Update app.py

app.py

@@ -16,9 +16,6 @@ from sklearn.metrics import accuracy_score
 # VECTORIZATION the u factor
 import matplotlib.pyplot as plt
 import os
-import torch
-import torchvision.transforms as transforms
-import torchvision.models as models
 from PIL import Image
 from tensorflow.keras.models import Sequential
 from tensorflow.keras.layers import Dense, Conv1D, MaxPooling1D, Flatten, Dropout
@@ -165,6 +162,7 @@ st.markdown("<p class='st-text'>قم بقراءة شروط الاستخدام ف
 
 picture = st.camera_input("Take a picture")
 
+
 if picture:
     bytes_data = picture.getvalue()
     frm = cv2.imdecode(np.frombuffer(bytes_data, np.uint8), cv2.IMREAD_COLOR)
@@ -176,58 +174,64 @@ if picture:
     gray = cv2.cvtColor(frm, cv2.COLOR_BGR2GRAY)
     average_brightness = cv2.mean(gray)[0]
     # st.text(str(average_brightness))
+    
     if average_brightness < 100:
         st.text("إضاءة غير جيدة")
         st.text("انتقل الى مكان جيد الإضاءة")
     else:
-
-        # Detect faces using cascade classifier
-        face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
-        faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30))
-        expansion_factor = 1.5
-        num_bins = 256
-        biggest_face = None
-        biggest_area = 0
-        target_size = (512,512)
-        for (x, y, w, h) in faces:
-            # Calculate the expanded dimensions
-            expanded_x = max(0, int(x - (w * (expansion_factor - 1) / 2)))
-            expanded_y = max(0, int(y - (h * (expansion_factor - 1) / 2)))
-            expanded_w = min(img_w, int(w * expansion_factor))
-            expanded_h = min(img_h, int(h * expansion_factor))
-    
-            # Crop the expanded face region from the frame
-            current_area = expanded_w * expanded_h
-            if current_area > biggest_area:
-                biggest_area = current_area
-                biggest_face = frm[expanded_y:expanded_y + expanded_h, expanded_x:expanded_x + expanded_w]
-                # biggest_face = frm[y:y + h, x:x + w]
-                resized_face = cv2.resize(biggest_face, target_size)
-        if biggest_face is not None:
-                
-            # Perform spatial pyramid feature extraction
-            rgb_features = spatial_pyramid(cv2.cvtColor(resized_face, cv2.COLOR_BGR2RGB), num_bins)
-            hsv_features = spatial_pyramid(cv2.cvtColor(resized_face, cv2.COLOR_BGR2HSV), num_bins)
-            ycbcr_features = spatial_pyramid(cv2.cvtColor(resized_face, cv2.COLOR_BGR2YCrCb), num_bins)
-    
-    
-            if rgb_features.size > 0 and hsv_features.size > 0 and ycbcr_features.size > 0:
-                combined_features = np.concatenate((rgb_features, hsv_features, ycbcr_features))
-                features_list.append(combined_features)
-            if len(features_list) > 0:
-                X_array = np.array(features_list)
-                # print(X_array.shape)
-                X_test_array_reshaped = np.expand_dims(X_array, axis=-1)
-                prediction = model.predict(X_test_array_reshaped)
-                prediction2 = model2.predict(X_test_array_reshaped)
-                if prediction >= 0.80 and prediction2 >= 0.00000000000001:
-                    st.text("صورة حقيقية")
-                    # st.text(str(prediction[0]))
-                    # st.text(str(prediction2[0]))
-                else:
-                    st.text("صورة مزيفة")
-                    st.text(str(prediction[0]))
-                    # st.text(str(prediction2[0]))
+        # Initialize the face detector
+        faceDetector = dlib.get_frontal_face_detector()
+        
+        # Assuming 'frm' is your input image
+        faces = faceDetector(frm, 0)
+        
+        # Check if there are any faces detected
+        if len(faces) > 0:
+            largest_face = None
+            max_area = 0
+        
+            # Find the largest face
+            for face in faces:
+                w = face.right() - face.left()
+                h = face.bottom() - face.top()
+                area = w * h
+                if area > max_area:
+                    max_area = area
+                    largest_face = face
+        
+            # If a largest face is detected
+            if largest_face is not None:
+                # Extract the largest face
+                face_img = frm[largest_face.top():largest_face.bottom(), largest_face.left():largest_face.right()]
+                # Now, 'face_img' contains the largest face. You can process it further as needed.
+                if np.array(face_img).size != 0 :
+                    target_size = (512, 512)
+                    resized_face = cv2.resize(face_img, target_size)                
+                    # Perform spatial pyramid feature extraction
+                    rgb_features = spatial_pyramid(cv2.cvtColor(resized_face, cv2.COLOR_BGR2RGB), num_bins)
+                    hsv_features = spatial_pyramid(cv2.cvtColor(resized_face, cv2.COLOR_BGR2HSV), num_bins)
+                    ycbcr_features = spatial_pyramid(cv2.cvtColor(resized_face, cv2.COLOR_BGR2YCrCb), num_bins)
+            
+            
+                    if rgb_features.size > 0 and hsv_features.size > 0 and ycbcr_features.size > 0:
+                        combined_features = np.concatenate((rgb_features, hsv_features, ycbcr_features))
+                        features_list.append(combined_features)
+                    if len(features_list) > 0:
+                        X_array = np.array(features_list)
+                        # print(X_array.shape)
+                        X_test_array_reshaped = np.expand_dims(X_array, axis=-1)
+                        prediction = model.predict(X_test_array_reshaped)
+                        prediction2 = model2.predict(X_test_array_reshaped)
+                        if prediction >= 0.80 and prediction2 >= 0.00000000000001:
+                            st.text("صورة حقيقية")
+                            # st.text(str(prediction[0]))
+                            # st.text(str(prediction2[0]))
+                        else:
+                            st.text("صورة مزيفة")
+                            st.text(str(prediction[0]))
+                            # st.text(str(prediction2[0]))
+            else:
+                st.text("لا يوجد وجه")
         else:
             st.text("لا يوجد وجه")
     # Provide guidance for users