Update app.py

app.py

@@ -7,18 +7,27 @@ 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
 
-# Download and load models
+# 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 face detector
+# Load MTCNN detector
 detector = MTCNN()
 
-# Detection thresholds
-MIN_FACE_SIZE = 60        # Accept faces larger than 60×60 pixels
-MIN_CONFIDENCE = 0.94     # Accept only confident detections
+# 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
+
+def is_dark(image):
+    gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)
+    return np.mean(gray) < MIN_BRIGHTNESS
 
 def predict(image):
     faces = detector.detect_faces(image)
@@ -27,32 +36,33 @@ def predict(image):
 
     output_image = image.copy()
     results = []
-    valid_faces = 0
+    face_count = 0
 
     for idx, face in enumerate(faces):
-        conf = face.get("confidence", 0)
         x, y, w, h = face['box']
-
-        # Filter out unclear faces
-        if w < MIN_FACE_SIZE or h < MIN_FACE_SIZE or conf < MIN_CONFIDENCE:
+        if w * h < MIN_FACE_AREA:
             continue
 
-        img_h, img_w = image.shape[:2]
         margin = 0.2
+        img_h, img_w = image.shape[:2]
         x = max(0, int(x - w * margin))
         y = max(0, int(y - h * margin))
-        x2 = min(img_w, x + int(w * (1 + 2 * margin)))
-        y2 = min(img_h, y + int(h * (1 + 2 * margin)))
-
+        w = int(w * (1 + 2 * margin))
+        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]
 
-        # Resize and preprocess
+        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_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, ...]
 
-        # Predict
         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
@@ -60,20 +70,19 @@ def predict(image):
         label = "Real" if avg > 0.41 else "Fake"
         color = (0, 255, 0) if label == "Real" else (0, 0, 255)
 
-        # Draw on image
+        face_count += 1
         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 {idx+1}: {label} (Avg: {avg:.3f}, XCP: {pred_xcp:.3f}, EFF: {pred_eff:.3f})")
-        valid_faces += 1
+        results.append(f"Face {face_count}: {label} (Avg: {avg:.3f}, XCP: {pred_xcp:.3f}, EFF: {pred_eff:.3f})")
 
-    if valid_faces == 0:
-        return "No clear or confident face detected", image
+    if not results:
+        return "No clear or confident face detected", output_image
 
     return "\n".join(results), output_image
 
-# Interface
+# Gradio Interface
 interface = gr.Interface(
     fn=predict,
     inputs=gr.Image(type="numpy", label="Upload Image"),
@@ -82,8 +91,9 @@ interface = gr.Interface(
         gr.Image(type="numpy", label="Annotated Image"),
     ],
     title="Deepfake Detector (Multi-Face Ensemble)",
-    description="Detects all visible faces in an image and classifies each as Real or Fake using Xception and EfficientNetB4 ensemble.",
+    description="Detects all confident faces and classifies each one as real or fake using Xception and EfficientNetB4 ensemble."
 )
 
 interface.launch()
 
+