Update app.py

app.py

@@ -1,6 +1,5 @@
 import os
 import json
-import logging
 import time
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from google.oauth2 import service_account
@@ -9,11 +8,7 @@ from googleapiclient.http import MediaIoBaseDownload, MediaFileUpload
 from PIL import Image
 import torch
 import io
-from deepface import DeepFace
-from scipy.spatial.distance import cosine  # Import for cosine similarity calculation
-
-# Set up logging
-logging.basicConfig(level=logging.DEBUG)
+from deepface import DeepFace  # Use DeepFace for advanced face recognition
 
 # Load Google Drive API credentials
 SERVICE_ACCOUNT_FILE = './.env'  # Assuming the uploaded JSON file is named '.env'
@@ -21,21 +16,18 @@ SCOPES = ['https://www.googleapis.com/auth/drive']
 
 try:
     if not os.path.exists(SERVICE_ACCOUNT_FILE):
-        logging.error(f"Service account file '{SERVICE_ACCOUNT_FILE}' not found.")
         raise FileNotFoundError(f"Service account file '{SERVICE_ACCOUNT_FILE}' not found.")
 
     with open(SERVICE_ACCOUNT_FILE, 'r') as json_file:
         credentials_info = json.load(json_file)
     credentials = service_account.Credentials.from_service_account_info(credentials_info, scopes=SCOPES)
     drive_service = build('drive', 'v3', credentials=credentials)
-    logging.debug("Google Drive API credentials loaded successfully.")
 except json.JSONDecodeError as e:
-    logging.error(f"Error parsing JSON service account file: {e}")
+    raise Exception(f"Error parsing JSON service account file: {e}")
 except FileNotFoundError as e:
-    logging.error(f"Service account file missing: {e}")
+    raise Exception(f"Service account file missing: {e}")
 except Exception as e:
-    logging.error(f"Unexpected error while loading credentials: {e}")
-    raise
+    raise Exception(f"Unexpected error while loading credentials: {e}")
 
 # Folder IDs
 aadhar_folder_id = '1Qtb5DYzSFE67Mbb5ZgDIqWUtdJaDD2F4'
@@ -43,25 +35,18 @@ cphotos_folder_id = '1DGeRqRbCPcfLDdEgP0h5fyX-MF8EQ8AH'
 suspects_folder_id = '1N3RMhVD0OygeufLPYod6IYLtqzvlm3Jv'
 
 # Limit the number of threads for scalability
-MAX_THREADS = 3
+MAX_THREADS = 5
 
 def list_files_in_folder(folder_id):
-    logging.debug(f"Listing files in folder ID: {folder_id}")
     query = f"'{folder_id}' in parents and trashed=false"
     try:
         results = drive_service.files().list(q=query, pageSize=50, fields="files(id, name, mimeType)").execute()
         files = results.get('files', [])
-        if not files:
-            logging.warning(f"No files found in folder ID: {folder_id}. Ensure that the folder has files and the service account has access.")
-        else:
-            logging.debug(f"Found {len(files)} files in folder ID: {folder_id}.")
         return files
     except Exception as e:
-        logging.error(f"Error listing files in folder ID: {folder_id} - {e}")
-        return []
+        raise Exception(f"Error listing files in folder ID: {folder_id} - {e}")
 
 def download_file(file_id, file_name):
-    logging.debug(f"Attempting to download file: {file_name} (ID: {file_id})")
     if not file_name.lower().endswith(('.jpg', '.jpeg', '.png')):
         file_name += ".jpg"
     try:
@@ -74,11 +59,9 @@ def download_file(file_id, file_name):
         file_io.seek(0)
         with open(file_name, 'wb') as f:
             f.write(file_io.read())
-        logging.debug(f"Successfully downloaded file: {file_name}")
         return file_name
     except Exception as e:
-        logging.error(f"Error downloading file ID: {file_id} - {e}")
-        return None
+        raise Exception(f"Error downloading file ID: {file_id} - {e}")
 
