.\d{2}\.\d{4}\b"
\ No newline at end of file
diff --git a/app/custome.py b/app/custome.py
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/app/extract_country/__pycache__/country_dictionary.cpython-38.pyc b/app/extract_country/__pycache__/country_dictionary.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..a2122ee358fc3f212cb0712020ee7f7dc5a860dd
Binary files /dev/null and b/app/extract_country/__pycache__/country_dictionary.cpython-38.pyc differ
diff --git a/app/extract_country/__pycache__/country_extract.cpython-38.pyc b/app/extract_country/__pycache__/country_extract.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..3708fd5eec4978cb32226feb31967261bf13bf31
Binary files /dev/null and b/app/extract_country/__pycache__/country_extract.cpython-38.pyc differ
diff --git a/app/extract_country/__pycache__/country_validator.cpython-38.pyc b/app/extract_country/__pycache__/country_validator.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..df751a5ce660e1496890facea0d2a32b34950962
Binary files /dev/null and b/app/extract_country/__pycache__/country_validator.cpython-38.pyc differ
diff --git a/app/extract_country/country_dictionary.py b/app/extract_country/country_dictionary.py
new file mode 100644
index 0000000000000000000000000000000000000000..4f690d1d5fe04b9c3507eb3638ce3b5502b536fe
--- /dev/null
+++ b/app/extract_country/country_dictionary.py
@@ -0,0 +1,44 @@
+country_data = {
+    'PAKISTAN' : ['PAK', 'PAKISTAN'],
+    'SWITZERLAND' : ['SCHWEIZERISCHE EIDGENOSSENSCHAFT', 'CONFEDERATION SUISSE', 'CONFEDERAZIONESVIZZERA', 'CONFEDERAZIUN SVIZRA', 'SWISS CONFEDERATION'],
+    'INDIA' : ['INDIA', 'Government of India'],
+    'GERMANY' : ['Bundesrepublik Deutschland','Germany', 'Westdeutschland' , 'Ostdeutschland'],
+    'BANGLADESH' : ['Bangladesh'],
+    'UNITED KINGDOM' : ['British Citizen', 'UNITED KINGDOM'],
+    'NETHERLANDS' : ['NETHERLANDS', 'NEDERLANDSE', 'NEDERLANDEN'],
+    'CANADA' : ['canada'],
+    'UNITED ARAB EMIRATES' : ['Arab Emirates', 'UAE'],
+    'OMAN' : ['OMAN'],
+    'JORDAN' : ['jordan'],
+    'BAHRAIN' : ['BAHRAIN'],
+    'KUWAIT' : ['KUWAIT'],
+    'QATAR' : ['Qatar'],
+    'LIBYA' : ['AFRiN MAHALLi MECLiSi'],
+    'SOUTH SUDAN' : ['Akon'],
+    'CHILLE' : ['DECHILE'],
+    'COLOMBIA' : ['COLOMBIA'],
+    'BRAZIL' : ['BRAZIL', 'BRASIL'],
+    'PERU' : ['DELPERU', 'CASADO'],
+    'URUGUAY' : ['DELURUGUAY'],
+    'Coasta Rica' : ['COSTARICA'],
+    'PARAGUAY' : ['PARAGUAY'],
+    'ECUADOR' : ['ECUADOR'],
+    'GUATEMALA' : ['GUATEMALA'],
+    'Bolivia' : ['Bolivariano', 'Bolivia'],
+    'El Salvador' : ['Salvador'],
+    'Dominican Republic' : ['REPUBLICADOMINICANA']
+}
+
+def find_country(ocr_list):
+    try:
+        for word_from_ocr_list in ocr_list:
+            word_normalized = word_from_ocr_list.upper()
+            for key, values in country_data.items():
+                for value in values:    
+                    if value.upper() in word_normalized:
+                        return True, key, ocr_list
+        else:
+            return False, None, ocr_list
+    except Exception as e:
+        print(f"An error occurred: {e}")
+        return False, None, ocr_list
\ No newline at end of file
diff --git a/app/extract_country/country_extract.py b/app/extract_country/country_extract.py
new file mode 100644
index 0000000000000000000000000000000000000000..8f1182f524f361162e78964912dbc3a4117f4535
--- /dev/null
+++ b/app/extract_country/country_extract.py
@@ -0,0 +1,23 @@
+from extract_country.country_validator import extract_country_name
+
+
+def country_extractor(ocr_list):
+    try:
+        country_found = False
+        country = None
+
+        result_string = ' '.join(string for string in ocr_list)
+        words = result_string.split()
+
+        for index,word in enumerate(words):
+            country_found, country_name = extract_country_name(word)
+            if country_found:
+                country_found = True
+                country = country_name
+                break
+
+        return country_found, country, ocr_list
+        
+    except Exception as e:
+        print("[Exception in country_extractor ] ", str(e))
+        return country_found, country, ocr_list
\ No newline at end of file
diff --git a/app/extract_country/country_validator.py b/app/extract_country/country_validator.py
new file mode 100644
index 0000000000000000000000000000000000000000..3b36b0b40b9fe72c836a78e5d67795274d46e682
--- /dev/null
+++ b/app/extract_country/country_validator.py
@@ -0,0 +1,15 @@
+import pycountry
+import re
+
+def extract_country_name(string):
