Skip to content

C
chineseocr

yinnxinn / chineseocr
与 Fork 源项目一致

从无法访问的项目Fork

通知 5
Star 0
Fork 0
C
chineseocr

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

提交 7305add9 编写于 作者: W wenlihaoyu
浏览文件
操作

fix error #339

上级 60d696c5
隐藏空白更改
内联 并排
Showing with 216 addition and 109 deletion
README.md
浏览文件 @ 7305add9
## 本项目基于[yolo3](https://github.com/pjreddie/darknet.git) 与[crnn](https://github.com/meijieru/crnn.pytorch.git) 实现中文自然场景文字检测及识别
master分支将保留一周，后续app分支将替换为master
# 实现功能
- [x] 文字方向检测 0、90、180、270度检测（支持dnn/tensorflow）
- [x] 支持(darknet/opencv dnn /keras)文字检测,支持darknet/keras训练
- [x] 不定长OCR训练(英文、中英文) crnn\dense ocr 识别及训练 ,新增pytorch转keras模型代码(tools/pytorch_to_keras.py)
- [x] 支持darknet 转keras, keras转darknet, pytorch 转keras模型
- [x] 新增对身份证/火车票结构化数据识别
- [ ] 新增语音模型修正OCR识别结果
- [ ] 新增CNN+ctc模型，支持DNN模块调用OCR，单行图像平均时间为0.02秒以下
- [ ] 优化CPU调用，识别速度与GPU接近(近期更新)
- [x] 支持darknet 转keras, keras转darknet, pytorch 转keras模型
- [x] 身份证/火车票结构化数据识别
- [x] 新增CNN+ctc模型，支持DNN模块调用OCR，单行图像平均时间为0.02秒以下
- [ ] CPU版本加速
- [ ] 支持基于用户字典OCR识别
- [ ] 新增语言模型修正OCR识别结果
- [ ] 支持树莓派实时识别方案
## 环境部署
......@@ -38,7 +39,6 @@ lib = CDLL(root+"chineseocr/darknet/libdarknet.so", RTLD_GLOBAL)
## 下载模型文件
模型文件地址:
* [baidu pan](https://pan.baidu.com/s/1gTW9gwJR6hlwTuyB6nCkzQ)
* [google drive](https://drive.google.com/drive/folders/1XiT1FLFvokAdwfE9WSUSS1PnZA34WBzy?usp=sharing)
复制文件夹中的所有文件到models目录
......@@ -56,22 +56,21 @@ keras 转darknet
python tools/keras_to_darknet.py -cfg_path models/text.cfg -weights_path models/text.h5 -output_path models/text.weights
```
## 编译语言模型
## 编译语言模型(可选)
``` Bash
git clone --recursive https://github.com/parlance/ctcdecode.git
cd ctcdecode
pip install .
```
## 下载语言模型
## 下载语言模型 (可选)
``` Bash
wget https://deepspeech.bj.bcebos.com/zh_lm/zh_giga.no_cna_cmn.prune01244.klm
mv zh_giga.no_cna_cmn.prune01244.klm chineseocr/models/
```
## web服务启动
## 模型选择
``` Bash
cd chineseocr## 进入chineseocr目录
ipython app.py 8080 ##8080端口号，可以设置任意端口
```
参考config.py文件
```
## 构建docker镜像
``` Bash
......@@ -83,6 +82,18 @@ docker run -d -p 8080:8080 chineseocr /root/anaconda3/bin/python app.py
```
## web服务启动
``` Bash
cd chineseocr## 进入chineseocr目录
python app.py 8080 ##8080端口号，可以设置任意端口
```
## 访问服务
http://127.0.0.1:8080/ocr
<img width="500" height="300" src="https://github.com/chineseocr/chineseocr/blob/master/test/demo.png"/>
## 识别结果展示
......@@ -92,11 +103,6 @@ docker run -d -p 8080:8080 chineseocr /root/anaconda3/bin/python app.py
<img width="500" height="300" src="https://github.com/chineseocr/chineseocr/blob/master/test/line-demo.png"/>
## 访问服务
http://127.0.0.1:8080/ocr
<img width="500" height="300" src="https://github.com/chineseocr/chineseocr/blob/master/test/demo.png"/>
## 参考
1. yolo3 https://github.com/pjreddie/darknet.git
......
app.py
浏览文件 @ 7305add9
......@@ -3,20 +3,108 @@
@author: lywen
"""
import os
import cv2
import json
import time
import uuid
import base64
import web
import numpy as np
import uuid
from PIL import Image
web.config.debug = True