 def extract_face_embedding(image_path):
     try:
@@ -86,25 +69,21 @@ def extract_face_embedding(image_path):
         embedding = DeepFace.represent(img_path=image_path, model_name='VGG-Face')[0]["embedding"]
         return embedding
     except Exception as e:
-        logging.error(f"Error extracting face encoding for {image_path}. Error: {e}")
-        return None
+        raise Exception(f"Error extracting face encoding for {image_path}. Error: {e}")
 
 def calculate_similarity(encoding1, encoding2):
-    # Use cosine similarity directly
-    distance = cosine(encoding1, encoding2)
-    similarity = 1 - distance
-    return similarity
+    # Use cosine similarity for comparison
+    similarity = DeepFace.find(img_path1=encoding1, img_path2=encoding2, distance_metric='cosine')[0]
+    return 1 - similarity  # Convert distance to similarity
 
 def compare_faces_with_encodings(encoding_cctv, aadhar_encodings, threshold=0.7):
     for aadhar_name, aadhar_encoding in aadhar_encodings:
         similarity = calculate_similarity(encoding_cctv, aadhar_encoding)
         if similarity > threshold:
-            logging.info(f"Match found: Similarity = {similarity:.2f} with Aadhar file: {aadhar_name}")
             return True
     return False
 
 def batch_process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id):
-    logging.debug("Starting processing of images...")
     aadhar_files = list_files_in_folder(aadhar_folder_id)
     cphotos_files = list_files_in_folder(cphotos_folder_id)
 
@@ -121,10 +100,10 @@ def batch_process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id
                     if encoding is not None:
                         aadhar_encodings.append((file['name'], encoding))
             except Exception as e:
-                logging.error(f"Error processing Aadhar file {file['name']}: {e}")
+                print(f"Error processing Aadhar file {file['name']}: {e}")
 
     if not aadhar_encodings:
-        logging.warning("No valid Aadhar face encodings found. Exiting.")
+        print("No valid Aadhar face encodings found. Exiting.")
         return
 
     # Extract CCTV encodings and compare concurrently
@@ -145,9 +124,9 @@ def batch_process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id
                 matched = compare_faces_with_encodings(encoding_cctv, aadhar_encodings)
                 if not matched:
                     unmatched_files.append(file_path)
-                    logging.info(f"Unmatched image queued for upload: {file['name']}")
+                    print(f"Unmatched image queued for upload: {file['name']}")
             except Exception as e:
-                logging.error(f"Error processing CCTV file {file['name']}: {e}")
+                print(f"Error processing CCTV file {file['name']}: {e}")
 
     # Upload unmatched files concurrently
     with ThreadPoolExecutor(max_workers=MAX_THREADS) as executor:
@@ -155,28 +134,24 @@ def batch_process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id
         for future in as_completed(upload_futures):
             try:
                 future.result()
-                logging.info(f"Successfully uploaded unmatched image to suspects folder.")
+                print(f"Successfully uploaded unmatched image to suspects folder.")
             except Exception as e:
-                logging.error(f"Error uploading unmatched file: {e}")
+                print(f"Error uploading unmatched file: {e}")
 
 def upload_file(file_path, folder_id):
-    logging.debug(f"Uploading file: {file_path} to folder ID: {folder_id}")
     file_metadata = {'name': os.path.basename(file_path), 'parents': [folder_id]}
     media = MediaFileUpload(file_path, resumable=True)
     try:
         file = drive_service.files().create(body=file_metadata, media_body=media, fields='id').execute()
-        logging.debug(f"Uploaded file ID: {file.get('id')}")
         return file.get('id')
     except Exception as e:
-        logging.error(f"Error uploading file {file_path} to folder ID: {folder_id} - {e}")
-        return None
+        raise Exception(f"Error uploading file {file_path} to folder ID: {folder_id} - {e}")
 
 def main():
     start_time = time.time()
-    logging.debug("Script started...")
     batch_process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id)
     end_time = time.time()
-    logging.debug(f"Script completed in {end_time - start_time:.2f} seconds.")
+    print(f"Script completed in {end_time - start_time:.2f} seconds.")
 
 if __name__ == "__main__":
     main()