+    pattern = r"\b[A-Za-z ]+\b"  # Matches any sequence of letters and spaces
+    matches = re.findall(pattern, string)
+    for match in matches:
+        try:
+            country = pycountry.countries.lookup(match)
+            print("COUNTRY : ",country.name)
+            return True, country.name
+        except LookupError:
+            pass
+    return False, None
+
diff --git a/app/extract_dates/__pycache__/date_engine.cpython-38.pyc b/app/extract_dates/__pycache__/date_engine.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..6eb6c127a66886016dcb839d1ca0962603b05fb0
Binary files /dev/null and b/app/extract_dates/__pycache__/date_engine.cpython-38.pyc differ
diff --git a/app/extract_dates/__pycache__/validate_date.cpython-38.pyc b/app/extract_dates/__pycache__/validate_date.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..21bb23035f584cf8e0de85b71c6eba6b9acfc0ec
Binary files /dev/null and b/app/extract_dates/__pycache__/validate_date.cpython-38.pyc differ
diff --git a/app/extract_dates/date_engine.py b/app/extract_dates/date_engine.py
new file mode 100644
index 0000000000000000000000000000000000000000..72ca2735ce6022f199fcc19013360e1f96beabf0
--- /dev/null
+++ b/app/extract_dates/date_engine.py
@@ -0,0 +1,34 @@
+from app.extract_dates.validate_date import find_smallest_date, validate_date
+
+
+def date_extractor(ocr_list):
+    try:
+        global dob_found
+        dob_found = False
+        dob = None
+        dates_list = []
+
+        for index,word in enumerate(ocr_list):
+            date_valid ,pattern = validate_date(word)
+            if date_valid:
+                # valid_pattern = pattern
+                ocr_list.pop(index) # removing elements from list that is being used.
+                dates_list.append(word)
+
+        if dates_list:
+            # print(dates_list)
+            dob = find_smallest_date(dates_list) # smallest date will be DOB
+            dob_found = True
+
+            print("DATE OF BIRTH : ", dob)
+        else:
+            print("Date not found")
+            dob_found = False
+            dob = ''
+        
+        return dob_found, dob, ocr_list
+        
+    except Exception as e:
+        print("[Exception in date_extractor] : ", str(e))
+        dob = ''
+        return dob_found, dob, ocr_list
\ No newline at end of file
diff --git a/app/extract_dates/validate_date.py b/app/extract_dates/validate_date.py
new file mode 100644
index 0000000000000000000000000000000000000000..8c5bceaff10a081e06e6ada098747c0e83b11efd
--- /dev/null
+++ b/app/extract_dates/validate_date.py
@@ -0,0 +1,21 @@
+import re
+from dateutil import parser
+
+def find_smallest_date(dates):
+    parsed_dates = [parser.parse(date) for date in dates]
+    smallest_date = min(parsed_dates)
+    print(smallest_date.strftime('%d-%m-%Y'))
+    return smallest_date.strftime('%d-%m-%Y')
+
+def validate_date(date_string):
+    patterns = [
+        r'^\d{2}/\d{2}/\d{4}$',    # MM/DD/YYYY
+        r'^\d{2}-\d{2}-\d{4}$',    # DD-MM-YYYY
+        r'^\d{2}.\d{2}.\d{4}$'    # DD.MM.YYYY 
+    ]
+
+    for pattern in patterns:
+        if re.match(pattern, date_string):
+            return True, pattern
+
+    return False, pattern
diff --git a/app/extract_gender/__pycache__/gender_extractor.cpython-38.pyc b/app/extract_gender/__pycache__/gender_extractor.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..a05b1253abe042ccb54c376ba1cdc53e39129730
Binary files /dev/null and b/app/extract_gender/__pycache__/gender_extractor.cpython-38.pyc differ
diff --git a/app/extract_gender/gender_extractor.py b/app/extract_gender/gender_extractor.py
new file mode 100644
index 0000000000000000000000000000000000000000..ce2946177a040fa801ffcd1a0aec737b9d16fc4e
--- /dev/null
+++ b/app/extract_gender/gender_extractor.py
@@ -0,0 +1,26 @@
+gender_labels = ["M","MALE", "F", "FEMALE", "V/F","N/F","FEMENINO","MASCULINA"]
+
+def gender_extract(ocr_list):
+    try:
+        for words in ocr_list:
+            for word in words.split(): 
+                word = word.upper()
+                if word in gender_labels:
+                    return True, word, ocr_list
+                elif "FEMALE" in word:
+                    gender = 'F'
+                    return True, gender, ocr_list
+                elif "MALE" in word:
+                    gender = 'M'
+                    return True, gender, ocr_list
+                elif "FEMENINO" in word:
+                    gender = "F"
+                    return True, gender, ocr_list
+                elif "MASCULINA" in word:
+                    gender = "M"
+                    return True, gender, ocr_list
+                
