Compare commits
No commits in common. "e8264dd9c9fe90c05a75affe8f775a9276dfb47f" and "855268e08d1ec4780a4525e0b26f886cdfb02508" have entirely different histories.
e8264dd9c9
...
855268e08d
|
|
@ -1,32 +0,0 @@
|
||||||
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')
|
|
||||||
|
|
@ -1,122 +0,0 @@
|
||||||
# -*- 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
|
|
||||||
|
|
@ -1,46 +0,0 @@
|
||||||
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,
|
|
||||||
}
|
|
||||||
|
|
||||||
}
|
|
||||||
Loading…
Reference in New Issue