From e11fecc2ddde37842d79037e39ffbc4a3a89baca Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E2=80=9C1715109585=E2=80=9D?= <1715109585@qq.com>
Date: Sat, 18 Feb 2023 23:56:45 +0800
Subject: [PATCH] =?UTF-8?q?=E6=9B=B4=E6=96=B0=E6=96=87=E5=AD=97=E8=AF=86?=
 =?UTF-8?q?=E5=88=AB=E7=9A=84=E6=A8=A1=E5=9D=97?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 ...07\345\255\227\350\257\206\345\210\253.py" | 35 +++++++++++++------
 1 file changed, 24 insertions(+), 11 deletions(-)

diff --git "a/pyefun/\344\272\272\345\267\245\346\231\272\350\203\275/\351\200\232\347\224\250\346\226\207\345\255\227\350\257\206\345\210\253.py" "b/pyefun/\344\272\272\345\267\245\346\231\272\350\203\275/\351\200\232\347\224\250\346\226\207\345\255\227\350\257\206\345\210\253.py"
index 44ec035..0eb7fda 100644
--- "a/pyefun/\344\272\272\345\267\245\346\231\272\350\203\275/\351\200\232\347\224\250\346\226\207\345\255\227\350\257\206\345\210\253.py"
+++ "b/pyefun/\344\272\272\345\267\245\346\231\272\350\203\275/\351\200\232\347\224\250\346\226\207\345\255\227\350\257\206\345\210\253.py"
@@ -1,22 +1,35 @@
 """
-需要安装 ppppocr 的库
-pip install ppppocr
+需要安装 rapidocr 的库
+pip install rapidocr-onnxruntime
 """
-import ppppocr
-
-ocr = ppppocr.ppppOcr()
 
 
 def 通用文字识别(图片路径):
-    dt_boxes, rec_res = ocr.ocr(图片路径)
-    return dt_boxes, rec_res
+    rapid_ocr = RapidOCR()
+    return result
 
 
 def 通用文字识别获取文字(图片路径):
-    dt_boxes, rec_res = ocr.ocr(图片路径)
-    return ocr.toText(rec_res)
+    rapid_ocr = RapidOCR()
+    result = rapid_ocr(图片路径)
+    results = []
+    for i, (rec, text, score) in enumerate(result[0]):
+        results.append(text)
+        print(text)
+    return " ".join(results)
 
 
 def 通用文字识别获取Json(图片路径):
-    dt_boxes, rec_res = ocr.ocr(图片路径)
-    return ocr.toJson(dt_boxes, rec_res)
+    rapid_ocr = RapidOCR()
+    result = rapid_ocr(图片路径)
+    results = []
+    for i, (dt_boxes, text, score) in enumerate(result[0]):
+        results.append(text)
+        print(text)
+        boxs = [(int(v[0]), int(v[1])) for v in dt_boxes]
+        results.append({
+            "text_box_position": boxs,
+            "text": text,
+            "confidence": str(score),
+        })
+    return results
\ No newline at end of file