Update app.py

app.py

@@ -1,42 +1,86 @@
-import cv2
+import face_recognition
 import pandas as pd
-import gradio as gr
-from deepface import DeepFace
-
-# Load the CSV data
-csv_path = '/content/photo.csv'  # Path to your CSV
-data = pd.read_csv(csv_path)
-
-# Function to match the recognized face with data in the CSV
-def get_person_data(image_filename):
-    person = data[data['filename'] == image_filename]
-    if not person.empty:
-        return f"Name: {person.iloc[0]['name']}, CNIC: {person.iloc[0]['cnic']}, Age: {person.iloc[0]['age']}, Hometown: {person.iloc[0]['hometown']}"
+import numpy as np  # Import numpy
+
+# Assuming the uploaded CSV file is named 'photo.csv' and the folder containing images is named 'image'
+image_dir = "image"
+info_path = "photo.csv"
+
+def load_dataset():
+  """Loads the dataset from CSV and image folder."""
+  try:
+    data = pd.read_csv(info_path)
+    print(f"CSV file loaded successfully: {info_path}")
+  except FileNotFoundError:
+    print(f"Error: CSV file not found at {info_path}")
+    return None, None, None
+  except Exception as e:
+    print(f"Error reading CSV file: {e}")
+    return None, None, None
+
+  known_face_encodings = []
+  known_face_names = []
+  for index, row in data.iterrows():
+    image_path = f"{image_dir}/{row['Name']}"
+    try:
+      image = face_recognition.load_image_file(image_path)
+      face_encoding = face_recognition.face_encodings(image)
+      if len(face_encoding) > 0:
+        known_face_encodings.append(face_encoding[0])
+        known_face_names.append(row['Name'])
+      else:
+        print(f"No face detected in {image_path}")
+    except FileNotFoundError:
+      print(f"Error: Image file not found at {image_path}")
+    except Exception as e:
+      print(f"Error processing image: {e}")
+      continue
+
+  return known_face_encodings, known_face_names, data
+
+def recognize_face(img):
+  """Recognizes faces in an image."""
+  try:
+    face_locations = face_recognition.face_locations(img)
+    face_encodings = face_recognition.face_encodings(img, face_locations)
+
+    for (top, right, bottom, left), face_encoding in zip(face_locations, face_encodings):
+      matches = face_recognition.compare_faces(known_face_encodings, face_encoding)
+      name = "Unknown"
+
+      face_distances = face_recognition.face_distance(known_face_encodings, face_encoding)
+      best_match_index = np.argmin(face_distances)
+      if matches[best_match_index]:
+        name = known_face_names[best_match_index]
+        person_info = data[data['Name'] == name]
+        cnic = person_info['CNIC'].values[0]
+        age = person_info['Age'].values[0]
+        hometown = person_info['Hometown'].values[0]
+        return f"{name}\nCNIC: {cnic}\nAge: {age}\nHometown: {hometown}"
+    return "No face detected."
+  except Exception as e:
+    return f"An error occurred: {e}"
+
+# Load the dataset
+known_face_encodings, known_face_names, data = load_dataset()
+
+if known_face_encodings and data is not None:
+  # Define the function to be used by the app
+  def app(image):
+    """Main function of the app that takes an image and returns the recognized face information."""
+    return recognize_face(image)
+else:
+  print("Error: Failed to load dataset or encode faces.")
+
+# Launch the app (if data loaded successfully)
+if known_face_encodings and data is not None:
+  from PIL import Image  # Optional dependency for handling potential image format issues
+
+  def preprocess_image(image):
+    """Preprocess the uploaded image if necessary (e.g., convert to RGB)."""
+    if isinstance(image, Image.Image):
+      return np.array(image.convert('RGB'))
     else:
-        return "Person not recognized"
-
-# Function to process the uploaded image for face recognition
-def recognize_face(image):
-    result = DeepFace.analyze(image, actions=['emotion'], enforce_detection=False)
-    for face in result:
-        x, y, w, h = face['region']['x'], face['region']['y'], face['region']['w'], face['region']['h']
-        face_img = image[y:y+h, x:x+w]
-        
-        try:
-            identity = DeepFace.find(img_path=face_img, db_path='/content/images', enforce_detection=False)
-            if not identity.empty:
-                matched_image = identity.iloc[0]['identity'].split('/')[-1]
-                person_info = get_person_data(matched_image)
-                return person_info
-        except:
-            return "No match found"
-    
-    return "No face detected"
-
-# Gradio Interface
-iface = gr.Interface(fn=recognize_face,
-                     inputs=gr.inputs.Image(type="numpy"),
-                     outputs=gr.outputs.Textbox(),
-                     live=True)
-
-iface.launch()
+      return image
+
+  app = app.preprocess(preprocess_image)  # Apply preprocessing if needed