pip install winocrFull install
pip install winocr[all]The language to be recognized can be specified by the lang parameter (second argument).
import winocr from PIL import Image img = Image.open('test.jpg') (await winocr.recognize_pil(img, 'ja')).textimport winocr import cv2 img = cv2.imread('test.jpg') (await winocr.recognize_cv2(img, 'ja')).textCreate a local connection by following these instructions.
pip install jupyterlab jupyter_http_over_ws jupyter serverextension enable --py jupyter_http_over_ws jupyter notebook --NotebookApp.allow_origin='https://colab.research.google.com' --ip=0.0.0.0 --port=8888 --NotebookApp.port_retries=0
Also available on Jupyter / Jupyter Lab.
import cv2 from winocr import recognize_cv2_sync img = cv2.imread('testocr.png') recognize_cv2_sync(img)['text'] 'This is a lot of 12 point text to test the ocr code and see if it works on all types of file format. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox.'from PIL import Image from winocr import recognize_pil_sync img = Image.open('testocr.png') recognize_pil_sync(img)['text'] 'This is a lot of 12 point text to test the ocr code and see if it works on all types of file format. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox. The quick brown dog jumped over the lazy fox.'from PIL import Image import concurrent.futures from winocr import recognize_pil_sync images = [Image.open('testocr.png') for i in range(1000)] with concurrent.futures.ProcessPoolExecutor() as executor: results = list(executor.map(recognize_pil_sync, images)) print(results)Run server
pip install winocr[api] winocr_servecurl localhost:8000?lang=ja --data-binary @test.jpgimport 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']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.
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] })# 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 : 7890408If you hate Python and just want to recognize it with PowerShell, click here
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)]The CPU is not used up.
import winocr [(await winocr.recognize_pil(img)).text for img in images]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))).textimport 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)