import model
filelock='file.lock'
if os.path.exists(filelock):
os.remove(filelock)
render = web.template.render('templates', base='base')
from config import DETECTANGLE
from apphelper.image import union_rbox,adjust_box_to_origin
from config import *
from apphelper.image import union_rbox,adjust_box_to_origin,base64_to_PIL
from application import trainTicket,idcard
if yoloTextFlag =='keras' or AngleModelFlag=='tf' or ocrFlag=='keras':
if GPU:
os.environ["CUDA_VISIBLE_DEVICES"] = str(GPUID)
import tensorflow as tf
from keras import backend as K
config = tf.ConfigProto()
config.gpu_options.allocator_type = 'BFC'
config.gpu_options.per_process_gpu_memory_fraction = 0.3## GPU最大占用量
config.gpu_options.allow_growth = True##GPU是否可动态增加
K.set_session(tf.Session(config=config))
K.get_session().run(tf.global_variables_initializer())
else:
##CPU启动
os.environ["CUDA_VISIBLE_DEVICES"] = ''
if yoloTextFlag=='opencv':
scale,maxScale = IMGSIZE
from text.opencv_dnn_detect import text_detect
elif yoloTextFlag=='darknet':
scale,maxScale = IMGSIZE
from text.darknet_detect import text_detect
elif yoloTextFlag=='keras':
scale,maxScale = IMGSIZE[0],2048
from text.keras_detect import text_detect
else:
print( "err,text engine in keras\opencv\darknet")
from text.opencv_dnn_detect import angle_detect
if ocr_redis:
##多任务并发识别
from apphelper.redisbase import redisDataBase
ocr = redisDataBase().put_values
else:
from crnn.keys import alphabetChinese,alphabetEnglish
if ocrFlag=='keras':
from crnn.network_keras import CRNN
if chineseModel:
alphabet = alphabetChinese
if LSTMFLAG:
ocrModel = ocrModelKerasLstm
else:
ocrModel = ocrModelKerasDense
else:
ocrModel = ocrModelKerasEng
alphabet = alphabetEnglish
LSTMFLAG = True
elif ocrFlag=='torch':
from crnn.network_torch import CRNN
if chineseModel:
alphabet = alphabetChinese
if LSTMFLAG:
ocrModel = ocrModelTorchLstm
else:
ocrModel = ocrModelTorchDense
else:
ocrModel = ocrModelTorchEng
alphabet = alphabetEnglish
LSTMFLAG = True
elif ocrFlag=='opencv':
from crnn.network_dnn import CRNN
ocrModel = ocrModelOpencv
alphabet = alphabetChinese
else:
print( "err,ocr engine in keras\opencv\darknet")
nclass = len(alphabet)+1
if ocrFlag=='opencv':
crnn = CRNN(alphabet=alphabet)
else:
crnn = CRNN( 32, 1, nclass, 256, leakyRelu=False,lstmFlag=LSTMFLAG,GPU=GPU,alphabet=alphabet)
if os.path.exists(ocrModel):
crnn.load_weights(ocrModel)
else:
print("download model or tranform model with tools!")
ocr = crnn.predict_job
from main import TextOcrModel
model = TextOcrModel(ocr,text_detect,angle_detect)
billList = ['通用OCR','火车票','身份证']
......@@ -30,79 +118,91 @@ class OCR:
post['H'] = 1000
post['width'] = 600
post['W'] = 600
post['uuid'] = uuid.uuid1().__str__()
post['billList'] = billList
return render.ocr(post)
def POST(self):
t = time.time()
data = web.data()
uidJob = uuid.uuid1().__str__()
data = json.loads(data)
billModel = data.get('billModel','')
textAngle = data.get('textAngle',False)##文字检测
