Merge branch 'main' of http://192.168.0.56:3000/BNSTechnologyDevelopment/ComponentDevelopment

OCRPython/paddleOcrTest.py

@@ -0,0 +1,32 @@
+from paddleocr import PaddleOCR, draw_ocr
+import time
+
+from extractor.identitycard_extractor import IdentityCardExtractor
+
+# Paddleocr目前支持的多语言语种可以通过修改lang参数进行切换
+# 例如`ch`, `en`, `fr`, `german`, `korean`, `japan`
+
+stat_time = time.time()
+ocr = PaddleOCR(use_angle_cls=True, lang="ch")  # need to run only once to download and load model into memory
+img_path = './images/内蒙古1正.png'
+result = ocr.ocr(img_path, cls=True)
+for idx in range(len(result)):
+    res = result[idx]
+    for line in res:
+        print(line)
+
+end_time = time.time()
+print(end_time - stat_time)
+
+# 显示结果
+# 如果本地没有simfang.ttf，可以在doc/fonts目录下下载
+from PIL import Image
+
+result = result[0]
+image = Image.open(img_path).convert('RGB')
+boxes = [line[0] for line in result]
+txts = [line[1][0] for line in result]
+scores = [line[1][1] for line in result]
+im_show = draw_ocr(image, boxes, txts, scores, font_path='doc/fonts/simfang.ttf')
+im_show = Image.fromarray(im_show)
+im_show.save('result.jpg')

