Giter Site home page Giter Site logo

walleclipse / chineseaddress_ocr Goto Github PK

View Code? Open in Web Editor NEW
348.0 16.0 133.0 246.36 MB

Photographing Chinese-Address OCR implemented using CTPN+CTC+Address Correction. 拍照文档中文地址文字识别。

Python 82.86% C++ 0.05% Shell 0.09% Cuda 1.74% JavaScript 15.27%
ocr text-detection text-recognition chinese-nlp keras-tensorflow

chineseaddress_ocr's People

Contributors

walleclipse avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

chineseaddress_ocr's Issues

虚拟机下使用cpu运行

打扰下,没有太搞懂给的cpu链接示例;跟着如下描述修改:
To use cpu only, I follow the author's instruction and make the following modifications:
(1) Set "USE_GPU_NMS " in the file ./ctpn/text.yml as "False"
(2) Set the "__C.USE_GPU_NMS" in the file ./lib/fast_rcnn/config.py as "False";
(3) Comment out the line "from lib.utils.gpu_nms import gpu_nms" in the file ./lib/fast_rcnn/nms_wrapper.py;
(4) To rebuild the setup.py:
最后的setup.py步骤应该与本项目应该无关;
在修改上面三个参数后运行 demo_final.py,在读取Vggnet_fast_rcnn_iter_86000;显示未找到/data/share/chinese_ocr/ctpn/checkpoints。
老师可能借用这个为baseline启动一个项目,目前因为设备问题,只有虚拟机没法用显卡。而对方近期需要演示一下demo。

检测+识别

你好 请教几个问题
1.请问检测那块的数据集是重新用具体所需图像标注训练还是直接用ctpn作者提供的数据voc啊
2.看项目介绍像是商户的证件,请问检测之前是对原图做个区域选择 还是直接全部检测啊,因为看到你最终只是检测公司地址这一块或者说预测前是否做了一些预处理呢 。
3.densenet识别那块 也是直接用原作者给出的数据进行训练的吗? 我看你给出了一个全是公司地址的一个测试集

about Grocery

the train data of Grocery don't need convert to wordvec? grocery.train(add_list) the format of add_list is ("adderss","广州...")

对不起我问你一个问题。

可以针对任何地址获悉吗?
你是怎么做到的?
例如,从其他国家学习并推断地址。
很抱歉,如果联系地点错误。

关于如何部署在微信小程序

博主您好,我是在校一名学生,之前也看了YCG的这个ctpn+densenet+ctc的ocr项目,也自己训练了模型,现在想学习您一样在微信小程序上这样部署,感觉比较炫酷,恕小弟唐突了,不知能否方便加下您的qq或者微信,小弟想跟您学习一下,我的qq是1164757353,微信是wjc953368

权重文件?

VGGnet_fast_rcnn_iter_86000.ckpt 在哪儿可以下载呀?可否提供?
十分感谢!

No result

when i run demo_final,it comes as follows:

This is the metric converter
What would you like to convert ?
You can either convert a measurement, weight or volume

请问,识别出的文字是中文乱码?怎么办?

大佬你好,我用的照片是ChineseAddress_OCR_Report.pdf里面的截图。我让demo_final.py下面的代码输出结果;
result, image_framed = ocr_whole.model(image)
output_file = os.path.join(result_dir, image_file.split('/')[-1])
Image.fromarray(image_framed).save(output_file)
ret_total = ''
for key in result:
string1 = result[key][1]
# print("predict line text :",string1)
string2 = re.sub("[\s+.!/_,$%^(+"']+|[+——!,。?、~@#¥%……&{}[]+", "", string1)

    print('key是什么?',key)
    print('内容是什么?')
    print(string2)

结果输出的是中文的乱码
key是什么? 1
内容是什么?
蓝供犁蓝脑栗蓝脑具蓝蓝蓝镂具蓝蓝蓝蓝供仗蓝仗仗仗蓝

请问怎么回事?我应该怎么办?

CTPN

你好,打扰一下,在ctpn模型中,在conv5进行3x3,步长为1的滑窗
。为什么得到的3x3xC的向量?卷积得到不是11C的向量吗?

识别结果全都是错的,类似乱码

您好,想问一下,为什么识别结果会是这样的?全都是乱码一样,请问知道为什么吗?还是我测试的时候哪里设置的不对吗?
识别结果为:
image

实际测试图像为:
demo

basemodel.predict(temp_x)

执行这一步的时候报错:
tensorflow.python.framework.errors_impl.AbortedError: Operation received an exception:Status: 3, message: could not create a reorder primitive descriptor, in file tensorflow/core/kernels/mkl_concat_op.cc:813
[[Node: concatenate_49/concat = _MklConcatV2[N=2, T=DT_FLOAT, Tidx=DT_INT32, _kernel="MklOp", _device="/job:localhost/replica:0/task:0/device:CPU:0"](conv2d_55/convolution, conv2d_56/BiasAdd, concatenate_49/concat/axis, conv2d_55/convolution:2, conv2d_56/BiasAdd:2, DMT/_10)]]

basemodel.load_weights(modelPath) 这一步没问题,在预测的时候报错了,请问这个是什么原因啊
谢谢

引用问题

/ctpn/lib/utils/init.py里的
from . import bbox
from . import cython_nms
总是报错,搜索不到bbox和cython_nms。。。网上搜了好多都没能解决
运行demo_final.py需要编译什么c文件吗

依赖包

python所需要的依赖包能发一下吗

tgrocery问题

请问是python3版本的吗?我运行的时候出现下面问题。
File "demo_final.py", line 10, in
from tgrocery import Grocery
File "/root/anaconda3/lib/python3.6/site-packages/tgrocery/init.py", line 1, in
from converter import *

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.