Update app.py

app.py

@@ -1,89 +1,63 @@
-import cv2
+import os
 import numpy as np
-import gradio as gr
+import cv2
 from mtcnn import MTCNN
+from PIL import Image
 from tensorflow.keras.models import load_model
 from tensorflow.keras.applications.xception import preprocess_input as xcp_pre
 from tensorflow.keras.applications.efficientnet import preprocess_input as eff_pre
+from tensorflow.keras.preprocessing.image import img_to_array
 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)
 
+model_xcp = load_model(xcp_path)
+model_eff = load_model(eff_path)
 
-# Load face detector
+# Face detector
 detector = MTCNN()
 
-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)
-    if not faces:
-        return "No face detected", image
+# Prediction function
+def predict_image(image_path):
+    img = cv2.imread(image_path)
+    if img is None:
+        return {"error": "Image could not be loaded"}
 
-    output_image = image.copy()
     results = []
+    faces = detector.detect_faces(img)
 
-    for idx, face in enumerate(faces):
-        x, y, w, h = face['box']
-
-        # Add 20% margin while staying inside bounds
-        margin = 0.2
-        img_h, img_w = image.shape[:2]
-        x = max(0, int(x - w * margin))
-        y = max(0, int(y - h * 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 + 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, ...]
+    # === Single or no face ===
+    if len(faces) <= 1:
+        img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+        img_xcp = xcp_pre(np.expand_dims(cv2.resize(img_rgb, (299, 299)), axis=0))
+        img_eff = eff_pre(np.expand_dims(cv2.resize(img_rgb, (224, 224)), axis=0))
 
-        # 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
+        xcp_pred = model_xcp.predict(img_xcp)[0][0]
+        eff_pred = model_eff.predict(img_eff)[0][0]
+        final_score = (xcp_pred + eff_pred) / 2
+        label = "REAL" if final_score > 0.5 else "FAKE"
 
-        label = "Real" if avg > 0.5 else "Fake"
-        color = (0, 255, 0) if label == "Real" else (0, 0, 255)
+        results.append({"face_id": "whole image", "label": label, "score": round(float(final_score), 3)})
+    else:
+        for idx, face in enumerate(faces):
+            x, y, w, h = face['box']
+            x, y = max(0, x), max(0, y)
+            cropped = img[y:y+h, x:x+w]
 
-        # 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)
+            if cropped.shape[0] < 60 or cropped.shape[1] < 60:
+                continue
 
-        results.append(f"Face {idx+1}: {label} (Avg: {avg:.3f}, XCP: {pred_xcp:.3f}, EFF: {pred_eff:.3f})")
+            face_rgb = cv2.cvtColor(cropped, cv2.COLOR_BGR2RGB)
+            img_xcp = xcp_pre(np.expand_dims(cv2.resize(face_rgb, (299, 299)), axis=0))
+            img_eff = eff_pre(np.expand_dims(cv2.resize(face_rgb, (224, 224)), axis=0))
 
-    return "\n".join(results), output_image
+            xcp_pred = model_xcp.predict(img_xcp)[0][0]
+            eff_pred = model_eff.predict(img_eff)[0][0]
+            final_score = (xcp_pred + eff_pred) / 2
+            label = "REAL" if final_score > 0.5 else "FAKE"
 
-# Gradio Interface
-interface = gr.Interface(
-    fn=predict,
-    inputs=gr.Image(type="numpy", label="Upload Image"),
-    outputs=[
-        gr.Textbox(label="Predictions"),
-        gr.Image(type="numpy", label="Annotated Image"),
-    ],
-    title="Deepfake Detector (Multi-Face Ensemble)",
-    description="Detects all faces in an image and classifies each one as real or fake using Xception and EfficientNetB4 ensemble.",
-)
+            results.append({"face_id": f"face_{idx+1}", "label": label, "score": round(float(final_score), 3)})
 
-interface.launch()
+    return results