OCR Vision Processing

Our optical character recognition (OCR) solutions allow to detect and extract text from a wide range of images. The solutions use state of the art vision processing tools based on deep learning.
Thanks to the recent advancements in machine learning especially the developments of new architectures based on deep learning, it is now possible to identify and automatically read even the most distorted, deformed and poorly printed text. Our tools have been pre-trained on a wide variety of fonts and can identify most text with no need for additional configuration. For better and improved accuracy it is possible to retrain the OCR vision tool and adjust it to specific OCR application requirements with an easy and intuitive interface.

OUR OCR PRODUCTS

All our solutions are easy to use, and there is no need for specialized training. An OCR vision job can be configured and integrated within a matter of minutes by a non-expert.

Our solutions can be deployed and integrated with your system both in an online and offline fashion.

ON-LINE Solution Integration

We provide access to a dedicated high-speed server trough a Vision API for image processing purposes. The Vision API can perform text detection and OCR  that can be requested by sending the content of an image to the server in the body of the HTTP request. Vision API uses RESTFull Web Services to communicate with a client system. This solution is especially useful for mobile and remote applications, where the resources for image processing are limited and can be utilized better to perform other tasks.

OFF-LINE Solution Integration

For applications that require off-line text detection and OCR we provide a wide range of APIs and Libraries that allow integration of our solutions with client systems. This is very often a case in industrial applications where a need for integration of vision tools into manufacturing production systems and in-house data processing is required. Our OCR products can be integrated with the following technologies:

 

  • .NET VB/C#
  • Java
  • Python 2/3
  • Cognex Vision Pro
  • JavaScript

TRY IT

Try the OCR demo application below. You can load your image by pressing the “LOAD FILE” button and selecting the image you want to process. To process the image, you need to press “RUN” button. Depending on the image size some of the parameters would need to be adjusted. This can be configured by adjusting the Segment, Link and Confidence threshold. The demo application can be used to perform OCR and detect text on images. The WEB application is a demo of a small subset of the functionality of our OCR products and service. For more information please contact us using the link below.

Speak to us about how we can transform your organisation

About Us

Interactive Coventry (IC) provides solutions to reduce the complexity and cognitive burden on accessing and processing large volumes of data.

Follow Us

©2018 Interactive Coventry Limited.
Registered in England and Wales number: 9884466 VAT No: 265 1642 06

Contact Us

+44 24 76158115

+44 24 77657724

info@interactivecoventry.com

Interactive Coventry Ltd
Techno Centre,
Coventry University Technology Park,
Puma Way,
Coventry, CV1 2TT,
United Kingdom