nowfound

Life & fun · December 30, 2019

Keras-OCR is an end-to-end, trainable OCR pipeline

A packaged and flexible version of the CRAFT text detector and Keras CRNN recognition model. - faustomorales/keras-ocr

Keras-OCR is an end-to-end, trainable OCR pipeline launched on December 30, 2019 with 11 votes, #779 of 2,946 launches that month and more than 75% of that year's launches. The site was still online in September 2026, 6 years on.

In plain words

Keras-OCR is an open-source optical character recognition pipeline built with Keras that can be trained end-to-end for custom OCR tasks. It is designed for developers and researchers who need to extract text from images programmatically. The system stands out by offering a complete, trainable solution rather than relying solely on pre-trained models, allowing users to adapt it to specific document types or handwriting styles.

written from the facts on this page · September 2026

Does a similar job

all alternatives →
  • OCR pipeline for ML training (tables, diagrams, math, multilingual)2025 · github.com · ▲170

    Hi HN, I’ve been working on an OCR pipeline specifically optimized for machine learning dataset preparation. It’s designed to process complex academic materials — including math formulas, tables, figures, and multilingual text — and output clean, structured formats like JSON and Markdown. Some features: • Multi-stage OCR combining DocLayout-YOLO, Google Vision, MathPix, and Gemini Pro Vision • Extracts and understands diagrams, tables, LaTeX-style math, and multilingual text (Japanese/Korean/English) • Highly tuned for ML training pipelines, including dataset generation and…

  • DeepSeek-OCR2025 · huggingface.co · ▲350

    Advanced visual-text compression technology

  • Mistral OCR2025 · mistral.ai · ▲592

    Introducing the world’s best document understanding API

  • Neural network optical character recognition2015 · github.com · ▲23

    Neural network OCR. Contribute to mateogianolio/ocr development by creating an account on GitHub.

  • OCR Arena – A playground for OCR modelsNov 2025 · ocrarena.ai · ▲216

    I built OCR Arena as a free playground for the community to compare leading foundation VLMs and open-source OCR models side-by-side. Upload any doc, measure accuracy, and (optionally) vote for the models on a public leaderboard. It currently has Gemini 3, dots.ocr, DeepSeek, GPT5, olmOCR 2, Qwen, and a few others. If there's any others you'd like included, let me know!

  • Infrrd OCR2018 · infrrd.ai · ▲118

    Extract data from invoices and receipts with AI based OCR

More life & fun this month

the category →

Source: Show HN post ↗

Launched alongside, December 2019

the whole month →
  • Find proven topics before they take off.

    Growth · 2019 · explodingtopics.com

  • AA

    After years of solo development I'm presenting: Angeldust, an omni-compatible action RPG and building game! Website: http://angeldu.st My single server hosts 250+K active players in one giant, dynamic fantasy world. Angeldust's game server is pervasively multithreaded, implementing John Carmack's dream of processing an immutable world state each tick. Both world handling and network traffic routing uses any number of threads. For networking, a typical game session only uses ~3Kbps of bandwidth, enabling decent play even over 2G/EDGE networks. The client is programmed in C++…

    Growth · 2019

  • AS

    Dev tools · 2019 · selfhostedsource.tech

  • A isometric city builder in JavaScript. Contribute to victorqribeiro/isocity development by creating an account on GitHub.

    Dev tools · 2019 · github.com

  • Play and create AI-generated adventures with infinite possibilities.

    AI · 2019 · aidungeon.io

  • Send hundreds of personalized emails with Gmail.

    Growth · 2019 · mailmeteor.com