Refactor preprocessing pipeline to integrate image background removal and resizing functionality

app.py

@@ -57,12 +57,80 @@ def extract_lbp_features(gray_img, P=8, R=1, method="uniform"):
     return hist
 
 
-def preprocessing_pipeline(pil_img):
-    img = np.array(pil_img)
+def preprocess_image_like_dataset(pil_img, target_size=100):
+    """
+    Preprocessing gambar dari luar dataset menjadi seperti dataset:
+    - Background putih
+    - Ukuran 100x100
+    - Fokus pada buah (centered dan cropped)
+    """
+    # Step 1: Hapus background menggunakan rembg (AI-powered background removal)
+    img_no_bg = remove(pil_img)
+    img_array = np.array(img_no_bg)
+    
+    # Step 2: Konversi RGBA ke RGB dengan background putih
+    if img_array.shape[-1] == 4:
+        # Ambil channel alpha
+        alpha = img_array[:, :, 3] / 255.0
+        rgb = img_array[:, :, :3]
+        
+        # Gabungkan dengan background putih
+        white_bg = np.ones_like(rgb) * 255
+        img_array = (rgb * alpha[:, :, np.newaxis] + white_bg * (1 - alpha[:, :, np.newaxis])).astype(np.uint8)
+    
+    # Step 3: Crop ke bounding box objek (hilangkan whitespace)
+    # Konversi ke grayscale untuk deteksi objek
+    gray = cv2.cvtColor(img_array, cv2.COLOR_RGB2GRAY)
+    # Threshold untuk menemukan objek (non-putih)
+    _, thresh = cv2.threshold(gray, 250, 255, cv2.THRESH_BINARY_INV)
+    
+    # Temukan contours
+    contours, _ = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
+    
+    if contours:
+        # Gabungkan semua contours untuk mendapat bounding box total
+        all_contours = np.vstack(contours)
+        x, y, w, h = cv2.boundingRect(all_contours)
+        
+        # Tambahkan padding 5% untuk memberikan sedikit ruang
+        padding = int(max(w, h) * 0.05)
+        x = max(0, x - padding)
+        y = max(0, y - padding)
+        w = min(img_array.shape[1] - x, w + 2 * padding)
+        h = min(img_array.shape[0] - y, h + 2 * padding)
+        
+        # Crop gambar
+        img_cropped = img_array[y:y+h, x:x+w]
+    else:
+        img_cropped = img_array
+    
+    # Step 4: Resize dengan mempertahankan aspect ratio dan center pada canvas putih 100x100
+    h, w = img_cropped.shape[:2]
+    
+    # Hitung scaling factor (fit ke target_size dengan margin)
+    scale = (target_size * 0.9) / max(h, w)  # 0.9 untuk margin
+    new_w = int(w * scale)
+    new_h = int(h * scale)
+    
+    # Resize objek
+    img_resized = cv2.resize(img_cropped, (new_w, new_h), interpolation=cv2.INTER_AREA)
+    
+    # Buat canvas putih 100x100
+    canvas = np.ones((target_size, target_size, 3), dtype=np.uint8) * 255
+    
+    # Hitung posisi untuk center objek
+    y_offset = (target_size - new_h) // 2
+    x_offset = (target_size - new_w) // 2
+    
+    # Letakkan objek di tengah canvas
+    canvas[y_offset:y_offset+new_h, x_offset:x_offset+new_w] = img_resized
+    
+    return canvas
+
 
-    # ubah format dari RGBA menjadi RGB
-    if img.shape[-1] == 4:
-        img = img[:, :, :3]
+def preprocessing_pipeline(pil_img):
+    # Preprocessing gambar menjadi 100x100 dengan background putih
+    img = preprocess_image_like_dataset(pil_img, target_size=100)
 
     img_float = img.astype(np.float32) / 255.0
     img_uint8 = (img_float * 255).astype(np.uint8)
@@ -98,13 +166,18 @@ def index():
         if file:
             try:
                 image = Image.open(file.stream)
+                
+                # Preprocessing image untuk prediksi dan tampilan
+                features = preprocessing_pipeline(image)
+                
+                # Gunakan gambar yang sudah di-preprocessing untuk ditampilkan
+                preprocessed_img = preprocess_image_like_dataset(image, target_size=100)
+                preprocessed_pil = Image.fromarray(preprocessed_img)
+                
                 img_io = io.BytesIO()
-                image.save(img_io, "PNG")
+                preprocessed_pil.save(img_io, "PNG")
                 encoded_img = base64.b64encode(img_io.getvalue()).decode("ascii")
                 img_data = f"data:image/png;base64, {encoded_img}"
-
-
-                features = preprocessing_pipeline(image)
                 
                 # Prediksi dengan probabilitas
                 pred_index = model.predict(features)[0]