From 09ff249363fd58a16fe0b6370bae181ce6a550c8 Mon Sep 17 00:00:00 2001
From: Topdu <784990967@qq.com>
Date: Mon, 15 Aug 2022 10:42:02 +0000
Subject: [PATCH] update arabic rec model & add pred reverse function

---
 .../multi_language/arabic_PP-OCRv3_rec.yml    |  2 +-
 ppocr/postprocess/rec_postprocess.py          | 25 +++++++++++++++++++
 ppocr/utils/dict/arabic_dict.txt              |  1 -
 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/configs/rec/PP-OCRv3/multi_language/arabic_PP-OCRv3_rec.yml b/configs/rec/PP-OCRv3/multi_language/arabic_PP-OCRv3_rec.yml
index 0ad1ab0a..8c650bd8 100644
--- a/configs/rec/PP-OCRv3/multi_language/arabic_PP-OCRv3_rec.yml
+++ b/configs/rec/PP-OCRv3/multi_language/arabic_PP-OCRv3_rec.yml
@@ -12,7 +12,7 @@ Global:
   checkpoints:
   save_inference_dir:
   use_visualdl: false
-  infer_img: doc/imgs_words/ch/word_1.jpg
+  infer_img: ./doc/imgs_words/arabic/ar_2.jpg
   character_dict_path: ppocr/utils/dict/arabic_dict.txt
   max_text_length: &max_text_length 25
   infer_mode: false
diff --git a/ppocr/postprocess/rec_postprocess.py b/ppocr/postprocess/rec_postprocess.py
index 7b994f81..e8a1cd42 100644
--- a/ppocr/postprocess/rec_postprocess.py
+++ b/ppocr/postprocess/rec_postprocess.py
@@ -45,6 +45,27 @@ class BaseRecLabelDecode(object):
             self.dict[char] = i
         self.character = dict_character
 
+        if 'arabic' in character_dict_path:
+            self.reverse = True
+        else:
+            self.reverse = False
+
+    def pred_reverse(self, pred):
+        pred_re = []
+        c_current = ''
+        for c in pred:
+            if c in self.character[79:]:
+                if c_current != '':
+                    pred_re.append(c_current)
+                pred_re.append(c)
+                c_current = ''
+            else:
+                c_current += c
+        if c_current != '':
+            pred_re.append(c_current)
+
+        return ''.join(pred_re[::-1])
+
     def add_special_char(self, dict_character):
         return dict_character
 
@@ -73,6 +94,10 @@ class BaseRecLabelDecode(object):
                 conf_list = [0]
 
             text = ''.join(char_list)
+
+            if self.reverse:  # for arabic rec
+                text = self.pred_reverse(text)
+
             result_list.append((text, np.mean(conf_list).tolist()))
         return result_list
 
diff --git a/ppocr/utils/dict/arabic_dict.txt b/ppocr/utils/dict/arabic_dict.txt
index e97abf39..916d421c 100644
--- a/ppocr/utils/dict/arabic_dict.txt
+++ b/ppocr/utils/dict/arabic_dict.txt
@@ -1,4 +1,3 @@
- 
 !
 #
 $
-- 
GitLab