Recent searches

No recent searches

Search options

Only available when logged in.
techhub.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A hub primarily for passionate technologists, but everyone is welcome

Administered by:

Server stats:

4.7K
active users

techhub.social: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.1

#ocr

5 posts5 participants1 post today
SODa<p>💡 Wie lassen sich Methoden des Machine Learning sinnvoll in der Sammlungsdigitalisierung &amp; -forschung einsetzen?</p><p>Im Interview spricht unser Kollege <span class="h-card" translate="no"><a href="https://fedihum.org/@mathias_zinnen" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>mathias_zinnen</span></a></span> über:<br>🔍 ML-Methoden für Text, Bild &amp; strukturierte Daten<br>🛠️ Open-Source-Tools<br>💡 Vermittlungsangebote zu ML-Tools im Sammlungskontext<br>🌱 Warum ressourcenschonende ML-Ansätze wichtig sind</p><p>➡️ <a href="https://sammlungen.io/blog/interview-mit-fachexpertise-2d-und-machine-learning?utm_campaign=coschedule&amp;utm_source=mastodon&amp;utm_medium=SODa%40fedihum.org" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">sammlungen.io/blog/interview-m</span><span class="invisible">it-fachexpertise-2d-und-machine-learning?utm_campaign=coschedule&amp;utm_source=mastodon&amp;utm_medium=SODa%40fedihum.org</span></a><br><a href="https://fedihum.org/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://fedihum.org/tags/2D" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>2D</span></a> <a href="https://fedihum.org/tags/SODaZentrum" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SODaZentrum</span></a> <a href="https://fedihum.org/tags/OCR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OCR</span></a> <a href="https://fedihum.org/tags/ML" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ML</span></a></p>
Taffer 🇨🇦 :godot:<p>Related to my epub DRM gripe, gImageReader (a front-end for Tesseract) does a great job of OCRing screen shots.</p><p>I'd still prefer a sane, reliable way to strip Adobe's DRM from epubs, or for publishers to stop using it.</p><p><a href="https://mastodon.gamedev.place/tags/ocr" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ocr</span></a> <a href="https://mastodon.gamedev.place/tags/tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tesseract</span></a> <a href="https://mastodon.gamedev.place/tags/gimagereader" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>gimagereader</span></a></p>
alcea<p><a href="https://mastodon.social/tags/GoodLuck" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GoodLuck</span></a> <a href="https://mastodon.social/tags/OCR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OCR</span></a> ing that...</p><p><a href="https://mastodon.social/tags/Firefish" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Firefish</span></a> works better iirc<br><a href="https://mastodon.social/tags/alttext" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>alttext</span></a></p>
Patrick Drechsler<p>looking for a self-hosting app which has good OCR for printed cooking books. Trying to digitize them.</p><p>Any recommendations?</p><p><a href="https://floss.social/tags/selfhosting" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>selfhosting</span></a> <a href="https://floss.social/tags/ocr" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ocr</span></a> <a href="https://floss.social/tags/cooking" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cooking</span></a> <a href="https://floss.social/tags/books" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>books</span></a></p>
Adi Keinan-Schoonbaert<p>My colleague Valentina Vavassori asked heritage organisations about how they do Automatic Text Recognition - the results were super interesting and rich - here's the data and a brief analysis: <a href="https://blogs.bl.uk/digital-scholarship/2025/07/automatic-text-recognition-in-cultural-heritage-institutions-survey-analysis.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">blogs.bl.uk/digital-scholarshi</span><span class="invisible">p/2025/07/automatic-text-recognition-in-cultural-heritage-institutions-survey-analysis.html</span></a> <br><a href="https://glammr.us/tags/britishlibrary" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>britishlibrary</span></a> <span class="h-card" translate="no"><a href="https://techhub.social/@BL_DigiSchol" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>BL_DigiSchol</span></a></span> <a href="https://glammr.us/tags/OCR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OCR</span></a> <a href="https://glammr.us/tags/HTR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HTR</span></a> <a href="https://glammr.us/tags/ATR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ATR</span></a></p>
Caio<p>A pauta de hoje do <a href="https://bolha.us/tags/TerSoftware" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TerSoftware</span></a> é sobre "gestão de papel". Recentemente, testei OCR para digitalização de tabelas e... não fiquei muito feliz com o resultado.</p><p>Acredito que <a href="https://bolha.us/tags/OCR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OCR</span></a> funcione melhor quando fica bem amarrado com o documento digitalizado (por exemplo, tornando um arquivo PDF buscável), mas para extração de texto, ainda é um grande "depende".</p><p>Na minha curta jornada, testei <a href="https://bolha.us/tags/Tesseract" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Tesseract</span></a> e <a href="https://bolha.us/tags/Docling" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Docling</span></a>. Talvez funcione com código bem escrito, mas acabei me rendendo e indo "no muque" mesmo.</p><p>O Tesseract parece bem fácil de instalar no Linux (mesmo no <a href="https://bolha.us/tags/openSUSE" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>openSUSE</span></a> Leap, que tem suas limitações por sair do SUSE empresarial, achei fácil), mas o Docling exigiu alguns malabarismos com ambientes em Python (usando conda e pip).</p><p>Para texto corrido, o Tesseract parece bem suficiente, já. Pode ser rodado via linha de comando e, pelo menos no openSUSE Leap, vários dicionários se encontram empacotados para facilitar.</p>