textLine = data.get('textLine',False)##只进行单行识别
imgString = data['imgString'].encode().split(b';base64,')[-1]
imgString = base64.b64decode(imgString)
jobid = uuid.uuid1().__str__()
path = 'test/{}.jpg'.format(jobid)
with open(path,'wb') as f:
f.write(imgString)
img = cv2.imread(path)##GBR
img = base64_to_PIL(imgString)
if img is not None:
img = np.array(img)
H,W = img.shape[:2]
timeTake = time.time()
if textLine:
##单行识别
partImg = Image.fromarray(img)
text = model.crnnOcr(partImg.convert('L'))
res =[ {'text':text,'name':'0','box':[0,0,W,0,W,H,0,H]} ]
else:
detectAngle = textAngle
_,result,angle= model.model(img,
detectAngle=detectAngle,##是否进行文字方向检测，通过web传参控制
config=dict(MAX_HORIZONTAL_GAP=50,##字符之间的最大间隔，用于文本行的合并
MIN_V_OVERLAPS=0.6,
MIN_SIZE_SIM=0.6,
TEXT_PROPOSALS_MIN_SCORE=0.1,
TEXT_PROPOSALS_NMS_THRESH=0.3,
TEXT_LINE_NMS_THRESH = 0.7,##文本行之间测iou值
),
leftAdjust=True,##对检测的文本行进行向左延伸
rightAdjust=True,##对检测的文本行进行向右延伸
alph=0.01,##对检测的文本行进行向右、左延伸的倍数
)
if billModel=='' or billModel=='通用OCR' :
result = union_rbox(result,0.2)
res = [{'text':x['text'],
'name':str(i),
'box':{'cx':x['cx'],
'cy':x['cy'],
'w':x['w'],
'h':x['h'],
'angle':x['degree']
}
} for i,x in enumerate(result)]
res = adjust_box_to_origin(img,angle, res)##修正box
elif billModel=='火车票':
res = trainTicket.trainTicket(result)
res = res.res
res =[ {'text':res[key],'name':key,'box':{}} for key in res]
elif billModel=='身份证':
res = idcard.idcard(result)
res = res.res
res =[ {'text':res[key],'name':key,'box':{}} for key in res]
while time.time()-t<=TIMEOUT:
if os.path.exists(filelock):
continue
else:
with open(filelock,'w') as f:
f.write(uidJob)
if textLine:
##单行识别
partImg = Image.fromarray(img)
text = crnn.predict(partImg.convert('L'))
res =[ {'text':text,'name':'0','box':[0,0,W,0,W,H,0,H]} ]
os.remove(filelock)
break
else:
detectAngle = textAngle
result,angle= model.model(img,
scale=scale,
maxScale=maxScale,
detectAngle=detectAngle,##是否进行文字方向检测，通过web传参控制
MAX_HORIZONTAL_GAP=100,##字符之间的最大间隔，用于文本行的合并
MIN_V_OVERLAPS=0.6,
MIN_SIZE_SIM=0.6,
TEXT_PROPOSALS_MIN_SCORE=0.1,
TEXT_PROPOSALS_NMS_THRESH=0.3,
TEXT_LINE_NMS_THRESH = 0.99,##文本行之间测iou值
LINE_MIN_SCORE=0.1,
leftAdjustAlph=0.01,##对检测的文本行进行向左延伸
rightAdjustAlph=0.01,##对检测的文本行进行向右延伸
)
if billModel=='' or billModel=='通用OCR' :
result = union_rbox(result,0.2)
res = [{'text':x['text'],
'name':str(i),
'box':{'cx':x['cx'],
'cy':x['cy'],
'w':x['w'],
'h':x['h'],
'angle':x['degree']
}
} for i,x in enumerate(result)]
res = adjust_box_to_origin(img,angle, res)##修正box
elif billModel=='火车票':
res = trainTicket.trainTicket(result)
res = res.res
res =[ {'text':res[key],'name':key,'box':{}} for key in res]
elif billModel=='身份证':
res = idcard.idcard(result)
res = res.res
res =[ {'text':res[key],'name':key,'box':{}} for key in res]
os.remove(filelock)
break
timeTake = time.time()-timeTake
timeTake = time.time()-t
os.remove(path)
return json.dumps({'res':res,'timeTake':round(timeTake,4)},ensure_ascii=False)
......
