Added new model and did some modification in script of pan data extraction

app/__init__.py

@@ -10,7 +10,7 @@ def create_app():
         # Load model once
         app.models = {
             'adhaarModel': YOLO('models/aadhaarYolov8.pt'),
-            'panModel': YOLO('models/PanModal_v3.pt')  # Load additional models as needed
+            'panModel': YOLO('models/PanYolo_v4.pt')  # Load additional models as needed
         }
 
     return app

app/services/panServices/panDataExtractor.py

@@ -1,4 +1,18 @@
 import re
+def filter_array(arr):
+    # Define the regex patterns
+    pattern_alphanumeric_special = re.compile(r'[\w]+[^.\s\w]+|[^.\s\w]+[\w]+')
+    pattern_numeric = re.compile(r'^[0-9]+$')
+    pattern_non_alpha = re.compile(r'[^.\s]*[^a-zA-Z\s][^.\s]*')
+    
+    # Filter the array
+    filtered_array = [
+        item for item in arr 
+        if not (pattern_alphanumeric_special.search(item) or 
+                pattern_numeric.match(item) or 
+                pattern_non_alpha.search(item))
+    ]
+    return filtered_array
 
 def extract_panData(data):
     unwanted_words = ["Name", "/Name", 'Permanent', 'Account', 'Number', 'Card', 'नाम', '/Name',
@@ -6,7 +20,10 @@ def extract_panData(data):
                       "VIT VE Hra / Father's Nama", 'पिता का नाम/ Fal', 'पिता का नाम / Fathe', "पिता का नाम / Father's Na", 
                       'जन्म की तारीख /।', 'जन्म का ताराख', "पिता का नाम/ Father's Nam", 'नाम /Name', "पिता का नाम / Father's Name", 
                       'जन्म का वाराज़', 'Date of Birth', 'Permanent Account Number Card', "Date of Birth", "/Date of Birth", 
-                      "Permanent Account Number", "Father's Name", "14 /Name", "/Father's Name"]
+                      "Permanent Account Number", "Father's Name", "14 /Name", "/Father's Name", 'HTH / Name']
+    
+
+    
     
     # Initialize result object
     result = {
@@ -27,7 +44,8 @@ def extract_panData(data):
     for item in data:
         if item not in unwanted_words and not combination_pattern.search(item):
             cleaned_data.append(item)
-
+    
+   
     # Check and extract PAN number
     pan_pattern = re.compile(r'^[A-Z]{5}[0-9]{4}[A-Z]$')
     for item in cleaned_data:
@@ -45,13 +63,14 @@ def extract_panData(data):
             break
 
     # If only two values are left, assume they are name and father's name
+    cleaned_data = filter_array(cleaned_data)
     if len(cleaned_data) == 2:
         result["data"]["name"] = cleaned_data[0]
         result["data"]["fatherName"] = cleaned_data[1]
     else:
         # Further cleaning of the data array to extract name and father's name
         cleaned_data = [item for item in cleaned_data if not combination_pattern.search(item) and item not in unwanted_words]
-        
+        print(cleaned_data, "after cleaning")
         # Check and extract name
         name_pattern = re.compile(r'^[A-Za-z .]+$')
         if len(cleaned_data) > 0 and name_pattern.match(cleaned_data[0]):
@@ -72,4 +91,4 @@ def extract_panData(data):
             result["error"] = f"{key} value is not found due to bad image."
             break
     
-    return result
+    return result

app/services/panServices/panOcr.py

@@ -2,7 +2,7 @@ from io import BytesIO
 from ...utils.azureOCR import analyze_image
 from ...utils.imageUtils import resize_if_needed, all_cropped_images_to_one_image
 from .panDataExtractor import extract_panData
-from collections import defaultdict
+# from collections import defaultdict
 
 def process_results(results, img):
     label_indices = {"pan_num": 0, "name": 1, "father": 2, "dob": 3}