Merge pull request #7 from PaddlePaddle/develop

update-2020-7-29

ppocr/utils/utility.py

@@ -14,6 +14,7 @@
 
 import logging
 import os
+import imghdr
 
 
 def initial_logger():
@@ -61,13 +62,14 @@ def get_image_file_list(img_file):
     if img_file is None or not os.path.exists(img_file):
         raise Exception("not found any img file in {}".format(img_file))
 
-    img_end = ['jpg', 'png', 'jpeg', 'JPEG', 'JPG', 'bmp']
-    if os.path.isfile(img_file) and img_file.split('.')[-1] in img_end:
+    img_end = {'jpg', 'bmp', 'png', 'jpeg', 'rgb', 'tif', 'tiff'}
+    if os.path.isfile(img_file) and imghdr.what(img_file) in img_end:
         imgs_lists.append(img_file)
     elif os.path.isdir(img_file):
         for single_file in os.listdir(img_file):
-            if single_file.split('.')[-1] in img_end:
-                imgs_lists.append(os.path.join(img_file, single_file))
+            file_path = os.path.join(img_file, single_file)
+            if imghdr.what(file_path) in img_end:
+                imgs_lists.append(file_path)
     if len(imgs_lists) == 0:
         raise Exception("not found any img file in {}".format(img_file))
     return imgs_lists