Aurora Deep Learning

Aurora Deep Learning

Intuitive Software for Individual Image Analysis

Zebra Aurora Deep Learning

This add-on product within Zebra comprehensive AuroraTM for OEM software portfolio offers a complete set of industrial-quality deep learning tools which can be used to solve problems that are far too complex for traditional machine vision algorithms and further enhance the outputs of AuroraTM Vision Studio and AuroraTM Vision Library software.

Features & anomaly detection, advanced optical character recognition (OCR) technology, and deep learning capabilities combine to recognize the way real-world images are used – and evolve accordingly.

Internally, AuroraTM Deep Learning uses large neural networks designed and optimized by Zebra research team for use in industrial inspection systems.

Together with AuroraTM Vision Studio, AuroraTM Deep Learning constitutes a complete solution for training and deploying modern machine vision systems.

All-In-One Software Package

The AuroraTM Vision for OEM portfolio offers the most comprehensive approach to the development of custom machine vision applications:

2D & 3D Algorithms
C++ and .NET Libraries
Rapid Development Environment
HMI Designer
Technical Support and Know-How
Deep Learning

AuroraTM Deep Learning vs Traditional Machine Vision

AuroraTM Deep Learning is a new reliable solution for machine vision problems that could not have been solved before. There are, however, applications that can still only be realized with traditional methods. How do you know which approach is better? Here is a quick guide:

Deep Learning

Typical applications:

  • Surface inspection (cracks, scratches)
  • Food, plant, wood inspection
  • Plastics injection molding
  • Textile inspection
  • Medical imaging

Typical characteristics:

  • Deformable objects
  • Variable orientation
  • Customer provides vague specifications with examples of good and bad parts
  • Reliability:99%
Hardware Requirements

AuroraTM Deep Learning can work on a standard industrial PC. But for better performance, we recommend using modern GPU boards from the NVIDIA® GeForce® and Tesla series with compute capability 3.5 or higher.

Traditional Machine Vision

Typical applications:

  • Dimensional measurements
  • Code reading
  • Presence or absence checking
  • Location of fiducials on PCB
  • Print inspection

Typical characteristics:

  • Rigid objects
  • Fixed orientation
  • Customer provides formal specifications with tolerances
  • Reliability:100%
Training Interface for End Users
  • AuroraTM Deep Learning allows end users who are non- vision experts to retrain a Deep Learning model on a factory floor.
  • Users of AuroraTM Vision Library can create their own training interface for end users using the C++ API.

For more information please do not hesitate to drop us an email at, send us message via WhatsApp or simply call us at +65 6694 6278 for more assistance.