Update app.py

app.py

@@ -7,27 +7,26 @@ from tensorflow.keras.applications.xception import preprocess_input as xcp_pre
 from tensorflow.keras.applications.efficientnet import preprocess_input as eff_pre
 from huggingface_hub import hf_hub_download
 
+
 # Load models
 xcp_path = hf_hub_download(repo_id="Zeyadd-Mostaffa/deepfake-image-detector_final", filename="xception_model.h5")
 eff_path = hf_hub_download(repo_id="Zeyadd-Mostaffa/deepfake-image-detector_final", filename="efficientnet_model.h5")
 xcp_model = load_model(xcp_path)
 eff_model = load_model(eff_path)
 
-# Load MTCNN detector
-detector = MTCNN()
-
-# Filters
-MIN_FACE_AREA = 6400        # 80x80 minimum face area
-MIN_SHARPNESS = 20          # blur threshold
-MIN_BRIGHTNESS = 30         # dark crop threshold
 
-def is_blurry(image):
-    gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
-    return cv2.Laplacian(gray, cv2.CV_64F).var() < MIN_SHARPNESS
+# Load face detector
+detector = MTCNN()
 
-def is_dark(image):
-    gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
-    return np.mean(gray) < MIN_BRIGHTNESS
+def expand_box(x, y, w, h, scale=1.5, img_shape=None):
+    """Expand face bounding box with margin."""
+    cx, cy = x + w // 2, y + h // 2
+    new_w, new_h = int(w * scale), int(h * scale)
+    x1 = max(0, cx - new_w // 2)
+    y1 = max(0, cy - new_h // 2)
+    x2 = min(img_shape[1], cx + new_w // 2)
+    y2 = min(img_shape[0], cy + new_h // 2)
+    return x1, y1, x2, y2
 
 def predict(image):
     faces = detector.detect_faces(image)
@@ -36,13 +35,11 @@ def predict(image):
 
     output_image = image.copy()
     results = []
-    face_count = 0
 
     for idx, face in enumerate(faces):
         x, y, w, h = face['box']
-        if w * h < MIN_FACE_AREA:
-            continue
 
+        # Add 20% margin while staying inside bounds
         margin = 0.2
         img_h, img_w = image.shape[:2]
         x = max(0, int(x - w * margin))
@@ -51,18 +48,16 @@ def predict(image):
         h = int(h * (1 + 2 * margin))
         x2 = min(img_w, x + w)
         y2 = min(img_h, y + h)
-        face_img = image[y:y2, x:x2]
 
-        if face_img.shape[0] < 40 or face_img.shape[1] < 40:
-            continue
-        if is_blurry(face_img) or is_dark(face_img):
-            continue
+        face_img = image[y:y2, x:x2]
 
+        # Resize + preprocess
         face_xcp = cv2.resize(face_img, (299, 299))
         face_eff = cv2.resize(face_img, (224, 224))
         xcp_tensor = xcp_pre(face_xcp.astype(np.float32))[np.newaxis, ...]
         eff_tensor = eff_pre(face_eff.astype(np.float32))[np.newaxis, ...]
 
+        # Predictions
         pred_xcp = xcp_model.predict(xcp_tensor, verbose=0).flatten()[0]
         pred_eff = eff_model.predict(eff_tensor, verbose=0).flatten()[0]
         avg = (pred_xcp + pred_eff) / 2
@@ -70,15 +65,12 @@ def predict(image):
         label = "Real" if avg > 0.41 else "Fake"
         color = (0, 255, 0) if label == "Real" else (0, 0, 255)
 
-        face_count += 1
+        # Annotate image
         cv2.rectangle(output_image, (x, y), (x2, y2), color, 2)
         cv2.putText(output_image, f"{label} ({avg:.2f})", (x, y - 10),
                     cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 2)
 
-        results.append(f"Face {face_count}: {label} (Avg: {avg:.3f}, XCP: {pred_xcp:.3f}, EFF: {pred_eff:.3f})")
-
-    if not results:
-        return "No clear or confident face detected", output_image
+        results.append(f"Face {idx+1}: {label} (Avg: {avg:.3f}, XCP: {pred_xcp:.3f}, EFF: {pred_eff:.3f})")
 
     return "\n".join(results), output_image
 
@@ -91,7 +83,7 @@ interface = gr.Interface(
         gr.Image(type="numpy", label="Annotated Image"),
     ],
     title="Deepfake Detector (Multi-Face Ensemble)",
-    description="Detects all confident faces and classifies each one as real or fake using Xception and EfficientNetB4 ensemble."
+    description="Detects all faces in an image and classifies each one as real or fake using Xception and EfficientNetB4 ensemble.",
 )
 
 interface.launch()