Implement background removal using GrabCut algorithm in preprocessing pipeline

app.py

@@ -57,12 +57,48 @@ def extract_lbp_features(gray_img, P=8, R=1, method="uniform"):
     return hist
 
 
+def remove_background(img):
+    """
+    Menghapus background gambar menggunakan GrabCut algorithm
+    """
+    # Buat mask
+    mask = np.zeros(img.shape[:2], np.uint8)
+    
+    # Inisialisasi background dan foreground models
+    bgd_model = np.zeros((1, 65), np.float64)
+    fgd_model = np.zeros((1, 65), np.float64)
+    
+    # Definisikan rectangle di sekitar objek (asumsi objek di tengah)
+    height, width = img.shape[:2]
+    rect = (10, 10, width - 10, height - 10)
+    
+    # Aplikasikan GrabCut
+    cv2.grabCut(img, mask, rect, bgd_model, fgd_model, 5, cv2.GC_INIT_WITH_RECT)
+    
+    # Modifikasi mask: background = 0, foreground = 1
+    mask2 = np.where((mask == 2) | (mask == 0), 0, 1).astype('uint8')
+    
+    # Terapkan mask ke gambar
+    img_no_bg = img * mask2[:, :, np.newaxis]
+    
+    # Ganti background dengan putih
+    img_no_bg[mask2 == 0] = [255, 255, 255]
+    
+    return img_no_bg
+
+
 def preprocessing_pipeline(pil_img):
     img = np.array(pil_img)
 
     # ubah format dari RGBA menjadi RGB
     if img.shape[-1] == 4:
         img = img[:, :, :3]
+    
+    # Resize gambar menjadi 100x100
+    img = cv2.resize(img, (100, 100), interpolation=cv2.INTER_AREA)
+    
+    # Hapus background
+    img = remove_background(img)
 
     img_float = img.astype(np.float32) / 255.0
     img_uint8 = (img_float * 255).astype(np.uint8)