SICK AppSpace SensorApps
Intelligent Inspection

Your Benefits

  • Simplified solution development in complex machine vision applications not possible with traditional rule-based machine vision
  • Example-based approach and easy-to-use user interface that makes it quick to learn without the need for a vision expert
  • Low cost of total ownership as deep learning network runs directly on the camera without additional hardware
  • Reliable inspection to reduce waste, avoid production downtime, and improve productivity
  • The SICK Nova Tools plug-in support with source code access offers customization capabilities to all SICK AppSpace developers

Overview

The Intelligent Inspection SensorApp from SICK ensures easy object classification that is not possible with traditional rule-based machine vision. The SensorApp is powered by deep learning technology and available as a licensed option when ordering InspectorP6xx 2D vision sensors from SICK. The example-based approach and easy-to-use user interface makes it quick to learn and paves the way for simplified solution development. The user can easily collect training data to be used in the neural network training, and deploy the trained network directly on the sensor without the need for any extra equipment. In addition, traditional rule-based machine vision software tools are included.

At a glance
  • Classification of objects powered by deep learning technology
  • Runs on InspectorP6xx 2D vision sensors
  • Easy-to-use user interface in web browser
  • Traditional rule-based machine vision software tools included
  • Quick customization with SICK Nova Tools

 

Artificial Intelligence Teaser Box Image
Artificial Intelligence Teaser Box Image

Industrial Artificial Intelligence

Unlocking the full potential of Intelligent Sensors with deep learning solutions

Learn more

Advantages

Artificial intelligence for machine vision

Deep learning is a subset of artificial intelligence (AI) that enables computers to mimic human decision-making and problem-solving. Deep-learning-based machine vision is well suited for objects with unpredictable characteristics, such as naturally grown objects, deformed and defect objects, as well as objects with complex or irregular shapes. The deep learning, example-based approach is intuitive and enables simplified solution development.

Solving a Deep Learning application with Intelligent Inspection from SICK

Collection of training data Collect training images using the InspectorP6xx 2D vision sensor with the Intelligent Inspection SensorApp.
Training and assessment Train and evaluate neural networks with the web-based training service dStudio from SICK.
Run network on sensor Upload the trained neural network to the sensor using the Intelligent Inspection SensorApp. New images are easily classified directly on the device.

Deep Learning and the example-based approach simplify application development.

Application examples for Deep Learning

Task: Classification of annual rings in wood Deep learning technology is well-suited for classifying the annual ring structure in the wood industry. Naturally and uniquely grown objects are difficult to classify with traditional rule-based machine vision.
Solution: Intelligent Inspection SensorApp Using the Intelligent Inspection SensorApp on the InspectorP6xx 2D vision sensors from SICK makes it possible to classify objects in an intuitive and human-like way.

Supported Products

Product families
Products

Applications

Technical overview

 
  • Technical data overview

    Technical data overview

    Task

    Classification

    Quality inspection

    Presence inspection

    Measuring, 2D

    Technology

    2D snapshot

    Image analysis

    Deep Learning

    Language

    English

    German

    Supported products

    InspectorP61x

    InspectorP62x

    InspectorP63x

    InspectorP64x

    InspectorP65x

    Minimum screen resolution1,366 px x 768 px
    Supported browsersGoogle Chrome (version 49 or higher)
All technical data can be found accompanying the individual product

Downloads