https://github.com/darpa-4-aui/ocr

OCR界面识别服务

https://github.com/darpa-4-aui/ocr

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (7.0%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

OCR界面识别服务

Basic Info
  • Host: GitHub
  • Owner: DARPA-4-AUI
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 431 KB
Statistics
  • Stars: 6
  • Watchers: 0
  • Forks: 1
  • Open Issues: 0
  • Releases: 0
Created over 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme License

README.md

OCR - modified for Bait and Switch patterns detection

The project is based on ChineseOCR for Chinese natural scene text detection and recognition. Thanks a lot!!!

Environment Setup

For GPU deployment, refer to: setup.md For CPU deployment, refer to: setup-cpu.md

Model Selection

Bash Refer to the config.py file

Building Docker Image

``` Bash

Download Anaconda3 Python environment installation package (https://repo.anaconda.com/archive/Anaconda3-2019.03-Linux-x86_64.sh) and place it in the chineseocr directory

Build the image

docker build -t chineseocr .

Start the service

docker run -d -p 8080:8080 chineseocr /root/anaconda3/bin/python app.py ```

Starting the Web Service

python app.py

Accessing the Service

To use this, you need to modify the image paths inside, or change it to accept image paths as an argument [file_path]

python client.py

Result

The results (in json format) will be stored in the result folder with the same name as their corresponding images.

Result Example

There is an example result in the result folder.

Owner

  • Name: DARPA4AUI
  • Login: DARPA-4-AUI
  • Kind: organization

GitHub Events

Total
  • Push event: 2
Last Year
  • Push event: 2

Dependencies

Dockerfile docker
  • ubuntu latest build
requirements.txt pypi
  • Cython *
  • bs4 *
  • easydict *
  • h5py *
  • ipython *
  • jupyter *
  • lmdb *
  • lxml *
  • mahotas *
  • matplotlib *
  • numpy *
  • opencv-contrib-python *
  • pandas *
  • pika *
  • pillow *
  • requests *
  • scipy *
  • web.py ==0.40.dev0