config.py
浏览文件 @ 7305add9
import os
########################文字检测########################
##文字检测引擎
pwd = os.getcwd()
opencvFlag = 'keras' ##keras,opencv,darknet，模型性能 keras>darknet>opencv
########################文字检测################################################
##文字检测引擎
IMGSIZE = (608,608)## yolo3 输入图像尺寸
## keras 版本anchors
yoloTextFlag = 'keras' ##keras,opencv,darknet，模型性能 keras>darknet>opencv
############## keras yolo ##############
keras_anchors = '8,11, 8,16, 8,23, 8,33, 8,48, 8,97, 8,139, 8,198, 8,283'
class_names = ['none','text',]
kerasTextModel=os.path.join(pwd,"models","text.h5")##keras版本模型权重文件
############## keras yolo ##############
############## darknet yolo ##############
darknetRoot = os.path.join(os.path.curdir,"darknet")## yolo 安装目录
yoloCfg = os.path.join(pwd,"models","text.cfg")
yoloWeights = os.path.join(pwd,"models","text.weights")
yoloData = os.path.join(pwd,"models","text.data")
############## darknet yolo ##############
########################文字检测########################
########################文字检测################################################
## GPU选择及启动GPU序号
GPU = True##OCR 是否启用GPU
GPUID=0##调用GPU序号
## nms选择,支持cython,gpu,python
nmsFlag='gpu'## cython/gpu/python ##容错性 优先启动GPU，其次是cpython 最后是python
if not GPU:
nmsFlag='cython'
##vgg文字方向检测模型
DETECTANGLE=True##是否进行文字方向检测
AngleModelPb = os.path.join(pwd,"models","Angle-model.pb")
AngleModelPb = os.path.join(pwd,"models","Angle-model.pb")
AngleModelPbtxt = os.path.join(pwd,"models","Angle-model.pbtxt")
AngleModelFlag = 'opencv' ## opencv or tf
######################OCR模型######################
######################OCR模型###################################################
ocr_redis = False##是否多任务执行OCR识别加速 如果多任务，则配置redis数据库，数据库账号参考apphelper/redisbase.py
##是否启用LSTM crnn模型
##OCR模型是否调用LSTM层
LSTMFLAG = True
ocrFlag = 'torch'##ocr模型 支持 keras torch opencv版本
##模型选择 True:中英文模型 False:英文模型
ocrFlag = 'torch'##ocr模型 支持 keras torch版本
chinsesModel = True
ocrModelKeras = os.path.join(pwd,"models","ocr-dense-keras.h5")##keras版本OCR，暂时支持dense
if chinsesModel:
if LSTMFLAG:
ocrModel = os.path.join(pwd,"models","ocr-lstm.pth")
else:
ocrModel = os.path.join(pwd,"models","ocr-dense.pth")
else:
##纯英文模型
LSTMFLAG=True
ocrModel = os.path.join(pwd,"models","ocr-english.pth")
######################OCR模型######################
chineseModel = True## 中文模型或者纯英文模型
##转换keras模型 参考tools目录
ocrModelKerasDense = os.path.join(pwd,"models","ocr-dense.h5")
ocrModelKerasLstm = os.path.join(pwd,"models","ocr-lstm.h5")
ocrModelKerasEng = os.path.join(pwd,"models","ocr-english.h5")
ocrModelTorchLstm = os.path.join(pwd,"models","ocr-lstm.pth")
ocrModelTorchDense = os.path.join(pwd,"models","ocr-dense.pth")
ocrModelTorchEng = os.path.join(pwd,"models","ocr-english.pth")
ocrModelOpencv = os.path.join(pwd,"models","ocr.pb")
######################OCR模型###################################################
TIMEOUT=30##超时时间
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或