Update app.py

app.py

@@ -10,6 +10,7 @@ import numpy as np
 from PIL import Image
 from facenet_pytorch import MTCNN, InceptionResnetV1
 import json
+import gradio as gr
 
 # Load Google Drive API credentials from the uploaded JSON file
 SERVICE_ACCOUNT_FILE = './.env'  # Assuming the uploaded JSON file is named '.env'
@@ -48,7 +49,6 @@ def list_files_in_folder(folder_id):
 
 def download_file(file_id, file_name):
     print(f"Attempting to download file: {file_name} (ID: {file_id})")
-    # Add extension if missing (assuming files are images)
     if not file_name.lower().endswith(('.jpg', '.jpeg', '.png')):
         file_name += ".jpg"
     try:
@@ -70,8 +70,7 @@ def download_file(file_id, file_name):
 def verify_and_fix_image(image_path):
     try:
         with Image.open(image_path) as img:
-            img.verify()  # Verify if the image is corrupt
-        # Reopen and save to ensure it's clean
+            img.verify()
         with Image.open(image_path) as img:
             img.save(image_path)
         print(f"Image verified and cleaned: {image_path}")
@@ -95,9 +94,9 @@ def upload_file(file_path, folder_id):
 def extract_face_embedding(image_path):
     try:
         image = Image.open(image_path)
-        face = mtcnn(image)  # Detect and crop the face
+        face = mtcnn(image)
         if face is not None:
-            embedding = resnet(face.unsqueeze(0))  # Get the face embedding
+            embedding = resnet(face.unsqueeze(0))
             return embedding
         else:
             print(f"No face detected in image: {image_path}")
@@ -107,7 +106,6 @@ def extract_face_embedding(image_path):
         return None
 
 def calculate_similarity(embedding1, embedding2):
-    # Calculate cosine similarity between two embeddings
     return torch.nn.functional.cosine_similarity(embedding1, embedding2).item()
 
 def process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id):
@@ -115,7 +113,6 @@ def process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id):
     aadhar_files = list_files_in_folder(aadhar_folder_id)
     cphotos_files = list_files_in_folder(cphotos_folder_id)
 
-    # Extract embeddings for all Aadhar images
     aadhar_embeddings = []
     for file in aadhar_files:
         print(f"Processing Aadhar file: {file['name']}")
@@ -125,7 +122,6 @@ def process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id):
             if embedding is not None:
                 aadhar_embeddings.append((file['name'], embedding))
 
-    # Compare each CCTV image with all Aadhar embeddings
     for file in cphotos_files:
         print(f"Processing CCTV file: {file['name']}")
         file_path = download_file(file['id'], file['name'])
@@ -139,7 +135,7 @@ def process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id):
         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
+            if similarity > 0.8:
                 matched = True
                 print(f"Match found for file: {file['name']} with Aadhar file: {aadhar_name}, Similarity: {similarity:.2f}")
                 break
@@ -150,12 +146,15 @@ def process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id):
 
     print("Processing of images completed.")
 
-def main():
+def run_script():
     start_time = time.time()
     print("Script started...")
     process_images(aadhar_folder_id, cphotos_folder_id, suspects_folder_id)
     end_time = time.time()
-    print(f"Script completed in {end_time - start_time:.2f} seconds.")
+    return f"Script completed in {end_time - start_time:.2f} seconds."
+
+# Gradio interface
+iface = gr.Interface(fn=run_script, inputs=[], outputs="text", description="Run the Image Processing Script")
 
 if __name__ == "__main__":
-    main()
+    iface.launch()