diff --git a/src/erase_leastcommon.py b/src/erase_leastcommon.py
index bef06d9..a3f6f87 100644
--- a/src/erase_leastcommon.py
+++ b/src/erase_leastcommon.py
@@ -46,8 +46,8 @@ def filternone(word_raw):
 x = -1
 leastcommon_list = []
 allwords = []
-scanimg = glob.glob('images-tiff/*.tiff')
-hocr = glob.glob('hocr/*.html')
+scanimg = sorted(glob.glob('images-tiff/*.tiff'))
+hocr = sorted(glob.glob('hocr/*.html'))
 maximum = 20 / len(scanimg) # this helps the script remove words in a way that is proportional to number of pages scanned 
 
 # loop through every image in scanimg folder
diff --git a/src/replace_leastcommon.py b/src/replace_leastcommon.py
index faa697b..cf15de0 100644
--- a/src/replace_leastcommon.py
+++ b/src/replace_leastcommon.py
@@ -63,8 +63,8 @@ def filternone(word_raw):
 x = -1
 leastcommon_list = []
 allwords = []
-scanimg = glob.glob('images-tiff/*.tiff')
-hocr = glob.glob('hocr/*.html')
+scanimg = sorted(glob.glob('images-tiff/*.tiff'))
+hocr = sorted(glob.glob('hocr/*.html'))
 num = 0
 maximum = 20 / len(scanimg) # this helps the script remove words in a way that is proportional to number of pages scanned