Dünyanın Lider Açık Kaynaklı
OCR Karakter Tanıma Motoru

# Homebrew ile Tesseract kurulumu
brew install tesseract

# Tüm dil paketlerini ekleme (Önerilen):
brew install tesseract-lang

# Doğrulama:
tesseract --version
tesseract --list-langs

# Ubuntu / Debian
sudo apt update
sudo apt install tesseract-ocr tesseract-ocr-tur tesseract-ocr-eng

# Fedora / RHEL
sudo dnf install tesseract tesseract-langpack-tur

# Arch Linux
sudo pacman -S tesseract tesseract-data-tur tesseract-data-eng

pip install pytesseract pillow opencv-python

# Python Örneği:
import pytesseract
from PIL import Image

# Görselden metin çıkarma
image = Image.open('belge.jpg')
text = pytesseract.image_to_string(image, lang='tur+eng')
print(text)

# Aranabilir PDF oluşturma
pdf = pytesseract.image_to_pdf_or_hocr('belge.png', extension='pdf', lang='tur')
with open('output.pdf', 'wb') as f:
    f.write(pdf)

npm install tesseract.js

// Node.js veya Tarayıcı Kodu:
import { createWorker } from 'tesseract.js';

const worker = await createWorker('tur');
const ret = await worker.recognize('resim.png');
console.log(ret.data.text);
await worker.terminate();