winocr 0.0.4

Windows.Media.Ocr

WinOCR

Installation

pip install winocr

Usage

Pillow

import winocr
from PIL import Image

img = Image.open('test.jpg')
print((await winocr.recognize_pil(img, 'ja')).text)

OpenCV

import winocr
import cv2

img = cv2.imread('test.jpg')
print((await winocr.recognize_cv2(img, 'ja')).text)

Connect to local runtime on Colaboratory

Web API

Run server

pip install winocr[api]
winocr_serve

curl

curl localhost:8000?lang=ja --data-binary @test.jpg

Python

import requests

bytes = open('test.jpg', 'rb').read()
requests.post('http://localhost:8000/?lang=ja', bytes).json()['text']

You can run OCR with the Colaboratory runtime with ./ngrok http 8000

from PIL import Image
from io import BytesIO

img = Image.open('test.jpg')
# Preprocessing
buf = BytesIO()
img.save(buf, format='JPEG')
requests.post('https://15a5fabf0d78.ngrok.io/?lang=ja', buf.getvalue()).json()['text']

import cv2
import requests

img = cv2.imread('test.jpg')
# Preprocessing
requests.post('https://15a5fabf0d78.ngrok.io/?lang=ja', cv2.imencode('.jpg', img)[1].tobytes()).json()['text']

JavaScript

If you only need to recognize Chrome and English, you can also consider the Text Detection API.

// File
const file = document.querySelector('[type=file]').files[0]
await fetch('http://localhost:8000/', {method: 'POST', body: file}).then(r => r.json())

// Blob
const blob = await fetch('https://image.itmedia.co.jp/ait/articles/1706/15/news015_16.jpg').then(r=>r.blob())
await fetch('http://localhost:8000/?lang=ja', {method: 'POST', body: blob}).then(r => r.json())

It is also possible to run OCR Server on Windows Server.

Information that can be obtained

You can get angle, text, line, word, BoundingBox.

import pprint

result = await winocr.recognize_pil(img, 'ja')
pprint.pprint({
    'text_angle': result.text_angle,
    'text': result.text,
    'lines': [{
        'text': line.text,
        'words': [{
            'bounding_rect': {'x': word.bounding_rect.x, 'y': word.bounding_rect.y, 'width': word.bounding_rect.width, 'height': word.bounding_rect.height},
            'text': word.text
        } for word in line.words]
    } for line in result.lines]
})

Language installation

# Run as Administrator
Add-WindowsCapability -Online -Name "Language.OCR~~~en-US~0.0.1.0"
Add-WindowsCapability -Online -Name "Language.OCR~~~ja-JP~0.0.1.0"

# Search for installed languages
Get-WindowsCapability -Online -Name "Language.OCR*"
# State: Not Present language is not installed, so please install it if necessary.
Name         : Language.OCR~~~hu-HU~0.0.1.0
State        : NotPresent
DisplayName  : ハンガリー語の光学式文字認識
Description  : ハンガリー語の光学式文字認識
DownloadSize : 194407
InstallSize  : 535714

Name         : Language.OCR~~~it-IT~0.0.1.0
State        : NotPresent
DisplayName  : イタリア語の光学式文字認識
Description  : イタリア語の光学式文字認識
DownloadSize : 159875
InstallSize  : 485922

Name         : Language.OCR~~~ja-JP~0.0.1.0
State        : Installed
DisplayName  : 日本語の光学式文字認識
Description  : 日本語の光学式文字認識
DownloadSize : 1524589
InstallSize  : 3398536

Name         : Language.OCR~~~ko-KR~0.0.1.0
State        : NotPresent
DisplayName  : 韓国語の光学式文字認識
Description  : 韓国語の光学式文字認識
DownloadSize : 3405683
InstallSize  : 7890408

If you hate Python and just want to recognize it with PowerShell, click here

Multi-Processing

By processing in parallel, it is 3 times faster. You can make it even faster by increasing the number of cores!

from PIL import Image

images = [Image.open('testocr.png') for i in range(1000)]

1 core(elapsed 48s)

The CPU is not used up.

import winocr

[(await winocr.recognize_pil(img)).text for img in images]

4 cores(elapsed 16s)

I'm using 100% CPU.

Create a worker module.

%%writefile worker.py
import winocr
import asyncio

async def ensure_coroutine(awaitable):
    return await awaitable

def recognize_pil_text(img):
    return asyncio.run(ensure_coroutine(winocr.recognize_pil(img))).text

import worker
import concurrent.futures

with concurrent.futures.ProcessPoolExecutor() as executor:
  # https://stackoverflow.com/questions/62488423
  results = executor.map(worker.recognize_pil_text, images)
list(results)