Update app.py

app.py

@@ -4,97 +4,114 @@ import cv2
 import matplotlib.pyplot as plt
 from PIL import Image, ImageChops, ImageEnhance
 from scipy import ndimage
-import io, json, warnings
+import io, warnings
 
 warnings.filterwarnings("ignore")
 
 # ═══════════════════════════════════════════════════
-# 🛡️ MEDIASHIELD X IMAGESHIELD (FUSION v3.0)
-# Calibration spéciale : Archives & Mode Sombre
+# 🛡️ MEDIASHIELD v3.0 — ARCHIVE & FORENSIC SUITE
 # ═══════════════════════════════════════════════════
 
 def apply_gamma_correction(img):
-    """Prépare l'image pour l'analyse si elle est trop sombre."""
+    """Prépare l'image pour l'analyse si elle est trop sombre (Archives)."""
     gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
     brightness = np.mean(gray)
     if brightness < 65:
-        # Correction pour révéler les artefacts de compression dans l'ombre
         gamma = 0.6
         invGamma = 1.0 / gamma
         table = np.array([((i / 255.0) ** invGamma) * 255 for i in np.arange(0, 256)]).astype("uint8")
         return cv2.LUT(img, table), f"🌙 Mode Sombre (Lumière: {brightness:.1f})"
     return img, "☀️ Lumière Standard"
 
+def verify_natural_grain(img):
+    """Distingue le lissage IA du grain organique d'une photo réelle."""
+    gray = cv2.cvtColor(img, cv2.COLOR_RGB2GRAY)
+    local_var = ndimage.generic_filter(gray, np.var, size=3)
+    avg_var = np.mean(local_var)
+    # Un score très bas (< 0.8) indique une texture mathématiquement 'trop' parfaite (IA)
+    if avg_var < 0.8:
+        return True, avg_var
+    return False, avg_var
+
 def analyze_forensics(img_input):
-    if img_input is None: return None, "❌ Aucune image"
+    if img_input is None: return None, "❌ Aucune image chargée."
     
-    # 1. Préparation (Correction de lumière S2T)
+    # 1. Nettoyage et Correction Gamma
     img_cv = cv2.cvtColor(img_input, cv2.COLOR_RGBA2RGB) if img_input.shape[2] == 4 else img_input.copy()
     img_ready, light_msg = apply_gamma_correction(img_cv)
     pil_img = Image.fromarray(img_ready)
 
-    # 2. Analyse de Chrominance (Signatures Nano Banana)
+    # 2. Analyse du Grain (Anti-Faux Positifs Archives)
+    is_too_smooth, grain_val = verify_natural_grain(img_ready)
+
+    # 3. Analyse de Chrominance (Signatures Couleurs IA)
     ycrcb = cv2.cvtColor(img_ready, cv2.COLOR_RGB2YCrCb)
     cr_var = ndimage.generic_filter(ycrcb[:,:,1], np.var, size=5)
-    chroma_score = np.std(cr_var) / (np.mean(cr_var) + 1e-8)
+    chroma_uniformity = np.std(cr_var) / (np.mean(cr_var) + 1e-8)
 
-    # 3. FFT & Grid Patterns (Signatures GAN/Diffusion)
-    gray = cv2.cvtColor(img_ready, cv2.COLOR_RGB2GRAY).astype(np.float32)
-    f_shift = np.fft.fftshift(np.fft.fft2(gray))
-    magnitude = np.abs(f_shift)
-    fft_vis = np.log(magnitude + 1)
+    # 4. FFT (Recherche de motifs de grille IA)
+    gray_f = cv2.cvtColor(img_ready, cv2.COLOR_RGB2GRAY).astype(np.float32)
+    f_shift = np.fft.fftshift(np.fft.fft2(gray_f))
+    fft_vis = np.log(np.abs(f_shift) + 1)
     
-    # 4. ELA (Error Level Analysis)
-    quality = 90
+    # 5. ELA (Error Level Analysis)
     buf = io.BytesIO()
-    pil_img.save(buf, format="JPEG", quality=quality)
+    pil_img.save(buf, format="JPEG", quality=90)
     recomp = Image.open(io.BytesIO(buf.getvalue())).convert("RGB")
     ela_diff = ImageChops.difference(pil_img, recomp)
     ela_vis = ImageEnhance.Brightness(ela_diff).enhance(10)
 