+        return False, None, ocr_list
+    except Exception as e:
+        print("[Exception in gender_extract] ", str(e))
+        return None, None, ocr_list
\ No newline at end of file
diff --git a/app/extract_identity_number/__pycache__/doc_number_extractor.cpython-38.pyc b/app/extract_identity_number/__pycache__/doc_number_extractor.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..3d889f798e2737209838acd62f09c3e634d753d9
Binary files /dev/null and b/app/extract_identity_number/__pycache__/doc_number_extractor.cpython-38.pyc differ
diff --git a/app/extract_identity_number/__pycache__/identity_number.cpython-38.pyc b/app/extract_identity_number/__pycache__/identity_number.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..c56b7202a67dca44d6bb7c6d0358d38c89474224
Binary files /dev/null and b/app/extract_identity_number/__pycache__/identity_number.cpython-38.pyc differ
diff --git a/app/extract_identity_number/doc_number_extractor.py b/app/extract_identity_number/doc_number_extractor.py
new file mode 100644
index 0000000000000000000000000000000000000000..ae31dd633d266769ce81fb1c08b50860df7c2f7b
--- /dev/null
+++ b/app/extract_identity_number/doc_number_extractor.py
@@ -0,0 +1,13 @@
+import re
+
+def doc_number(ocr_list):
+    try:
+
+        for item in ocr_list:
+            if (len(item) >= 6 and item[0].isnumeric() ) or (len(item) >= 6 and (item[0].isalpha() and item[1].isnumeric())):
+                print("DOCUMENT NUMBRE IS : ", item)
+                return True, item, ocr_list    
+        return False, None, ocr_list
+    except Exception as e:
+        print("Exception in doc_number : " ,str(e))
+        return False, None, ocr_list
\ No newline at end of file
diff --git a/app/extract_identity_number/identity_number.py b/app/extract_identity_number/identity_number.py
new file mode 100644
index 0000000000000000000000000000000000000000..8bfe18af487360fa82ae512376fadbb67b986272
--- /dev/null
+++ b/app/extract_identity_number/identity_number.py
@@ -0,0 +1,2 @@
+def identity_card_extractor(ocr_list):
+    pass
\ No newline at end of file
diff --git a/app/extract_mrz/__pycache__/mrz_detect.cpython-38.pyc b/app/extract_mrz/__pycache__/mrz_detect.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..d4a170c105efa39ba4bc2f95399934a4c3422956
Binary files /dev/null and b/app/extract_mrz/__pycache__/mrz_detect.cpython-38.pyc differ
diff --git a/app/extract_mrz/__pycache__/mrz_engine.cpython-38.pyc b/app/extract_mrz/__pycache__/mrz_engine.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..51c6f3b6d5408fc935bfc514eaee1e6fca53a6fb
Binary files /dev/null and b/app/extract_mrz/__pycache__/mrz_engine.cpython-38.pyc differ
diff --git a/app/extract_mrz/mrz_detect.py b/app/extract_mrz/mrz_detect.py
new file mode 100644
index 0000000000000000000000000000000000000000..653b7bad6ef0ea660270ac3d10e9d2f8201fc3dc
--- /dev/null
+++ b/app/extract_mrz/mrz_detect.py
@@ -0,0 +1,34 @@
+import cv2
+from readmrz import MrzDetector
+
+from constants.paths import EXTRACTED_MRZ_PATH
+
+
+def MRZ_detector(img_path):
+    try:
+        mrz_found = False
+        gray = []
+
+        detector = MrzDetector()
+
+        image = detector.read(img_path)
+        cropped = detector.crop_area(image)
+        gray = cv2.cvtColor(cropped, cv2.COLOR_BGR2GRAY)
+
+        cv2.imshow('Image', cropped)
+        cv2.waitKey(0)
+        cv2.destroyAllWindows()
+
+        if len(cropped) != 13:
+            mrz_found = True
+            
+            cv2.imwrite(EXTRACTED_MRZ_PATH, gray)
+            print("MRZ FOUND")
+            # cv2.imshow('Image', cropped)
+            # cv2.waitKey(0)
+            # cv2.destroyAllWindows()
+            
+        return mrz_found, gray
+    except Exception as e:
+        print("[Exception in MRZ_detector] : ", str(e))
+        return mrz_found, gray
\ No newline at end of file
diff --git a/app/extract_mrz/mrz_engine.py b/app/extract_mrz/mrz_engine.py
new file mode 100644
index 0000000000000000000000000000000000000000..63e1826d1c1267598765faac71b1375294cc3194
--- /dev/null
+++ b/app/extract_mrz/mrz_engine.py
@@ -0,0 +1,72 @@
+from mrz.checker.td1 import TD1CodeChecker
+from mrz.checker.td2 import TD2CodeChecker
+from mrz.checker.td3 import TD3CodeChecker
+
+def mrz_engine(mrz_list, lenghtOfChars):
+    try:
+        user_data = {}
+
+        if lenghtOfChars == 90:
+            check = TD1CodeChecker(f"{mrz_list[0]}\n"
+                                f"{mrz_list[1]}\n"
+                                f"{mrz_list[2]}"
+                                )
+        elif lenghtOfChars == 72:
+            check = TD2CodeChecker(f"{mrz_list[0]}\n"
+                                f"{mrz_list[1]}")
+
+        elif lenghtOfChars == 88:
+            check = TD3CodeChecker(f"{mrz_list[0]}\n"
+                                f"{mrz_list[1]}")
+        else:
+            check = False  
+
+        result = bool(check)
+        # print(result)
+        if result:
+            user_data = check.fields()
+            # print(fields.name,fields.surname )
+            # print(get_country(fields.country))
+        else:
+            print("FAILED")
+        
+        return user_data
+    except Exception as e:
+        print("[Exception in mrz_engine] : ", str(e))
+        return user_data
+    
+def mrz_corrector(capital_strings, lenghtOfCharaters):
+
+    try:
+        lines = len(capital_strings)
+
+        if lines == 2 and lenghtOfCharaters not in [72, 88]:
+            safe_check = {72: 3, 88: 3}
+            for index, line in enumerate(capital_strings):
+                if len(line) != safe_check[lenghtOfCharaters]:
+                    char_difference = safe_check[lenghtOfCharaters] - len(line)
+                    line = line + char_difference * '<'
+                    capital_strings[index] = line
+                    lenghtOfCharaters = len(capital_strings)*len(line)
+
+            for index, line in enumerate(capital_strings):
+                if len(line) != 30:
+                    char_difference = 30 - len(line)
+                    line = line + char_difference * '<'
+                    capital_strings[index] = line
+                    lenghtOfCharaters = len(capital_strings)*len(line)
+
+        elif lines == 3 and lenghtOfCharaters != 90:
+            for index, line in enumerate(capital_strings):
+                if len(line) != 30:
+                    char_difference = 30 - len(line)
+                    line = line + char_difference * '<'
+                    capital_strings[index] = line
+                    lenghtOfCharaters = len(capital_strings)*len(line)
+    
+        return lenghtOfCharaters, capital_strings
+    except Exception as e:
+       print("[Exception in mrz_corrector] : ", str(e))
+       lenghtOfCharaters = 0
+       capital_strings = []
+       return lenghtOfCharaters, capital_strings
\ No newline at end of file
diff --git a/app/images/idcards/1.png b/app/images/idcards/1.png
new file mode 100644
index 0000000000000000000000000000000000000000..b0c808fe005ac4c0d2566f006b3b124ea5e4f266
Binary files /dev/null and b/app/images/idcards/1.png differ
diff --git a/app/images/idcards/BlacksSharpen.jpg b/app/images/idcards/BlacksSharpen.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..074e3227de46dcd5b40a5a0f9f70fada9e22d09a
Binary files /dev/null and b/app/images/idcards/BlacksSharpen.jpg differ
diff --git a/app/images/idcards/EO3kzEEUcAEeNbf.jpg b/app/images/idcards/EO3kzEEUcAEeNbf.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..b4488f0f87f7600a43dfeb73cc2c4f38cde4e5ce
Binary files /dev/null and b/app/images/idcards/EO3kzEEUcAEeNbf.jpg differ
diff --git a/app/images/idcards/Genunie-ID-Card-Online.jpg b/app/images/idcards/Genunie-ID-Card-Online.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a432292b566ce0a9989c3c489a74806d92e46825
Binary files /dev/null and b/app/images/idcards/Genunie-ID-Card-Online.jpg differ
diff --git a/app/images/idcards/IMG_20221130_180809.jpg b/app/images/idcards/IMG_20221130_180809.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..6c5bc50bff712a5c02d0d8b2f111361fff836257
--- /dev/null
+++ b/app/images/idcards/IMG_20221130_180809.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb72de3c358fd6239c9a27b7fcfb0b16c5403389677fa6d4edf3754cfc93aa6
+size 2901719
diff --git a/app/images/idcards/IMG_20230210_171555.jpg b/app/images/idcards/IMG_20230210_171555.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..31b0ab8683f04d3f4eee55e0b3219fbe4875f2a6
Binary files /dev/null and b/app/images/idcards/IMG_20230210_171555.jpg differ
diff --git a/app/images/idcards/IMG_20230210_171610.jpg b/app/images/idcards/IMG_20230210_171610.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..315b3912bce79f5327ea3027e3a166f9fc08f493
Binary files /dev/null and b/app/images/idcards/IMG_20230210_171610.jpg differ
diff --git a/app/images/idcards/ShahzainCNIC.jpg b/app/images/idcards/ShahzainCNIC.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..24715d3a4028451f86dc9592556b0ae186234c4c
--- /dev/null
+++ b/app/images/idcards/ShahzainCNIC.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04eaf3e2a6c46ea3551c56a99dbd2334d00d1776c3fbd27925bdd7f21d084470
+size 1668246
