diff --git a/Applications/DocXChain/modules/text_recognition.py b/Applications/DocXChain/modules/text_recognition.py
index d76301e..b0f676c 100644
--- a/Applications/DocXChain/modules/text_recognition.py
+++ b/Applications/DocXChain/modules/text_recognition.py
@@ -54,9 +54,11 @@ def __call__(self, image, detections):
             for i in range(detections.shape[0]):  # this part can be largely accelerated via parallelization (leave for future work)
                 pts = self.order_point(detections[i])
                 image_crop = self.crop_image(image, pts)
-                rec = self.text_recognizer(image_crop)
+                try:
+                    rec = self.text_recognizer(image_crop)
+                except:
+                    rec = {'text': ['']}
                 result.append(rec)
-
         return result
 
     def recognize_cropped_image(self, cropped_image):
@@ -153,4 +155,4 @@ def release(self):
         if self.text_recognizer is not None:
             del self.text_recognizer
 
-        return 
\ No newline at end of file
+        return