diff --git a/doc/table/layout.jpg b/doc/table/layout.jpg
new file mode 100644
index 0000000000000000000000000000000000000000..db7246b314556d73cd49d049b9b480887b6ef994
Binary files /dev/null and b/doc/table/layout.jpg differ
diff --git a/doc/table/layout.png b/doc/table/layout.png
deleted file mode 100644
index d8b56701f611593b2188c8d4844966ab48a8fb91..0000000000000000000000000000000000000000
Binary files a/doc/table/layout.png and /dev/null differ
diff --git a/ppstructure/layout/README.md b/ppstructure/layout/README.md
index a193ffd3b979535bed003dc884c2c34adf24b701..fde6d75a4d278551aba77075c3f9789a24a01b21 100644
--- a/ppstructure/layout/README.md
+++ b/ppstructure/layout/README.md
@@ -26,7 +26,7 @@ pip install -U https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-a
 ```python
 import cv2
 import layoutparser as lp
-image = cv2.imread("doc/table/layout.png")
+image = cv2.imread("doc/table/layout.jpg")
 image = image[..., ::-1]
 
 # 加载模型
diff --git a/ppstructure/layout/README_en.md b/ppstructure/layout/README_en.md
index d94b2aa47ef10724d23ce0ff813dffdd7dde6eb7..2d885c567b15d305602e9fb00058c4cf281de041 100644
--- a/ppstructure/layout/README_en.md
+++ b/ppstructure/layout/README_en.md
@@ -27,7 +27,7 @@ Use LayoutParser to identify the layout of a given document:
 ```python
 import cv2
 import layoutparser as lp
-image = cv2.imread("doc/table/layout.png")
+image = cv2.imread("doc/table/layout.jpg")
 image = image[..., ::-1]
 
 # load model