Update app.py

app.py

@@ -1,120 +1,87 @@
 import gradio as gr
 from transformers import pipeline
 from PIL import Image, ExifTags
-import numpy as np
 import cv2
+import numpy as np
+
+# Model Hugging Face untuk AI vs Human
+detector = pipeline("image-classification", model="microsoft/resnet-50")
 
-# Model utama AI-detector
-detector = pipeline("image-classification", model="umm-maybe/AI-image-detector")
+def analyze_image(image):
+    # Convert ke format OpenCV
+    img_cv = cv2.cvtColor(np.array(image), cv2.COLOR_RGB2BGR)
 
-# Model backup (general classifier)
-general = pipeline("image-classification", model="google/vit-base-patch16-224")
+    # ---- 1. Prediksi dengan model HF ----
+    preds = detector(image)
+    ai_score = 0.0
+    human_score = 0.0
+    for p in preds:
+        if "artificial" in p["label"].lower() or "ai" in p["label"].lower():
+            ai_score += p["score"]
+        else:
+            human_score += p["score"]
 
-def analyze_image(img_pil):
-    img = np.array(img_pil)
+    # Normalisasi biar total 1
+    total = ai_score + human_score
+    if total > 0:
+        ai_score /= total
+        human_score /= total
 
-    # Blur detection (variance of Laplacian)
-    gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
+    # ---- 2. Analisis blur/noise ----
+    gray = cv2.cvtColor(img_cv, cv2.COLOR_BGR2GRAY)
     blur_score = cv2.Laplacian(gray, cv2.CV_64F).var()
-
-    # Noise estimation (std deviation)
     noise_score = np.std(gray)
 
-    # Edge consistency
-    edges = cv2.Canny(gray, 100, 200)
-    edge_score = np.std(edges)
-
-    # JPEG artifacts (kasar: std dev dari DCT block)
-    dct = cv2.dct(np.float32(gray) / 255.0)
-    jpeg_artifact = np.std(dct)
+    # Semakin kecil blur/noise → semakin cenderung AI
+    blur_factor = 1.0 if blur_score < 100 else 0.0
+    noise_factor = 1.0 if noise_score < 20 else 0.0
 
-    # Metadata kamera
-    metadata = "Tidak Ada"
+    # ---- 3. Cek metadata kamera ----
+    has_metadata = False
     try:
-        exif_data = img_pil._getexif()
-        if exif_data:
-            metadata = "Ada"
+        exif = image._getexif()
+        if exif is not None:
+            for tag, value in exif.items():
+                decoded = ExifTags.TAGS.get(tag, tag)
+                if decoded in ["Make", "Model"]:
+                    has_metadata = True
     except:
         pass
 
-    return blur_score, noise_score, edge_score, jpeg_artifact, metadata
-
-def detect_image(img):
-    try:
-        # Prediksi AI-detector
-        result1 = detector(img)
-        label1 = result1[0]['label']
-        conf1 = round(result1[0]['score'] * 100, 2)
-
-        # Prediksi model general
-        result2 = general(img)
-        label2 = result2[0]['label']
-        conf2 = round(result2[0]['score'] * 100, 2)
-
-        # Analisis teknis
-        blur, noise, edge, jpeg_art, metadata = analyze_image(img)
-
-        # --- Voting System ---
-        ai_score = 0
-        real_score = 0
-
-        # Dari model AI-detector
-        if "fake" in label1.lower() or "artificial" in label1.lower():
-            ai_score += conf1
-        elif "real" in label1.lower() or "human" in label1.lower():
-            real_score += conf1
-
-        # Dari metadata
-        if metadata == "Ada":
-            real_score += 30  # bobot ekstra untuk foto asli
-        else:
-            ai_score += 20
-
-        # Dari noise & blur
-        if noise > 20 and blur > 50:
-            real_score += 20
-        else:
-            ai_score += 10
-
-        # Hasil akhir
-        total = ai_score + real_score + 1e-6
-        ai_pct = round((ai_score / total) * 100, 2)
-        real_pct = round((real_score / total) * 100, 2)
-
-        if ai_pct > real_pct:
-            final = f"⚠️ Kemungkinan Besar AI Generated ({ai_pct}%)"
-        else:
-            final = f"✅ Kemungkinan Besar Foto Asli ({real_pct}%)"
-
-        output = f"""
-### Hasil Deteksi:
-{final}
-
-**Persentase AI:** {ai_pct}%  
-**Persentase Asli:** {real_pct}%
-
-**Model AI-detector:** {label1} ({conf1}%)  
-**Model General (ViT):** {label2} ({conf2}%)
-
-**Analisis Kamera & Teknis:**  
-- Blur Score: {round(blur,2)}  
-- Noise Score: {round(noise,2)}  
-- Edge Consistency (STD): {round(edge,2)}  
-- JPEG Artifact Level: {round(jpeg_art,2)}  
-- Metadata Kamera: {metadata}
-"""
-        return output
-    except Exception as e:
-        return f"Terjadi error: {str(e)}"
-
-# UI Gradio
-iface = gr.Interface(
-    fn=detect_image,
+    metadata_factor = 0.0 if has_metadata else 1.0
+
+    # ---- 4. Ensemble skor ----
+    final_score = (
+        0.6 * ai_score +
+        0.2 * blur_factor +
+        0.1 * noise_factor +
+        0.1 * metadata_factor
+    )
+
+    result = "AI Generated" if final_score > 0.5 else "Foto Asli"
+
+    # ---- 5. Hasil detail ----
+    details = f"""
+    🔍 Hasil Deteksi:
+    {result}
+
+    Skor Model AI-detector: {ai_score:.2f}
+    Skor Human: {human_score:.2f}
+    Blur Score: {blur_score:.2f}
+    Noise Score: {noise_score:.2f}
+    Metadata Kamera: {"Ada" if has_metadata else "Tidak Ada"}
+    Final Score: {final_score:.2f}
+    """
+    return details
+
+# Gradio UI
+demo = gr.Interface(
+    fn=analyze_image,
     inputs=gr.Image(type="pil"),
-    outputs="markdown",
-    title="AI vs Real Image Detector (Hybrid)",
-    description="Deteksi AI vs Foto Asli dengan kombinasi model + analisis teknis (blur, noise, edge, metadata)."
+    outputs="text",
+    title="AI vs Real Image Detector",
+    description="Upload foto untuk mendeteksi apakah gambar asli atau hasil AI."
 )
 
 if __name__ == "__main__":
-    iface.launch()
+    demo.launch()