diff --git a/app/images/idcards/_13.jpg b/app/images/idcards/_13.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..ee0ad063be8573d436daa6f143a00a7aa06d9142
Binary files /dev/null and b/app/images/idcards/_13.jpg differ
diff --git "a/app/images/idcards/aadhaar backside image\302\240.jpg" "b/app/images/idcards/aadhaar backside image\302\240.jpg"
new file mode 100644
index 0000000000000000000000000000000000000000..6bb9cff2d22df93791cf0a5bf5d4e92b4c733866
--- /dev/null
+++ "b/app/images/idcards/aadhaar backside image\302\240.jpg"	
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b33cf99463058edcd1474456b5c0a8e25bc002c1527fa67d972b129af10a4d4
+size 2028688
diff --git a/app/images/idcards/aadhaar frontside image.jpg b/app/images/idcards/aadhaar frontside image.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..69d07dec2f9ffa0fea6e474235e87ba2776cb885
--- /dev/null
+++ b/app/images/idcards/aadhaar frontside image.jpg	
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41905aa6b4558a2abb16a6ef709915f802d4edc3ec2969aec5a23e3dfa6a54b5
+size 1474221
diff --git a/app/images/idcards/cnic.jpg b/app/images/idcards/cnic.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..9150aa442548baca9485b1f0ec9a2edabb1e7638
Binary files /dev/null and b/app/images/idcards/cnic.jpg differ
diff --git a/app/images/idcards/d.jpg b/app/images/idcards/d.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..a646034e35d1ef2d13486941351511e270030bfc
--- /dev/null
+++ b/app/images/idcards/d.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:015dac6cbf5f50177323f5f7da4be88bd1a110f2c573ead0989b1fd3995ddeb7
+size 1447958
diff --git a/app/images/idcards/driving licence backside image.jpg b/app/images/idcards/driving licence backside image.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..00e93e07891dc7a3524eb78f0c01348ddd45b8df
--- /dev/null
+++ b/app/images/idcards/driving licence backside image.jpg	
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45b95b081250dde945a8118865fb21045c27fd5d04f795684ddffaf98dcbf490
+size 1532900
diff --git a/app/images/idcards/driving licence frontside image.jpg b/app/images/idcards/driving licence frontside image.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..3ff86dc7610d02a9fa5790223510ef690daccfd1
--- /dev/null
+++ b/app/images/idcards/driving licence frontside image.jpg	
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cc3754647dea187a11bfdfcff6c8cb84f97d860beb6a4ca40bb8872b3d8e06c
+size 2011567
diff --git a/app/images/idcards/e4d62a4127719bb07ed88275c3802bf907f026978d1de2a531c1e7967e60bea9.webp b/app/images/idcards/e4d62a4127719bb07ed88275c3802bf907f026978d1de2a531c1e7967e60bea9.webp
new file mode 100644
index 0000000000000000000000000000000000000000..f51396a4cff1ee3b2cdb005c6d1eee49b9c344c0
Binary files /dev/null and b/app/images/idcards/e4d62a4127719bb07ed88275c3802bf907f026978d1de2a531c1e7967e60bea9.webp differ
diff --git a/app/images/idcards/front.jpg b/app/images/idcards/front.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..dfd8b36261045e9d4ee743b7dbbe265331f1c152
--- /dev/null
+++ b/app/images/idcards/front.jpg
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e4f511129548855a1d5b68a2aa60eb8877ab69406499fec43bc1566c6804bd
+size 2186537
diff --git a/app/images/idcards/image.jpg b/app/images/idcards/image.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..77b92c4ee8f3072d17026e42fbdb37620fa1cf2e
Binary files /dev/null and b/app/images/idcards/image.jpg differ
diff --git a/app/images/idcards/image_with_text.jpg b/app/images/idcards/image_with_text.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..beac74464d9844c5f7587f17f8bee466c4325a61
Binary files /dev/null and b/app/images/idcards/image_with_text.jpg differ
diff --git a/app/images/idcards/input.jpg b/app/images/idcards/input.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..358b1b73d6ddae8a4607198579a4573af1ae7c79
Binary files /dev/null and b/app/images/idcards/input.jpg differ
diff --git a/app/images/idcards/m.jpg b/app/images/idcards/m.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..ca81f9ba68c197723fadb03b55ec47a59528b4f5
Binary files /dev/null and b/app/images/idcards/m.jpg differ
diff --git a/app/images/idcards/maxresdefault.jpg b/app/images/idcards/maxresdefault.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..2ee9a1c0c104baa2afa59ee8837410aa6836a7da
Binary files /dev/null and b/app/images/idcards/maxresdefault.jpg differ
diff --git a/app/images/idcards/mm.jpg b/app/images/idcards/mm.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..acdf6792fd3009a2a0e1ce4286ddf5ca3607b638
Binary files /dev/null and b/app/images/idcards/mm.jpg differ
