What Is Surya OCR? How It Differs from NDLOCR, and Measurements on an Old English-Language Newspaper
https://tech.ldas.jp/en/posts/surya-ocr-historical-english-newspaper/
@nakamura196.bsky.social
@nakamura196.bsky.socialWhat Is Surya OCR? How It Differs from NDLOCR, and Measurements on an Old English-Language Newspaper
https://tech.ldas.jp/en/posts/surya-ocr-historical-english-newspaper/
@ossradarai.bsky.socialA comparative study benchmarks eight open-source lightweight VLMs (up to 7B parameters) for OCR-to-JSON extraction on university heritage collections, highlighting open alternatives to closed-source APIs.
#opensource #OCR #documentAI #VLM
https://arxiv.org/abs/2610.11818
@qdrddr.bsky.social
@admin.educationSay goodbye to messy #OCR pipelines and single-vector bottlenecks: #Perplexity just dropped #ColBERTx-style multimodal embeddings that let us search raw PDFs directly, while pulling the ultimate cheapskate move: querying a heavyweight 9B index with a lightning-fast 0.6B model.
@baisukltd.bsky.socialNeed to find that old invoice? B.A.I.S. makes it quick and easy. Scan, then OCR for searchable PDFs. Same day service! peopleperhour.com/hourlie/o… #pdf #ocr
@runningvalencia.bsky.socialSpartan en Madrid 2027: fechas, modalidades y sede de la carrera. #Spartan #Madrid #OCR #Running #CarrerasDeObstáculos #SanAgustínDelGuadalix
@baisukltd.bsky.socialWhen scanning private docs, should you use local or cloud OCR? Here’s when to go local. baisuk.gumroad.com/l/ooefzo #automation #ocr
@cheerchain.bsky.social
@lepasoft.bsky.socialFree GPT and OCR on your OS
github.com/jonlepage/LS...
#gpt #app #ocr #promptbuilder
@azapiai.bsky.socialManual entry of identity-document details can slow down digital forms. An Aadhaar OCR API can extract fields like name, address, DOB, ID number, gender, and father’s name, helping applications reduce repetitive data entry and process documents faster.
@baisukltd.bsky.socialHave you ever tried searching for text within a scanned PDF? It can be frustrating! OCR technology at B.A.I.S. makes them searchable, saving you time and hassle. peopleperhour.com/hourlie/o… #pdf #ocr
@stoneinsandal.bsky.social
@lepasoft.bsky.social
@tatageek.witter.cz.ap.brid.gyOCR trénink s dětmi
#garmin #beatyesterday #ocr
@synthesisai.bsky.socialOpen-source OCR done right: Chandra OCR 2 parses tables, forms and handwriting into clean Markdown/JSON, runs 100% locally, tops olmocr.
Full setup in Telegram: https://t.me/synthesis_feed #ai #tech #opensource #coding #devtools #ocr
@baisukltd.bsky.socialTired of sifting through endless scans? B.A.I.S. turns your PDFs into search-friendly docs. Try it now and see the difference! peopleperhour.com/hourlie/o… #pdf #ocr
@pixoate.bsky.socialFinance data trapped in receipt photos and scanned PDFs? Extract fields and tables into text, CSV or Excel, keep the source beside the result, and check totals before anything hits a ledger.
@pixoate.bsky.socialOCR meter reading for equipment: pull hour-meter readings from photos, then confirm the counter, decimal and machine before they reach your maintenance records.
@pixoate.bsky.socialTwo identical printers, one needs servicing. Which one? A guide to scanning equipment serial numbers into a reviewed asset register.
@pixoate.bsky.socialOCR a screenshot, a photo of a table or handwritten notes? Picking the wrong OCR mode is the usual cause of bad results. Which one fits each case.