Show HN: OCR pipeline for ML training (tables, diagrams, math, multilingual)
(github.com/ses4255)
This OCR system is specifically designed to extract structured data from complex educational materials—such as exam papers—in a format optimized for machine learning (ML) training.
This OCR system is specifically designed to extract structured data from complex educational materials—such as exam papers—in a format optimized for machine learning (ML) training.
Show HN: Docsumo's OCR Benchmark Report – Surpassing Mistral and Landing AI
(docsumo.com)
In the past month, the AI community witnessed the launch of two much-anticipated OCR solutions—Mistral OCR by the Mistral team (known for their LLMs) and Agentic Document Extraction by Landing AI, Andrew Ng’s company. At Docsumo, we live and breathe Document AI. So when these releases hit the market, we couldn’t resist putting them to the test
In the past month, the AI community witnessed the launch of two much-anticipated OCR solutions—Mistral OCR by the Mistral team (known for their LLMs) and Agentic Document Extraction by Landing AI, Andrew Ng’s company. At Docsumo, we live and breathe Document AI. So when these releases hit the market, we couldn’t resist putting them to the test
Show HN: Qwen-2.5-32B is now the best open source OCR model
(github.com/getomni-ai)
A benchmarking tool that compares OCR and data extraction capabilities of different large multimodal models such as gpt-4o, evaluating both text and json extraction accuracy. The goal of this benchmark is to publish a comprehensive benchmark of OCR accuracy across traditional OCR providers and multimodal Language Models. The evaluation dataset and methodologies are all Open Source, and we encourage expanding this benchmark to encompass any additional providers.
A benchmarking tool that compares OCR and data extraction capabilities of different large multimodal models such as gpt-4o, evaluating both text and json extraction accuracy. The goal of this benchmark is to publish a comprehensive benchmark of OCR accuracy across traditional OCR providers and multimodal Language Models. The evaluation dataset and methodologies are all Open Source, and we encourage expanding this benchmark to encompass any additional providers.
How do open source VLMs perform at OCR
(getomni.ai)
For several months, we’ve been evaluating how well vision models handle OCR. Our initial benchmark focused on the closed-source models (GPT, Gemini, and Claude) and their comparisons to traditional OCR providers (AWS, Azure, GCP, etc.).
For several months, we’ve been evaluating how well vision models handle OCR. Our initial benchmark focused on the closed-source models (GPT, Gemini, and Claude) and their comparisons to traditional OCR providers (AWS, Azure, GCP, etc.).
ScanSearch Integrates Workflow and Full OCR Scan
(scansearch.com)
Scanning documents with full-text OCR improves efficiency by making them searchable, allowing quick access to information. It enhances collaboration, ensures compliance, and strengthens security by safeguarding sensitive data, providing a significant edge for businesses.
Scanning documents with full-text OCR improves efficiency by making them searchable, allowing quick access to information. It enhances collaboration, ensures compliance, and strengthens security by safeguarding sensitive data, providing a significant edge for businesses.
Auntie PDF – an open source app built using Mistral OCR
(auntiepdf.com)
Your all-knowing guide that unpacks every PDF into clear, actionable insights. Just like your favorite aunt, but for documents!
Your all-knowing guide that unpacks every PDF into clear, actionable insights. Just like your favorite aunt, but for documents!
Evaluating Mistral OCR Against Gemini 2.0 Flash
(reducto.ai)
Today, Mistral AI released a new OCR model, claiming to be state-of-the-art (SOTA) on unreleased benchmarks. We decided to put the model to the test.
Today, Mistral AI released a new OCR model, claiming to be state-of-the-art (SOTA) on unreleased benchmarks. We decided to put the model to the test.
I built an extension that lets you extract text from anywhere to your clipboard
(chromewebstore.google.com)
Extract text from any part of your browser screen using Esticra OCR.
Extract text from any part of your browser screen using Esticra OCR.
Putting Andrew Ng's OCR models to the test
(runpulse.com)
Today, Andrew Ng, one of the legends of the AI world, released a new document extraction service that went viral on X.
Today, Andrew Ng, one of the legends of the AI world, released a new document extraction service that went viral on X.
Ask HN: What is the best method for turning a scanned book as a PDF into text?
(ycombinator.com)
I like reading philosophy, particularly from the authors rather than a secondhand account.
I like reading philosophy, particularly from the authors rather than a secondhand account.
Benchmarking vision-language models on OCR in dynamic video environments
(arxiv.org)
This paper introduces an open-source benchmark for evaluating Vision-Language Models (VLMs) on Optical Character Recognition (OCR) tasks in dynamic video environments.
This paper introduces an open-source benchmark for evaluating Vision-Language Models (VLMs) on Optical Character Recognition (OCR) tasks in dynamic video environments.
OCR Crypto Stealers in Google Play and App Store
(securelist.com)
In March 2023, researchers at ESET discovered malware implants embedded into various messaging app mods. Some of these scanned users’ image galleries in search of crypto wallet access recovery phrases. The search employed an OCR model which selected images on the victim’s device to exfiltrate and send to the C2 server. The campaign, which targeted Android and Windows users, saw the malware spread through unofficial sources.
In March 2023, researchers at ESET discovered malware implants embedded into various messaging app mods. Some of these scanned users’ image galleries in search of crypto wallet access recovery phrases. The search employed an OCR model which selected images on the victim’s device to exfiltrate and send to the C2 server. The campaign, which targeted Android and Windows users, saw the malware spread through unofficial sources.
Liberate tabular data from scanned documents
(blog.wzb.eu)
During the last months I often had to deal with the problem of extracting tabular data from scanned documents.
During the last months I often had to deal with the problem of extracting tabular data from scanned documents.
Show HN: Adventures in OCR
(medusis.com)
This past few weeks I've been working on OCRing an ancient book: a late 19th century edition of 18th century memoirs, in French: Les Mémoires de Saint-Simon.
This past few weeks I've been working on OCRing an ancient book: a late 19th century edition of 18th century memoirs, in French: Les Mémoires de Saint-Simon.
Show HN: High-accuracy OCR API for receipts/invoice with easy customisation
(visionparser.com)
Welcome to the next level of document automation! Our innovative OCR API, powered by state-of-the-art Generative AI, gives you a flexible solution that fits your unique workflow and business requirements. Experience exceptional accuracy, speed, affordability and customisation.
Welcome to the next level of document automation! Our innovative OCR API, powered by state-of-the-art Generative AI, gives you a flexible solution that fits your unique workflow and business requirements. Experience exceptional accuracy, speed, affordability and customisation.
Show HN: I launched a super cheap and simple to use OCR tool for macOS
(textcapture.app)
Ever tried to quickly copy and paste some text, only to realize it's unselectable or embedded in a video or image? That happens to me all the time!
Ever tried to quickly copy and paste some text, only to realize it's unselectable or embedded in a video or image? That happens to me all the time!
Show HN: PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o
(github.com/yigitkonur)
Swift OCR: LLM Powered Fast OCR ⚡
Swift OCR: LLM Powered Fast OCR ⚡
General OCR Theory: Towards OCR-2.0 via a Unified End-to-End Model
(huggingface.co)
Traditional OCR systems (OCR-1.0) are increasingly unable to meet people's usage due to the growing demand for intelligent processing of man-made optical characters.
Traditional OCR systems (OCR-1.0) are increasingly unable to meet people's usage due to the growing demand for intelligent processing of man-made optical characters.