From a1ca342a97163e7a73a10e21c6849ed6b7dbc78a Mon Sep 17 00:00:00 2001
From: Recolic Keghart <root@recolic.net>
Date: Sun, 17 May 2020 20:30:12 +0800
Subject: [PATCH] Add hust_code OCR
---
hust_code.py | 50 +++++++++++++++++++++++++++++++-------------------
1 file changed, 31 insertions(+), 19 deletions(-)
diff --git a/hust_code.py b/hust_code.py
index 8f3ded4..34e6138 100644
--- a/hust_code.py
+++ b/hust_code.py
@@ -1,26 +1,38 @@
from PIL import Image
-import sys
+import sys, subprocess
-i, o = sys.argv[1:]
+tmp_fname = '/tmp/.recolic-hust.ocr-tmp.png'
-im = Image.open(i)
-# In pass.hust.edu.cn verification code, the second frame is COMPLETE!
-# let's get the second frame.
-im.seek(im.tell()+1)
-im.save(o)
+def prepare_ocr(input_fname, output_fname):
+ im = Image.open(input_fname)
+ # In pass.hust.edu.cn verification code, the second frame is COMPLETE!
+ # let's get the second frame.
+ im.seek(im.tell()+1)
+
+ # To white-black
+ im = im.convert('L')
+ im = im.point(lambda x: 0 if x<254 else 255, '1')
+ # Try to crop. The Silly ocr doesn't like a single_line good image...
+ # Should use `tesseract output.png stdout --psm 8 -c tessedit_char_whitelist=0123456789` for cropped image.
+ #w, h = im.size
+ #if w == 90 and h == 58:
+ # im = im.crop((0, 18, w, 39))
+ #else:
+ # print('WARNING: Expected image w=90, h=58, Got image w={}, h={}.'.format(w, h))
+ # Save for OCR
+ im.save(output_fname)
-im = Image.open(o)
-# To white-black
-im = im.convert('L')
-im = im.point(lambda x: 0 if x<254 else 255, '1')
-# Try to crop
-w, h = im.size
-if w == 90 and h == 58:
- im = im.crop((0, 18, w, 39))
-else:
- print('WARNING: Expected image w=90, h=58, Got image w={}, h={}.'.format(w, h))
-# Save for OCR
-im.save(o)
+def do_ocr(input_fname):
+ output = subprocess.check_output(['tesseract', input_fname, 'stdout']).decode('utf-8')
+ for line in output.split('\n'):
+ line = line.strip()
+ if len(line) == 4 and line.isdigit():
+ return line
+ return None
+#i = sys.argv[1]
+#prepare_ocr(i, tmp_fname)
+#print(do_ocr(tmp_fname))
+def recognize_hust_code()
--
GitLab