Mesin Pengenalan Karakter (OCR)
Open Source Terbaik di Dunia

# Pasang Tesseract dengan Homebrew
brew install tesseract

# Pasang semua paket bahasa tambahan (Disarankan):
brew install tesseract-lang

# Verifikasi:
tesseract --version
tesseract --list-langs

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

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

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

pip install pytesseract pillow opencv-python

# Contoh Python:
import pytesseract
from PIL import Image

# Ekstrak teks dari gambar
image = Image.open('dokumen.jpg')
text = pytesseract.image_to_string(image, lang='ind+eng')
print(text)

# Hasilkan PDF yang dapat dicari
pdf = pytesseract.image_to_pdf_or_hocr('dokumen.png', extension='pdf', lang='ind')
with open('output.pdf', 'wb') as f:
    f.write(pdf)

npm install tesseract.js

// Kode Node.js atau Browser:
import { createWorker } from 'tesseract.js';

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