Dissent Doe :cupofcoffee:<p>HHS' Office for Civil Rights Settles HIPAA Privacy and Security Rule Investigation with Deer Oaks Behavioral Health for $225k and a Corrective Action Plan:</p><p><a href="https://databreaches.net/2025/07/08/hhs-office-for-civil-rights-settles-hipaa-privacy-and-security-rule-investigation-with-deer-oaks-behavioral-health-for-225k-and-a-corrective-action-plan/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">databreaches.net/2025/07/08/hh</span><span class="invisible">s-office-for-civil-rights-settles-hipaa-privacy-and-security-rule-investigation-with-deer-oaks-behavioral-health-for-225k-and-a-corrective-action-plan/</span></a></p><p>This was a ransomware attack in 2023 claimed by LockBit. Deer Oaks was already under investigation for a prior breach and HHS OCR expanded their case. </p><p><a href="https://infosec.exchange/tags/databreach" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>databreach</span></a> <a href="https://infosec.exchange/tags/healthsec" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>healthsec</span></a> <a href="https://infosec.exchange/tags/HIPAA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HIPAA</span></a> <a href="https://infosec.exchange/tags/cybersecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cybersecurity</span></a> <a href="https://infosec.exchange/tags/ransomware" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ransomware</span></a> <a href="https://infosec.exchange/tags/LockBit" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LockBit</span></a> <a href="https://infosec.exchange/tags/HHS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>HHS</span></a> <a href="https://infosec.exchange/tags/OCR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OCR</span></a></p>
Pyrzout :vm:<p>Convert Any Book to a DIY Audiobook? <a href="https://hackaday.com/2025/07/06/convert-any-book-to-a-diy-audiobook/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hackaday.com/2025/07/06/conver</span><span class="invisible">t-any-book-to-a-diy-audiobook/</span></a> <a href="https://social.skynetcloud.site/tags/ArtificialIntelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ArtificialIntelligence</span></a> <a href="https://social.skynetcloud.site/tags/RaspberryPiZero2W" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RaspberryPiZero2W</span></a> <a href="https://social.skynetcloud.site/tags/GoogleGemini2" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GoogleGemini2</span></a>.5 <a href="https://social.skynetcloud.site/tags/speechsynthesis" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechsynthesis</span></a> <a href="https://social.skynetcloud.site/tags/RaspberryPi" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RaspberryPi</span></a> <a href="https://social.skynetcloud.site/tags/PiperVoice" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PiperVoice</span></a> <a href="https://social.skynetcloud.site/tags/webcam" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>webcam</span></a> <a href="https://social.skynetcloud.site/tags/GenAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenAI</span></a> <a href="https://social.skynetcloud.site/tags/CV2" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CV2</span></a> <a href="https://social.skynetcloud.site/tags/ocr" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ocr</span></a> <a href="https://social.skynetcloud.site/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a></p>
Tiago F. R. Ribeiro<p>O Nanonets-OCR-s da Nanonets é um modelo OCR que transforma documentos em markdown estruturado, ideal para LLMs. Recursos incluem reconhecimento de equações LaTeX, descrição inteligente de imagens, deteção de assinaturas e marcas d'água, manipulação de caixas de seleção e extração de tabelas complexas.</p><p>📎<a href="https://huggingface.co/nanonets/Nanonets-OCR-s" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">huggingface.co/nanonets/Nanone</span><span class="invisible">ts-OCR-s</span></a></p><p>📎<a href="https://github.com/NanoNets/docext" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">github.com/NanoNets/docext</span><span class="invisible"></span></a></p><p>📎<a href="https://idp-leaderboard.org/details/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">idp-leaderboard.org/details/</span><span class="invisible"></span></a></p><p><a href="https://mastodon.social/tags/OCR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OCR</span></a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mastodon.social/tags/MachineLearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MachineLearning</span></a> <a href="https://mastodon.social/tags/Markdown" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Markdown</span></a> <a href="https://mastodon.social/tags/ProcessamentoDeDocumentos" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ProcessamentoDeDocumentos</span></a> <a href="https://mastodon.social/tags/LaTeX" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LaTeX</span></a> <a href="https://mastodon.social/tags/BigData" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BigData</span></a></p>
IT News<p>Convert Any Book to a DIY Audiobook? - If the idea of reading a physical book sounds like hard work, [Nick Bild’s] latest... - <a href="https://hackaday.com/2025/07/06/convert-any-book-to-a-diy-audiobook/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">hackaday.com/2025/07/06/conver</span><span class="invisible">t-any-book-to-a-diy-audiobook/</span></a> <a href="https://schleuss.online/tags/artificialintelligence" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>artificialintelligence</span></a> <a href="https://schleuss.online/tags/raspberrypizero2w" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>raspberrypizero2w</span></a> <a href="https://schleuss.online/tags/googlegemini2" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>googlegemini2</span></a>.5 <a href="https://schleuss.online/tags/speechsynthesis" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechsynthesis</span></a> <a href="https://schleuss.online/tags/raspberrypi" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>raspberrypi</span></a> <a href="https://schleuss.online/tags/pipervoice" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>pipervoice</span></a> <a href="https://schleuss.online/tags/webcam" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>webcam</span></a> <a href="https://schleuss.online/tags/genai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>genai</span></a> <a href="https://schleuss.online/tags/cv2" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>cv2</span></a> <a href="https://schleuss.online/tags/ocr" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ocr</span></a> <a href="https://schleuss.online/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a></p>
hansamann 🔥❄️🚀 (he/him)<p>Survived the Kulmbach Beast! 21km of pure pain and glory. Blog post with all the details here: <a href="https://open.substack.com/pub/hansamann/p/conquering-the-kulmbach-beast-a-spartan?r=1sq3ws&amp;utm_campaign=post&amp;utm_medium=web&amp;showWelcomeOnShare=true" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">open.substack.com/pub/hansaman</span><span class="invisible">n/p/conquering-the-kulmbach-beast-a-spartan?r=1sq3ws&amp;utm_campaign=post&amp;utm_medium=web&amp;showWelcomeOnShare=true</span></a> <br><a href="https://chaos.social/tags/SpartanRace" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpartanRace</span></a> <a href="https://chaos.social/tags/OCR" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OCR</span></a></p>
*
Rainer Simon

