Log in
Log in
Or log in with
GoogleGoogle
Twitter Twitter
Facebook Facebook
Apple Apple     
Sign up
Or log in with
GoogleGoogle
Twitter Twitter
Facebook Facebook
Apple Apple     
News
All NewsCompaniesIndexesCurrency / ForexCommoditiesCryptocurrenciesETFInterest RatesEconomyThemesSectors

Mindee Introduces Advanced Open-Source Optical Character Recognition with docTR

12/07/2021 | 08:33am EST

Leveraging deep learning and open-source, Mindee opens up state-of-the-art OCR capabilities to benefit the entire developer community

Mindee, the API-first platform designed for developers to eliminate manual data entry, announced the introduction of docTR, a seamless, high-performing, and accessible open-source library for OCR-related tasks powered by deep learning.

Mindee’s docTR provides optical character recognition with accessibility for the entire developer community. Combining textual parsing through text and object detection and recognition, this open-source repository offers a wider range and complex use cases. Going beyond the textual elements, it provides a holistic view of information encoded in visual forms, including QR codes, barcodes, information in ID pictures, and even logos.

Powered by the machine learning tool of your choice, TensorFlow 2 or PyTorch, DocTR features training capabilities for text detection in documents and images as well as recognition with pretrained parameters. It incorporates a five-line code to load documents, extract text with a predictor, and optimize for very high end-to-end performances, including inference speed on both CPU and GPU.

“At Monk, we have integrated state-of-the-art OCR models using docTR into our production pipeline to tackle our clients’ needs,” said Nicolas Schuhl, Head of Delivery at Monk. “DocTR offers amazing open-source tools to develop and deploy python OCR at scale with PyTorch or TensorFlow.”

With this offering, Mindee provides a wide audience, from entry-level developers to domain experts who want to train their model (researchers), the tools to support efforts in their transformation from intensive manual data entry (e.g., from physical documents, PDFs or images) to a full digital process. docTR was developed to provide organizations with tangible results ranging from time savings through the development process; easy integration with existing systems and architectures; minimized deployment costs; to increased productivity across departments with faster retrieval of information from documents.

“Releasing docTR as an open-source library opened a world of possibilities for innovation,” said Frédéric Harper, Director of Developer Relations at Mindee. “At Mindee, we take pride in adding value to the developer community. We made this code available with that in mind, to ensure developers can read it, understand it and be sure it’s safe. We are providing everyone with the possibility of making this OCR tool their own by allowing them to modify the code to fit their applications and infrastructure needs.”

docTR is fully available now with multiple ways to access:

To learn more about Mindee, please visit Mindee.com

About Mindee

Mindee is a pioneer of document parsing API leveraging machine learning to reduce manual data entry in software products. Headquartered in San Francisco, CA, U.S. and Paris, France, the company serves the finance, research, insurance, government, healthcare and logistics industries with state-of-the-art software for the developer community. Backed by venture capitalists including GGV Capital, Alven, Serena Capital, Venture Capital BPI France, as well as executive standouts from the application development industry, Mindee is well positioned to take advantage of the robotics process automation trend. For more information visit us at: mindee.com and follow us on LinkedIn, Twitter


ę Business Wire 2021
Latest news "Companies"
05:36pAM Best Affirms Credit Ratings of Chubb Limited and Its Subsidiaries
BU
05:35pY-mAbs Announces Complete Response Letter for Omburtamab Biologics License Application
AQ
05:34pDogecoin Lost 4.62% to $0.101 at 5 p.m. ET -- Data Talk
DJ
05:34pEthereum Lost 1.55% to $1276.85 at 5 p.m. ET -- Data Talk
DJ
05:34pBitcoin Lost 1.00% to $16931.40 at 5 p.m. ET -- Data Talk
DJ
05:33pG7 price cap coalition official says optimistic about agreeing o…
RE
05:32pG7 price cap coalition official says price caps will be adjusted…
RE
05:31pTAG Oil Announces Annual General Meeting Voting Results
PR
05:31pOld republic announces appointment of mike baumel as senior vice president
PR
05:31pCumulus Media's Westwood One Adds “The Matt Walsh Show” to Syndicated Radio
GL
Latest news "Companies"