Update app.py

app.py

@@ -1,62 +1,80 @@
 import gradio as gr
 from transformers import pipeline
-from PIL import Image
+from PIL import Image, ExifTags, ImageStat, ImageFilter
+import numpy as np
 
 # Model utama untuk deteksi AI
-detector = pipeline("image-classification", model="umm-maybe/AI-image-detector")  
+detector = pipeline("image-classification", model="umm-maybe/AI-image-detector")
 
-# Model tambahan general (backup)
+# Model tambahan general classifier (backup)
 general = pipeline("image-classification", model="google/vit-base-patch16-224")
 
-def detect_image(img):
+def analyze_noise(img):
+    gray = img.convert("L")
+    arr = np.array(gray)
+    return np.std(arr)  # Standar deviasi → noise
+
+def analyze_blur(img):
+    gray = img.convert("L")
+    arr = np.array(gray)
+    lap = cv2.Laplacian(arr, cv2.CV_64F).var()
+    return lap  # Variansi Laplacian → blur
+
+def metadata_score(img):
     try:
-        # Prediksi dengan AI detector
+        exif = img._getexif()
+        if exif is None:
+            return 1  # Tidak ada metadata → kemungkinan AI
+        for tag, value in exif.items():
+            decoded = ExifTags.TAGS.get(tag, tag)
+            if decoded == "Make" or decoded == "Model":
+                return 0  # Ada kamera → kemungkinan asli
+        return 1
+    except:
+        return 1
+
+def detect_image(img: Image.Image):
+    try:
+        # Prediksi AI-detector
         result1 = detector(img)
-        label1 = result1[0]['label'].lower()
-        conf1 = result1[0]['score'] * 100
+        label1 = result1[0]['label']
+        conf1 = result1[0]['score']  # 0-1
 
-        # Prediksi dengan model general
+        # Prediksi general model
         result2 = general(img)
-        conf2 = result2[0]['score'] * 100
+        label2 = result2[0]['label']
+        conf2 = result2[0]['score']
 
-        # Kombinasi skor untuk hybrid
-        # Logika: AI detector > 50% dianggap AI, <50% dianggap asli
-        if "fake" in label1 or "artificial" in label1:
-            ai_score = conf1
-            real_score = 100 - ai_score
-        elif "human" in label1 or "real" in label1:
-            real_score = conf1
-            ai_score = 100 - real_score
-        else:
-            # fallback jika label tidak spesifik
-            ai_score = conf1 / 2
-            real_score = 100 - ai_score
+        # Analisis blur & noise
+        noise = analyze_noise(img)
+        try:
+            import cv2
+            blur = analyze_blur(img)
+        except:
+            blur = 0
 
-        # Sensitivitas tambahan: jika AI photorealistic tapi AI score rendah
-        # gunakan hasil general model sebagai penyesuaian
-        ai_score += conf2 * 0.1
-        real_score = 100 - ai_score
+        # Metadata
+        meta = metadata_score(img)
 
-        # Batasi 0-100
-        ai_score = max(0, min(100, round(ai_score, 2)))
-        real_score = max(0, min(100, round(real_score, 2)))
+        # Weighted skor akhir (lebih sensitif terhadap AI photorealistic)
+        ai_score = conf1 * 0.6 + meta * 0.2 + (1 - min(noise/100,1)) * 0.1 + (1 - min(blur/1000,1)) * 0.1
+        ai_score = min(max(ai_score, 0), 1)  # Clamp 0-1
+        human_score = 1 - ai_score
 
-        if ai_score == 100:
-            final = "🖼️ Gambar ini 100% Hasil AI"
-        elif real_score == 100:
-            final = "🖼️ Gambar ini 100% Asli"
-        else:
-            final = f"🖼️ Gambar ini {ai_score}% AI / {real_score}% Asli"
+        ai_percent = round(ai_score * 100, 2)
+        human_percent = round(human_score * 100, 2)
 
         output = f"""
 ### Hasil Deteksi:
-{final}
+🖼️ Gambar ini {ai_percent}% AI / {human_percent}% Asli
 
-**Model AI-detector:** {label1} ({round(conf1,2)}%)
-**Model General (ViT):** {result2[0]['label']} ({round(conf2,2)}%)
+**Model AI-detector:** {label1} ({round(conf1*100,2)}%)  
+**Model General (ViT):** {label2} ({round(conf2*100,2)}%)  
+**Blur Score:** {round(blur,2)}  
+**Noise Score:** {round(noise,2)}  
+**Metadata Kamera:** {"Ada" if meta==0 else "Tidak Ada"}
 """
         return output
-
     except Exception as e:
         return f"Terjadi error: {str(e)}"
 
@@ -64,8 +82,8 @@ iface = gr.Interface(
     fn=detect_image,
     inputs=gr.Image(type="pil"),
     outputs="markdown",
-    title="AI vs Real Image Detector Hybrid",
-    description="Upload foto untuk mendeteksi persentase kemungkinan AI vs Asli."
+    title="Hybrid AI vs Foto Asli Detector",
+    description="Upload foto untuk mendeteksi persentase AI vs foto asli. Lebih sensitif terhadap AI photorealistic."
 )
 
 if __name__ == "__main__":