diff --git a/app/images/idcards/mrz-1.webp b/app/images/idcards/mrz-1.webp
new file mode 100644
index 0000000000000000000000000000000000000000..8aecc8c19254b1bc05bd7e22191701afc54123da
Binary files /dev/null and b/app/images/idcards/mrz-1.webp differ
diff --git a/app/images/idcards/pakistan.jpg b/app/images/idcards/pakistan.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..997ca82d51404a3ddb0ae755da016e8e26e6e6eb
Binary files /dev/null and b/app/images/idcards/pakistan.jpg differ
diff --git a/app/images/idcards/rafay Cnic.jpg b/app/images/idcards/rafay Cnic.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..77b92c4ee8f3072d17026e42fbdb37620fa1cf2e
Binary files /dev/null and b/app/images/idcards/rafay Cnic.jpg differ
diff --git a/app/images/idcards/sehrish non corp.png b/app/images/idcards/sehrish non corp.png
new file mode 100644
index 0000000000000000000000000000000000000000..40534720bc2a426c3dc5fde7dddbe85e9c55fe9e
Binary files /dev/null and b/app/images/idcards/sehrish non corp.png differ
diff --git a/app/images/idcards/shefqet.png b/app/images/idcards/shefqet.png
new file mode 100644
index 0000000000000000000000000000000000000000..37dbaeed0395146e0c96cfa47fe9fb5e740c09fd
Binary files /dev/null and b/app/images/idcards/shefqet.png differ
diff --git a/app/images/passports/ID_POLAND_BACK.png b/app/images/passports/ID_POLAND_BACK.png
new file mode 100644
index 0000000000000000000000000000000000000000..879b10b176237dc2a7a2e8fd8e6e3e3286ef3cc4
Binary files /dev/null and b/app/images/passports/ID_POLAND_BACK.png differ
diff --git a/app/images/passports/Sweden.png b/app/images/passports/Sweden.png
new file mode 100644
index 0000000000000000000000000000000000000000..3ed64b892d712a4fabfd83e466e845d9b7fe7c6b
Binary files /dev/null and b/app/images/passports/Sweden.png differ
diff --git a/app/images/passports/bean.jpg b/app/images/passports/bean.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..e0dbd0a8f778cf2e8fd3903025a753b786484d61
Binary files /dev/null and b/app/images/passports/bean.jpg differ
diff --git a/app/images/passports/czech-passport-2006-mrz-data-KJDTYE.jpg b/app/images/passports/czech-passport-2006-mrz-data-KJDTYE.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..2ec0c2db17f75eef4496e28415306cbe764a150b
Binary files /dev/null and b/app/images/passports/czech-passport-2006-mrz-data-KJDTYE.jpg differ
diff --git a/app/images/passports/foreignpassportrus.jpg b/app/images/passports/foreignpassportrus.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..37fe20051aeb6774659d9b568ad46a0aed504275
Binary files /dev/null and b/app/images/passports/foreignpassportrus.jpg differ
diff --git a/app/images/passports/image_with_text.jpg b/app/images/passports/image_with_text.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..beac74464d9844c5f7587f17f8bee466c4325a61
Binary files /dev/null and b/app/images/passports/image_with_text.jpg differ
diff --git a/app/images/passports/passport old.jpg b/app/images/passports/passport old.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..00f2d12e0d209024df8dd9590da11d443ed06ee2
Binary files /dev/null and b/app/images/passports/passport old.jpg differ
diff --git a/app/images/passports/passport.jpg b/app/images/passports/passport.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..616d1e8a2e512ef5f7a41119b5ee68214fddabba
Binary files /dev/null and b/app/images/passports/passport.jpg differ
diff --git a/app/images/passports/td3_image.jpg b/app/images/passports/td3_image.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..c2bb3b2c763a0a4e57390271b99af9d4ee7d3c73
Binary files /dev/null and b/app/images/passports/td3_image.jpg differ
diff --git a/app/images/passports/where_is_your_mrz_passport_number.jpg b/app/images/passports/where_is_your_mrz_passport_number.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..25b01ba8650093d8d8026e01e44fcc7e7db3fb2d
Binary files /dev/null and b/app/images/passports/where_is_your_mrz_passport_number.jpg differ
diff --git a/app/layoutLM_api/__pycache__/api.cpython-38.pyc b/app/layoutLM_api/__pycache__/api.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..3e3b13ac1920bffb7612e1c877823169a5736f41
Binary files /dev/null and b/app/layoutLM_api/__pycache__/api.cpython-38.pyc differ
diff --git a/app/layoutLM_api/api.py b/app/layoutLM_api/api.py
new file mode 100644
index 0000000000000000000000000000000000000000..5756e030cc3e59e2bb092aad31db294e58fc0bd8
--- /dev/null
+++ b/app/layoutLM_api/api.py
@@ -0,0 +1,56 @@
+import requests
+import mimetypes
+import requests
+import mimetypes
+from butler import Client
+import os
