Skip to content
  • Our Work
    • Fields
      • Cardiology
      • ENT
      • Gastro
      • Orthopedics
      • Ophthalmology
      • Pulmonology
      • Surgical
      • Urology
      • Other
    • Modalities
      • Endoscopy
      • Medical Segmentation
      • Microscopy
      • Ultrasound
  • Success Stories
  • Insights
    • Magazine
    • Upcoming Events
    • Webinars
    • Meetups
    • News
    • Blog
  • The company
    • About us
    • Careers
Menu
  • Our Work
    • Fields
      • Cardiology
      • ENT
      • Gastro
      • Orthopedics
      • Ophthalmology
      • Pulmonology
      • Surgical
      • Urology
      • Other
    • Modalities
      • Endoscopy
      • Medical Segmentation
      • Microscopy
      • Ultrasound
  • Success Stories
  • Insights
    • Magazine
    • Upcoming Events
    • Webinars
    • Meetups
    • News
    • Blog
  • The company
    • About us
    • Careers
Contact

Deep Learning For OCR

Consult with RSIP Vision now

Deep Neural Networks Used for Optical Character Recognition

Optical Character Recognition (OCR) used for the visual inspection of documents has found wide application in both industry and research.  The automatic recognition and analysis of printed characters by vision-based algorithms is still much more advanced and widely used than the handwritten one, mainly due to the difficulties in dealing with the variability in handwritten characters’ shapes and styles (see figure). It is thus a challenging effort to place handwritten OCR in a single context. Oftentimes tailor-made algorithms and adjustments are needed to utilize automatic text recognition of different languages; account for people’s different handwriting styles and text slant; as well as deal with technical imaging issues, e.g camera position, camera angle, uneven illumination etc.

Deep learning for OCR

The fast development of Deep Neural Networks (DNN) as a learning mechanism to perform recognition has gained popularity in the past decade.  This popularity is owed primarily to the high accuracy DNN has achieved in both spotting text region and deciphering the characters simultaneously. Deep Neural Networks, or Convolution Neural Networks (CNN) are essentially multi-layered learning and feature processing neural networks. Each neuron (node) in each layer is fed with information passed from nodes connected to it. A processing mechanism (transfer function) then determines how much of the processed information will be passed to the nodes connected to the present one. The architecture of the network, that is, the way neurons and layers are connected, plays a primary role in determining the network’s ability to produce meaningful results.

ocrpicss

The advantage of DNNs is that architecture can be made heterogeneous.  Similar to the human visual system, different neurons and processing layers are more sensitive to different features of objects. Edges of objects are seen more sharply by one set of neurons, while others are more sensitive to color gradients. This heterogeneity is exploited by researchers to construct sophisticated architectures, in which neurons and layers are connected in a way that data propagates back and forth between them before producing a result.
The potential of DNNs in OCR has been widely demonstrated by many teams of researchers. Among others, an architecture for both text detection and character recognition was given by Jaderberg, Vadaldet and Zisserman. An implementation of DNN on GPUs has shown to speed up processing time and accuracy in an architecture devised by Ciresan et al. who trained and tested it against a deformed character dataset.   Detection and OCR in natural scene images was performed by Jaderberg et al. which also may be applied to images and real-time video obtained by cellphones. For Latin and Chinese OCR see Cirasan, and for Telugu scripts, Achanta and Hastie.  These examples are by no means exhaustive, interested readers are encouraged to refer to references within the articles mentioned.

Consult with RSIP Vision now

References:
Jaderberg, Max, Andrea Vedaldi, and Andrew Zisserman. “Deep features for text spotting.” Computer Vision–ECCV 2014. Springer International Publishing, 2014. 512-528.
Cireşan, Dan C., et al. “Handwritten digit recognition with a committee of deep neural nets on gpus.” arXiv preprint arXiv:1103.4487 (2011).
Jaderberg, Max, et al. “Synthetic data and artificial neural networks for natural scene text recognition.” arXiv preprint arXiv:1406.2227 (2014).
Cireşan, Dan C., Ueli Meier, and Jürgen Schmidhuber. “Transfer learning for Latin and Chinese characters with deep neural networks.” Neural Networks (IJCNN), The 2012 International Joint Conference on. IEEE, 2012.
Achanta, Rakesh, and Trevor Hastie. “Telugu OCR Framework using Deep Learning.” arXiv preprint arXiv:1509.05962 (2015).

Share

Share on linkedin
Share on twitter
Share on facebook

Related Content

Prostate Guidance

Intra-op Prostate Guidance by RSIP Vision

Automated IBD Scoring

IBD Scoring – Clario, GI Reviewers and RSIP Vision Team Up

Soft Tissues Tracking during Brain Surgery

Soft Tissue Tracking during Brain Surgeries

Next Generation Intra-op Navigation

Neph - Partial Nephrectomy surgery

RSIP Neph Announces a Revolutionary Intra-op Solution for Partial Nephrectomy Surgeries

Benign Prostatic Hyperplasia BPH

AI for Benign Prostatic Hyperplasia BPH

Prostate Guidance

Intra-op Prostate Guidance by RSIP Vision

Automated IBD Scoring

IBD Scoring – Clario, GI Reviewers and RSIP Vision Team Up

Soft Tissues Tracking during Brain Surgery

Soft Tissue Tracking during Brain Surgeries

Next Generation Intra-op Navigation

Neph - Partial Nephrectomy surgery

RSIP Neph Announces a Revolutionary Intra-op Solution for Partial Nephrectomy Surgeries

Benign Prostatic Hyperplasia BPH

AI for Benign Prostatic Hyperplasia BPH

Show all

RSIP Vision

Field-tested software solutions and custom R&D, to power your next medical products with innovative AI and image analysis capabilities.

Read more about us

Get in touch

Please fill the following form and our experts will be happy to reply to you soon

Recent News

IBD Scoring – Clario, GI Reviewers and RSIP Vision Team Up

RSIP Neph Announces a Revolutionary Intra-op Solution for Partial Nephrectomy Surgeries

Announcement – RSIP Vision Presents Successful Preliminary Results from Clinical Study of 2D-to-3D Knee Bones Reconstruction

Announcement – New Urological AI Tool for 3D Reconstruction of the Ureter

All news
Upcoming Events
Stay informed for our next events
Subscribe to Our Magazines

Subscribe now and receive the Computer Vision News Magazine every month to your mailbox

 
Subscribe for free
Follow us
Linkedin Twitter Facebook Youtube

contact@rsipvision.com

Terms of Use

Privacy Policy

© All rights reserved to RSIP Vision 2023

Created by Shmulik

  • Our Work
    • title-1
      • Ophthalmology
      • Uncategorized
      • Ophthalmology
      • Pulmonology
      • Cardiology
      • Orthopedics
    • Title-2
      • Orthopedics
  • Success Stories
  • Insights
  • The company