Create app.py

app.py

@@ -0,0 +1,135 @@
+import os
+import io
+import time
+from collections import defaultdict
+import numpy as np
+from PIL import Image
+from deepface import DeepFace
+from google.oauth2 import service_account
+from googleapiclient.discovery import build
+from googleapiclient.http import MediaIoBaseDownload, MediaFileUpload
+from simple_salesforce import Salesforce
+
+# Configuration settings
+SCOPES = ['https://www.googleapis.com/auth/drive']
+SERVICE_ACCOUNT_FILE = r'C:\Users\Ajaya\Downloads\vertical-sunset-440402-h4-f3e25263f3a1.json'
+SF_USERNAME = 'navyagrand7890@gmail.com'
+SF_PASSWORD = 'navya@123'
+SF_SECURITY_TOKEN = 'NeAPhh5Puxmc1EsL1IJPcQB5'
+AADHAR_FOLDER_ID = '1Qtb5DYzSFE67Mbb5ZgDIqWUtdJaDD2F4'
+CPHOTOS_FOLDER_ID = '1DGeRqRbCPcfLDdEgP0h5fyX-MF8EQ8AH'
+SUSPECTS_FOLDER_ID = '1N3RMhVD0OygeufLPYod6IYLtqzvlm3Jv'
+THRESHOLD = 0.65
+
+# Initialize services
+def initialize_services():
+    credentials = service_account.Credentials.from_service_account_file(SERVICE_ACCOUNT_FILE, scopes=SCOPES)
+    drive_service = build('drive', 'v3', credentials=credentials)
+    sf = Salesforce(username=SF_USERNAME, password=SF_PASSWORD, security_token=SF_SECURITY_TOKEN)
+    return drive_service, sf
+
+# List files in a folder
+def list_files_in_folder(drive_service, folder_id):
+    query = f"'{folder_id}' in parents and trashed=false"
+    results = drive_service.files().list(q=query, pageSize=1000, fields="files(id, name)").execute()
+    return results.get('files', [])
+
+# Download a file from Google Drive
+def download_file(drive_service, file_id, file_name):
+    request = drive_service.files().get_media(fileId=file_id)
+    file_io = io.BytesIO()
+    downloader = MediaIoBaseDownload(file_io, request)
+    done = False
+    while not done:
+        _, done = downloader.next_chunk()
+    download_path = os.path.join("downloads", file_name)
+    os.makedirs("downloads", exist_ok=True)
+    with open(download_path, 'wb') as f:
+        f.write(file_io.getvalue())
+    return download_path
+
+# Group similar images based on DeepFace embeddings
+def group_similar_images(image_paths):
+    embeddings = []
+    grouped_images = defaultdict(list)
+
+    # Get embeddings for each image
+    for image_path in image_paths:
+        embedding = DeepFace.represent(image_path, model_name='ArcFace', enforce_detection=False)[0]['embedding']
+        embeddings.append((image_path, embedding))
+
+    # Cluster images based on similarity
+    for i, (image_path_i, embedding_i) in enumerate(embeddings):
+        for j, (image_path_j, embedding_j) in enumerate(embeddings):
+            if i >= j:
+                continue
+            similarity = np.dot(embedding_i, embedding_j) / (np.linalg.norm(embedding_i) * np.linalg.norm(embedding_j))
+            if similarity > 0.85:  # Threshold for grouping similar images
+                grouped_images[i].append(image_path_j)
+
+    # Print the number of images per group
+    print(f"[INFO] Grouped similar images into {len(grouped_images)} groups based on similarity.")
+
+    return grouped_images
+
+# Function to pick best match per group
+def pick_best_match_and_clean_up(grouped_images, aadhar_images, threshold, suspects_folder_id, drive_service, sf):
+    for group_id, image_paths in grouped_images.items():
+        match_found = False
+        for cphoto_path in image_paths:
+            for aadhar_path in aadhar_images:
+                is_match, distance = compare_faces_deepface(aadhar_path, cphoto_path, threshold)
+                if is_match:
+                    match_found = True
+                    print(f"[INFO] Match found for group {group_id} with image {cphoto_path}")
+                    break
+            if match_found:
+                break
+
+        # Clean up: only keep best-matched image, delete others
+        if match_found:
+            for extra_path in image_paths:
+                if extra_path != cphoto_path:
+                    os.remove(extra_path)
+                    print(f"[INFO] Deleted redundant image: {extra_path}")
+        else:
+            # No match found for the group, mark as suspect
+            for cphoto_path in image_paths:
+                uploaded_file_id, uploaded_file_url = upload_file(drive_service, cphoto_path, suspects_folder_id)
+                create_suspect_record_in_salesforce(sf, uploaded_file_id, os.path.basename(cphoto_path), uploaded_file_url)
+
+# Upload file to Google Drive
+def upload_file(drive_service, file_path, folder_id):
+    file_metadata = {'name': os.path.basename(file_path), 'parents': [folder_id]}
+    media = MediaFileUpload(file_path, resumable=True)
+    file = drive_service.files().create(body=file_metadata, media_body=media, fields='id, webViewLink').execute()
+    return file.get('id'), file.get('webViewLink')
+
+# Salesforce record creation
+def create_suspect_record_in_salesforce(sf, file_id, file_name, file_url):
+    record = {'Name': file_name, 'File_ID__c': file_id, 'File_Name__c': file_name, 'File_URL__c': file_url}
+    sf.zia__c.create(record)
+    print(f"[INFO] Created suspect record in Salesforce for file: {file_name}")
+
+# Compare images with DeepFace
+def compare_faces_deepface(img1_path, img2_path, threshold):
+    result = DeepFace.verify(img1_path=img1_path, img2_path=img2_path, model_name='ArcFace', enforce_detection=False)
+    return result['verified'], result['distance']
+
+def main():
+    drive_service, sf = initialize_services()
+    aadhar_files = list_files_in_folder(drive_service, AADHAR_FOLDER_ID)
+    cphotos_files = list_files_in_folder(drive_service, CPHOTOS_FOLDER_ID)
+
+    # Download Aadhaar images
+    aadhar_images = [download_file(drive_service, file['id'], file['name']) for file in aadhar_files]
+
+    # Download CCTV images and group by similarity
+    cphotos_paths = [download_file(drive_service, file['id'], file['name']) for file in cphotos_files]
+    grouped_images = group_similar_images(cphotos_paths)
+
+    # Process each group to find best match and clean up
+    pick_best_match_and_clean_up(grouped_images, aadhar_images, THRESHOLD, SUSPECTS_FOLDER_ID, drive_service, sf)
+
+if __name__ == "__main__":
+    main()