-    # 5. Calcul du Score Final
+    # 6. Système de Score S2T Ariana
     score = 0
     reasons = []
-    if chroma_score < 0.9: 
-        score += 35
-        reasons.append("⚠️ Bruit chromatique trop uniforme (Typique IA)")
-    if np.std(magnitude) > 100000: # Seuil simplifié
+
+    if is_too_smooth:
+        score += 25
+        reasons.append(f"⚡ Texture suspecte (Grain trop faible: {grain_val:.2f})")
+    else:
+        score -= 10
+        reasons.append("✅ Grain organique détecté (Photo réelle)")
+
+    if chroma_uniformity < 0.9: 
         score += 30
-        reasons.append("🔮 Artefacts de fréquence détectés (FFT)")
+        reasons.append("⚠️ Bruit chromatique uniforme (Signature IA)")
+
     if np.mean(np.array(ela_diff)) < 1.2:
-        score += 25
+        score += 20
         reasons.append("🔍 Compression suspecte (ELA trop lisse)")
 
-    final_verdict = "🔴 TRÈS PROBABLEMENT IA" if score > 60 else "🟢 PROBABLEMENT RÉEL"
+    # Bornage du score
+    score = max(0, min(100, score))
+    verdict = "🔴 IA DÉTECTÉE" if score > 55 else "🟠 SUSPECT" if score > 35 else "🟢 AUTHENTIQUE"
     
-    # Visualisation
+    # Visualisation des preuves
     fig, axes = plt.subplots(1, 3, figsize=(15, 5))
     axes[0].imshow(img_cv); axes[0].set_title(f'Original ({light_msg})')
-    axes[1].imshow(fft_vis, cmap='viridis'); axes[1].set_title('Fréquences (FFT)')
-    axes[2].imshow(ela_vis); axes[2].set_title('Analyse ELA')
+    axes[1].imshow(fft_vis, cmap='magma'); axes[1].set_title('Spectre Fréquence (FFT)')
+    axes[2].imshow(ela_vis); axes[2].set_title('Analyse ELA (Compression)')
     for ax in axes: ax.axis('off')
+    plt.tight_layout()
     
-    report = f"🛡️ MEDIASHIELD v3.0\nVERDICT: {final_verdict}\nScore: {score}/100\n\n{light_msg}\n\n" + "\n".join(reasons)
+    report = f"🛡️ RAPPORT MEDIASHIELD v3.0\nVERDICT : {verdict}\nIndice de confiance IA : {score}/100\n\nDiagnostic :\n" + "\n".join(reasons)
     return fig, report
 
 # ═══════════════════════════════════════════════════
-# UI Ariana Edition
+# INTERFACE UTILISATEUR (GRADIO)
 # ═══════════════════════════════════════════════════
 
 with gr.Blocks(title="MediaShield v3.0", theme=gr.themes.Soft()) as demo:
-    gr.Markdown("# 🛡️ MediaShield v3.0 — Forensic Archive Suite")
-    gr.Markdown("Fusion du moteur ImageShield et du correcteur optique MediaShield.")
+    gr.Markdown("# 🛡️ MediaShield v3.0")
+    gr.Markdown("**Expertise Forensic S2T** : Détection IA, analyse de grain et correction d'archives.")
     
     with gr.Row():
-        with gr.Column():
-            input_file = gr.Image(label="Dépôt d'archive numérique", type="numpy")
-            run_btn = gr.Button("DÉMARRER L'ANALYSE FORENSIC", variant="primary")
-        with gr.Column():
-            output_plot = gr.Plot(label="Cartographie des signaux")
-            output_text = gr.Textbox(label="Rapport d'expertise S2T", lines=8)
+        with gr.Column(scale=1):
+            input_file = gr.Image(label="Charger une image (Photo ou Archive)", type="numpy")
+            run_btn = gr.Button("LANCER L'ANALYSE", variant="primary")
+        with gr.Column(scale=2):
+            output_plot = gr.Plot(label="Preuves visuelles")
+            output_text = gr.Textbox(label="Rapport d'expertise", lines=10)
 
     run_btn.click(analyze_forensics, inputs=input_file, outputs=[output_plot, output_text])
 
 if __name__ == "__main__":
-    demo.launch()
-
+    demo.launch()