If you haven’t checked in on #IMMARKUS lately (understandable—there’s been a lot going on!)—we’ve added even more transcription service options.

You can now run OCR or full-text transcription with a single click using:

• Anthropic Claude
• Azure Computer Vision
• Google Gemini
• Google Vision OCR
• LLaMA & Qwen via kluster.ai
• OCR.space
• OpenAI GPT
• Volcano Engine Doubao 1.5 Vision Pro

Try it out here: immarkus.xmarkus.org

#OCR#DigitalHumanities#ImageAnnotation
Continued thread
Táta Geek

Je to tam.
#ocr tréninková dráha je hotová. Jen jsem měl použít o kousek delší trubku, pro děti by to mohlo být ještě tak o 10cm níž

*
Terence Eden

I have a genuine AI problem which I can't find an easy solution for.

We use Google's Vision API to OCR inscription from photographs.

Most of the time it is great, but sometimes it includes homographic characters.

For example - openbenches.org/bench/38224

It has misdetected the letters in "ΤΟΝΙΑ" as Greek rather than Latin.

I can't send a language hint, because people upload images from all over the world.

Is there a good (preferably free) OCR which wouldn't make this mistake?

OpenBenchesIn Loving Memory of ΤΟΝΙΑ HENDRIKS 21st November 2023
#AI#OCR
TrendingLive feeds
About