OCRPython/util/ocr_recognition.py

@@ -0,0 +1,122 @@
+# -*- coding: utf-8 -*-
+import time
+import sys
+import io
+from paddleocr import PaddleOCR
+
+from configs.basic_config import *
+from extractor.identitycard_extractor import IdentityCardExtractor
+import base64
+import json
+
+sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
+
+
+class OCRRecognition:
+    @staticmethod
+    def extractIdCardInfo(type: int = 0, filePath1: str = "", filePath2: str = "") -> str:
+        if 0 == type:
+            logger.info("0 == type")
+            return OCRRecognition.extractIdCardInfoByPath(filePath1, filePath2)
+        elif 1 == type:
+            logger.info("1 == type")
+            return OCRRecognition.extractIdCardInfoByBase64Data(filePath1, filePath2)
+        else:
+            logger.info("type is other")
+            finalResult = {"code": NO_DEFINED_FUNCTION_ERROR,
+                           "msg": error_codes[NO_DEFINED_FUNCTION_ERROR]}
+            return json.dumps(finalResult, ensure_ascii=False)
+
+    @staticmethod
+    def extractIdCardInfoByPath(filePath1: str = "", filePath2: str = "") -> str:
+        logger.info(f"ocr加载开始计时")
+        start_time = time.time()  # 记录结束时间
+        ocr = PaddleOCR(use_angle_cls=True, lang="ch")  # need to run only once to download and load model into memory
+        text = ""
+        finalResult = {
+            "code": LOCAL_PATH_NOT_EXIST,
+            "msg": error_codes[LOCAL_PATH_NOT_EXIST],
+
+        }
+        try:
+            if len(filePath1) > 0:
+                if os.path.exists(filePath1):
+                    result = ocr.ocr(filePath1, cls=False)
+                    for idx in range(len(result)):
+                        res = result[idx]
+                        for line in res:
+                            text += (line[1][0] + '\n')
+                else:
+                    logger.error(f"{filePath1} doesn't exist,error information:{finalResult}")
+                    return json.dumps(finalResult, ensure_ascii=False)
+
+            if len(filePath2) > 0:
+                if os.path.exists(filePath2):
+                    result = ocr.ocr(filePath2, cls=False)
+                    for idx in range(len(result)):
+                        res = result[idx]
+                        for line in res:
+                            text += (line[1][0] + '\n')
+                else:
+                    logger.error(f"{filePath2} doesn't exist,error information:{finalResult}")
+                    return json.dumps(finalResult, ensure_ascii=False)
+
+        except Exception as e:
+            finalResult["code"] = OCR_RECOGNIZE_OTHER_EXCEPTION
+            finalResult["msg"] = error_codes[OCR_RECOGNIZE_OTHER_EXCEPTION]
+            logger.error(f"{e} ,error information:{finalResult}")
+            return json.dumps(finalResult, ensure_ascii=False)
+
+        if 0 != len(text):
+            extractor = IdentityCardExtractor()
+            tempdict = extractor.extract_textbyPaddle(text)
+            jsonString = json.dumps(tempdict, ensure_ascii=False)
+            end_time = time.time()  # 记录结束时间
+            execution_time = end_time - start_time  # 计算执行时间
+            logger.info(f"extractIdCardInfoByPath 耗时{execution_time}秒")
+            return jsonString
+        else:
+            finalResult["code"] = NO_TEXT_RECOGNIZED
+            finalResult["msg"] = error_codes[NO_TEXT_RECOGNIZED]
+            logger.error(f"{filePath1},{filePath2} can't be recognized,error information:{finalResult}")
+            return json.dumps(finalResult, ensure_ascii=False)
+
+    @staticmethod
+    def extractIdCardInfoByBase64Data(base64data1: str, base64Data2: str) -> str:
+        finalResult = {
+            "code": BASE64_DATA_INCOMPLETE,
+            "msg": error_codes[BASE64_DATA_INCOMPLETE],
+        }
+        logger.info(f"extractIdCardInfoByBase64Data")
+        start_time = time.time()  # 记录结束时间
+        jsonString = ""
+        try:
+            if 0 != len(base64data1):
+                image_data1 = base64.b64decode(base64data1)
+                with open("file1.png", "wb") as file:
+                    file.write(image_data1)
+
+            if 0 != len(base64Data2):
+                image_data2 = base64.b64decode(base64Data2)
+                with open("file2.png", "wb") as file:
+                    file.write(image_data2)
+
+            if os.path.exists("file1.png") and os.path.exists("file2.png"):
+                jsonString = OCRRecognition.extractIdCardInfoByPath("file1.png", "file2.png")
+                os.remove("file1.png")
+                os.remove("file2.png")
+            elif os.path.exists("file1.png"):
+                jsonString = OCRRecognition.extractIdCardInfoByPath("file1.png", "")
+                os.remove("file1.png")
+            elif os.path.exists("file2.png"):
+                jsonString = OCRRecognition.extractIdCardInfoByPath("file2.png", "")
+                os.remove("file2.png")
+        except Exception as e:
+            logger.error(e)
+            logger.error(f"{e},error information:{finalResult}")
+            return json.dumps(finalResult, ensure_ascii=False)
+
+        end_time = time.time()  # 记录结束时间
+        execution_time = end_time - start_time  # 计算执行时间
+        logger.info(f"extractIdCardInfoByBase64Data 耗时{execution_time}秒")
+        return jsonString

OCRTool/src/main/java/com/bonus/core/IdentifyRecognitionParams.java

@@ -0,0 +1,46 @@
+package com.bonus.core;
+
+/**
+ * @author wangvivi
+ */
+public class IdentifyRecognitionParams {
+    private RecognitionType type;
+    private String recognitionFrontData = "";
+    private String recognitionBackData = "";
+
+
+    public int getType() {
+        return type.ordinal();
+    }
+
+    public void setType(RecognitionType type) {
+        this.type = type;
+    }
+
+    public String getRecognitionFrontData() {
+        return this.recognitionFrontData;
+    }
+
+    public void setRecognitionFrontData(String recognitionFrontData) {
+        this.recognitionFrontData = recognitionFrontData;
+    }
+
+    public String getRecognitionBackData() {
+        return this.recognitionBackData;
+    }
+
+    public void setRecognitionBackData(String recognitionBackData) {
+        this.recognitionBackData = recognitionBackData;
+    }
+
+
+    // Enum for different recognition types
+    public enum RecognitionType {
+        //参数带入的是图片路径
+        IDENTITY_CARD_PATH ,
+        //参数传入的是图片的base64编码
+        IDENTITY_CARD_BASE64_DATA,
+        INVOICE_PATH,
+    }
+
+}