+from dotenv import load_dotenv
+
+mimetypes.init()
+load_dotenv()
+
+api_key = os.getenv('api_key')
+queue_id = os.getenv('queue_id')
+
+
+def custom_ocr(image_path):
+    
+    extracted_field = {
+        'name':             '',
+        'dob':              '',
+        'country':          '',
+        'gender':           '',
+        'document_number':  '',
+    }
+
+    # PUT THIS IN ENV FILE
+    # Make sure to add your API Key to the auth headers
+    
+
+    # Response is a strongly typed object
+    response = Client(api_key).extract_document(queue_id, image_path)
+    dictionary = response.to_dict()
+    print("dictionary : ", dictionary)
+
+    for field in dictionary['formFields']:
+
+        if ('Name' in field['fieldName']) and (extracted_field['name'] == ''):
+            
+            if field['fieldName'] == 'Last Name':
+                extracted_field['name'] = field['value']
+            elif field['fieldName'] == 'First Name':
+                extracted_field['name'] = field['value']
+            elif field['fieldName'] == 'Middle Name':
+                extracted_field['name'] = field['value']
+        
+        if field['fieldName'] == 'Document Number':
+            extracted_field['document_number'] = field['value']
+
+        if field['fieldName'] == 'Date of Birth':
+            extracted_field['dob'] = field['value']
+
+        if (field['fieldName'] == 'State' or field['fieldName'] == 'County' or field['fieldName'] == 'Place of Birth' ) and (len(field['value']) > 0):
+            extracted_field['country'] = field['value']
+
+    print("MODEL EXTRACTED FIELDS : ", extracted_field)
+    return extracted_field
\ No newline at end of file
diff --git a/app/ocr_engine/__pycache__/ocr.cpython-38.pyc b/app/ocr_engine/__pycache__/ocr.cpython-38.pyc
new file mode 100644
index 0000000000000000000000000000000000000000..6ba4991ba218301d6a90c40babf94b6405f9ed20
Binary files /dev/null and b/app/ocr_engine/__pycache__/ocr.cpython-38.pyc differ
diff --git a/app/ocr_engine/ocr.py b/app/ocr_engine/ocr.py
new file mode 100644
index 0000000000000000000000000000000000000000..e165a31cc69a458c2bb472a9609cff07e429d0de
--- /dev/null
+++ b/app/ocr_engine/ocr.py
@@ -0,0 +1,5 @@
+from paddleocr import PaddleOCR, draw_ocr
+from PIL import Image
+import torch
+
+OCR = PaddleOCR(use_angle_cls=True, lang='en') # need to run only once to download and load model into memory
\ No newline at end of file
diff --git a/app/output/mrz_image.jpg b/app/output/mrz_image.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..6f5be705278b37630116c26243d50e135bf5914d
Binary files /dev/null and b/app/output/mrz_image.jpg differ
diff --git a/app/run.py b/app/run.py
new file mode 100644
index 0000000000000000000000000000000000000000..fdfa16134685d4fc1ae0e738129f84a24fde2ca2
--- /dev/null
+++ b/app/run.py
@@ -0,0 +1,66 @@
+from constants.paths import IMAGE_PATH
+from extract_country.country_extract import country_extractor
+from extract_dates.date_engine import date_extractor
+from extract_gender.gender_extractor import gender_extract
+from extract_identity_number.identity_number import identity_card_extractor
+from extract_mrz.mrz_detect import MRZ_detector
+from ocr_engine.ocr import ocr
+from extract_mrz import mrz_engine
+import re
+
+def main():
+    global extract_text
+    extract_text = []
+
+    mrz_found, cropped = MRZ_detector(IMAGE_PATH)
+
+    result = ocr.ocr(cropped, cls=True) #extracting MRZ text with ocr
+
+    if mrz_found and not (len(result) <= 1):
+        
+        lenghtOfCharaters = 0
+        capital_strings = []
+        print('\n')
+        for x,line in enumerate(result[0]):
+            text = line[1][0]
+            
+            print(text)
+
+            capital_strings.append(text.upper())
+            lenghtOfCharaters = len(text.upper()) + lenghtOfCharaters
+        
+        print('\n')
+        print("Extracted Text : ",capital_strings)
+        print("The lenght of charaters is : ", lenghtOfCharaters)
+
+        lenghtOfCharaters, capital_strings = mrz_engine.mrz_corrector(capital_strings,lenghtOfCharaters)
+
+        if lenghtOfCharaters != 0 and len(capital_strings) != 0:
+            user_data = mrz_engine(capital_strings,lenghtOfCharaters)
+            print("USER DATA : ", user_data)
+    else:
+        print("MRZ NOT FOUND \nExtracting full card \n")
+        
+        result = ocr.ocr(IMAGE_PATH, cls=True)
+        print("\n")
+
+        # extract_text = [] #storing extracting text in a list
+
+        for idx in range(len(result)):
+            res = result[idx]
+            for line in res:
+                string_value = line[1][0]
+                extract_text.append(string_value)
+                
+        print("LIST : ", extract_text)
+        
+        dob_found, dob, ocr_list = date_extractor(extract_text)
+        # gender_found, gender, ocr_list = gender_extract(ocr_list)
+        # country_found, country, ocr_list = country_extractor(ocr_list)
+        # identity_number_found, identity_number, ocr_list = identity_card_extractor(ocr_list)
+        # dob_found, DOB = date_extractor(extract_text)
+        # dob_found, DOB = date_extractor(extract_text)
+        # print("UPDAETD LIST : ", ocr_list)
+
+if __name__ == "__main__":
+    main()
\ No newline at end of file
diff --git a/deploy.py b/deploy.py
new file mode 100644
index 0000000000000000000000000000000000000000..ca6f00b26125e4087d2f3d32c69391d3515ad7f5
--- /dev/null
+++ b/deploy.py
@@ -0,0 +1,63 @@
+import numpy as np
+import gradio as gr
+from fastapi import FastAPI, File, UploadFile
+from app.extract_country.country_dictionary import find_country
+from app.extract_dates.date_engine import date_extractor
+from app.extract_gender.gender_extractor import gender_extract
+from app.extract_identity_number.doc_number_extractor import doc_number
+from app.ocr_engine.ocr import OCR
+from paddleocr import PaddleOCR
+from app.layoutLM_api.api import custom_ocr
+import cv2
+
+def ocr(input_img):
+    print(type(input_img))
+    ocr = PaddleOCR(use_angle_cls=True, lang='en') # need to run only once to download and load model into memory
+
+    file_path = 'app/images/idcards/input.jpg'
+    cv2.imwrite(file_path, input_img)
+
+    # with open(file_path, "wb+") as file_object:
+    #     file_object.write(input_img.file.read())
+    
+    dictionary = custom_ocr(file_path)
+
+    if '' in list(dictionary.values()):
+        print("Missing value found in Dic")
+        
+        extract_text = []
+        result = ocr.ocr(file_path, cls=True)
+
+        extract_text = [line[1][0] for res in result for line in res]
+        print("extract_text", extract_text)
+
+        if len(dictionary['gender']) == 0:
+            print("Gender Missing")
+            gender_found, gender, ocr_list = gender_extract(extract_text)
+            
+            dictionary["gender"] = gender if gender_found else None
+
+        if len(dictionary['dob']) == 0:
+            print("Dob Missing")
+            dob_found, dob, ocr_list = date_extractor(extract_text)
+
+            dictionary["dob"] = dob if dob_found else None
+
+        if len(dictionary['country']) == 0:
+            print("Country Missing")
+            country_found, country, ocr_list = find_country(extract_text)
+            dictionary["country"] = country if country_found else None
+
+        if len(dictionary['document_number']) == 0:
+            print("document Number missing")
+
+            document_number_found, document_number, ocr_list = doc_number(extract_text)
+            dictionary["document_number"] = document_number if document_number_found else None
+
+
+    print("Updated Dict ",dictionary)
+    response = {"Status" : 200, "OCR" : dictionary}  
+    return response
+
+demo = gr.Interface(ocr, gr.Image(), "json")
+demo.launch(share=True)
\ No newline at end of file
diff --git a/main.py b/main.py
new file mode 100644
index 0000000000000000000000000000000000000000..659c32f56e9899212da81947c34ecb9c1386fad1
--- /dev/null
+++ b/main.py
@@ -0,0 +1,5 @@
+import uvicorn
+
+if __name__ == "__main__":
+    uvicorn.run("app.app:app",host="0.0.0.0", port=8000, reload=True)
+    
\ No newline at end of file
diff --git a/test.py b/test.py
new file mode 100644
index 0000000000000000000000000000000000000000..abe353d7514046ec352d06bafbce09bd8d5af684
--- /dev/null
+++ b/test.py
@@ -0,0 +1,19 @@
+import re
+
+def identify_document_id(data_list):
+    keywords = ["Document ID", "Document Number", "Passport Number", "ID Number"]  # Add other possible keywords
+
+    for item in data_list:
+        for keyword in keywords:
+            if keyword in item:
+                # Extract document ID based on format and length
+                document_id = re.findall(r'\b[A-Za-z0-9]+\b', item)
+                # Additional checks for format and length can be added here
+                return document_id[0] if document_id else None
+
+    return None
+
+# Test the function with the given data list
+data_list = ["Govermment of the People's Republic of Bangladesh", 'NationalIDCard', '12May 1975', 'HETH', 'Caaaat', 'Name', 'ROMANARAHMAN', 'Date of tn 12 May 1975', '8673674936']
+document_id = identify_document_id(data_list)
+print(document_id)