diff --git a/README.md b/README.md
index 33995acb..8a70c8cf 100644
--- a/README.md
+++ b/README.md
@@ -37,10 +37,10 @@ tar -xf inference.tar
 export PYTHONPATH=.
 
 # 预测image_dir指定的单张图像
-python tools/infer/predict_system.py --image_dir="/Demo.jpg" --det_model_dir="./inference/det/"  --rec_model_dir="./inference/rec/"
+python3 tools/infer/predict_system.py --image_dir="./demo.jpg" --det_model_dir="./inference/det/"  --rec_model_dir="./inference/rec/"
 
 # 预测image_dir指定的图像集合
-python tools/infer/predict_system.py --image_dir="/test_imgs/" --det_model_dir="./inference/det/"  --rec_model_dir="./inference/rec/"
+python3 tools/infer/predict_system.py --image_dir="./infer_imgs/" --det_model_dir="./inference/det/"  --rec_model_dir="./inference/rec/"
 ```
 更多的文本检测、识别串联推理使用方式请参考文档教程中[基于推理引擎预测](./doc/inference.md)。
 
diff --git a/ppocr/postprocess/db_postprocess.py b/ppocr/postprocess/db_postprocess.py
index 3f6a0514..b8e18e66 100644
--- a/ppocr/postprocess/db_postprocess.py
+++ b/ppocr/postprocess/db_postprocess.py
@@ -46,9 +46,11 @@ class DBPostProcess(object):
         bitmap = _bitmap
         height, width = bitmap.shape
 
-        # img, contours, _ = cv2.findContours((bitmap * 255).astype(np.uint8), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
-        contours, _ = cv2.findContours((bitmap * 255).astype(np.uint8),
-                                       cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
+        outs = cv2.findContours((bitmap * 255).astype(np.uint8), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
+        if len(outs) == 3:
+            img, contours, _ = outs[0], outs[1], outs[2]
+        elif len(outs) == 2:
+            contours, _ = outs[0], outs[1]
 
         num_contours = min(len(contours), self.max_candidates)
         boxes = np.zeros((num_contours, 4, 2), dtype=np.int16)
diff --git a/tools/infer/predict_system.py b/tools/infer/predict_system.py
index 83acdbe5..3c9bc821 100755
--- a/tools/infer/predict_system.py
+++ b/tools/infer/predict_system.py
@@ -84,7 +84,7 @@ def sorted_boxes(dt_boxes):
     """
     Sort text boxes in order from top to bottom, left to right
     args:
-        dt_boxes(array)：detected text boxes with shape [4, 2]
+        dt_boxes(array):detected text boxes with shape [4, 2]
     return:
         sorted boxes(array) with shape [4, 2]
     """
@@ -108,6 +108,7 @@ if __name__ == "__main__":
     is_visualize = True
     for image_file in image_file_list:
         img = cv2.imread(image_file)
+        print(img.shape)
         if img is None:
             logger.info("error in loading image:{}".format(image_file))
             continue