โ† ์ตœ์‹  ํ”„๋กœ๋•ํŠธ

BetterOCR combines and corrects multiple OCR engines with an LLM

๐Ÿ” Better text detection by combining multiple OCR engines (EasyOCR, Tesseract, and Pororo) with ๐Ÿง  LLM.

์˜คํ”ˆ์†Œ์Šค

642 ์Šคํƒ€ ยท GitHub์™ธ๋ถ€ ์‚ฌ์ดํŠธ

github.com ๋ฐฉ๋ฌธ์™ธ๋ถ€ ์‚ฌ์ดํŠธ

๋ฐ˜์‘ (1)

๋น„์Šทํ•œ ํ”„๋กœ๋•ํŠธ

์„ค๋ช…์ด ๋น„์Šทํ•œ ์ˆœ

  1. LLM-aided OCR

    github.com

    Correcting Tesseract OCR errors with LLMs

    Hacker News479์ 

  2. Using LLama2 to Correct OCR Errors

    github.com

    Enhances Tesseract OCR output using LLMs (local or API) for error correction, smart chunking, and markdown formatting of scanned PDFs

    Hacker News54์ 

  3. Qwen-2.5-32B is now the best open source OCR model

    github.com

    OCR Benchmark

    Hacker News211์ 

  4. Surya

    github.com

    OCR and line detection in 93 languages

    Hacker News11์ 

  5. Benchmarking VLMs vs. Traditional OCR

    getomni.ai

    Vision models have been gaining popularity as a replacement for traditional OCR.

    Hacker News146์ 