Update app.py

app.py

@@ -1,6 +1,6 @@
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
-# New function for batch processing images in parallel
+# New function to extract embeddings in parallel and batch process CCTV images against Aadhar embeddings
 def batch_process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id):
     # Fetch Aadhar and CCTV files
     aadhar_files = list_files_in_folder(aadhar_folder_id)
@@ -9,48 +9,67 @@ def batch_process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id
     # Extract Aadhar embeddings in parallel
     aadhar_embeddings = []
     with ThreadPoolExecutor() as executor:
-        future_to_aadhar = {executor.submit(download_file, file['id'], file['name']): file['name'] for file in aadhar_files}
+        future_to_aadhar = {executor.submit(download_file, file['id'], file['name']): file for file in aadhar_files}
         for future in as_completed(future_to_aadhar):
-            file_name = future_to_aadhar[future]
+            file = future_to_aadhar[future]
             try:
                 file_path = future.result()
                 if file_path:
                     embedding = extract_face_embedding(file_path)
                     if embedding is not None:
-                        aadhar_embeddings.append((file_name, embedding))
+                        aadhar_embeddings.append((file['name'], embedding))
             except Exception as e:
-                print(f"Error processing Aadhar file {file_name}: {e}")
+                print(f"Error processing Aadhar file {file['name']}: {e}")
 
-    # Process CCTV files in parallel
+    # Verify that embeddings were successfully extracted for at least one Aadhar file
+    if not aadhar_embeddings:
+        print("No valid Aadhar face embeddings found. Exiting.")
+        return
+
+    # Process CCTV files and compare with Aadhar embeddings
     unmatched_files = []
     with ThreadPoolExecutor() as executor:
-        for file in cphotos_files:
-            file_path = download_file(file['id'], file['name'])
-            if not file_path:
-                continue
-
-            embedding_cctv = extract_face_embedding(file_path)
-            if embedding_cctv is None:
-                continue
-
-            matched = False
-            for aadhar_name, aadhar_embedding in aadhar_embeddings:
-                similarity = calculate_similarity(embedding_cctv, aadhar_embedding)
-                if similarity > 0.8:  # Adjust the threshold as necessary
-                    matched = True
-                    print(f"Match found: {file['name']} with Aadhar file: {aadhar_name}, Similarity: {similarity:.2f}")
-                    break
-
-            if not matched:
-                unmatched_files.append(file_path)
-                print(f"Unmatched image queued for upload: {file['name']}")
+        future_to_cphoto = {executor.submit(download_file, file['id'], file['name']): file for file in cphotos_files}
+        for future in as_completed(future_to_cphoto):
+            file = future_to_cphoto[future]
+            try:
+                file_path = future.result()
+                if not file_path:
+                    continue
+
+                embedding_cctv = extract_face_embedding(file_path)
+                if embedding_cctv is None:
+                    continue
+
+                matched = compare_faces_with_embeddings(embedding_cctv, aadhar_embeddings)
+                if not matched:
+                    unmatched_files.append(file_path)
+                    print(f"Unmatched image queued for upload: {file['name']}")
+            except Exception as e:
+                print(f"Error processing CCTV file {file['name']}: {e}")
 
     # Upload unmatched files
     with ThreadPoolExecutor() as executor:
-        for file_path in unmatched_files:
-            executor.submit(upload_file, file_path, suspects_folder_id)
+        upload_futures = [executor.submit(upload_file, file_path, suspects_folder_id) for file_path in unmatched_files]
+        for future in as_completed(upload_futures):
+            try:
+                future.result()
+                print(f"Successfully uploaded unmatched image to suspects folder.")
+            except Exception as e:
+                print(f"Error uploading unmatched file: {e}")
+
+def compare_faces_with_embeddings(embedding_cctv, aadhar_embeddings, threshold=0.7):
+    """
+    Compare the given CCTV embedding with a list of Aadhar embeddings.
+    If the similarity score exceeds the threshold, it's a match.
+    """
+    for aadhar_name, aadhar_embedding in aadhar_embeddings:
+        similarity = calculate_similarity(embedding_cctv, aadhar_embedding)
+        if similarity > threshold:
+            print(f"Match found: Similarity = {similarity:.2f} with Aadhar file: {aadhar_name}")
+            return True
+    return False
 
-# Replace the main function to call the new batch processing function
 def main():
     start_time = time.time()
     print("Script started...")