Deep Learning and Edge - Multipix Imaging
Save time, speak to our experts on 01730 233332 Expert Advice
For the fastest lead times on cameras, call 01730 233332 Get Fast Delivery
Filter by type
Knowledge Base
Support Blog
Stock Status
In stock
Out of stock

Deep Learning and Edge

What is Deep Learning?

Neural Networks are computing systems inspired by the biological neural networks that constitute the human brain. Convolutional Neural Networks (CNN) are a class of deep, feed-forward artificial neural networks, most commonly applied to analysing images. Deep Learning uses large CNNs to solve complex problems difficult or impossible to solve with conventional computer vision algorithms. Deep Learning algorithms may be easier to use for some inspection/classification applications as they typically learn by example. They do not require the user to figure out how to classify or inspect parts.

Instead, in an initial training phase, they learn just by being shown many images of the parts to be inspected. After successful training, they can be used to classify parts, or detect and segment defects. This is powerful technology, offering solutions to applications previously impossible with traditional algorithmic approach. However, understanding when to use Deep Learning (and when not to) it is very important if you are to achieve a desirable result. Multipix Imaging’s Technology Specialists are here to offer you expert and informative advice on Deep Learning.

Unsupervised Anomaly Detection

Only need to train images of good objects/scenes

Fast Implementation

Supervised Anomaly Detection

Training of good and defect objects/scenes are required.

Most Robust Results

Ideal Applications for Deep Learning

  • Detecting faulty products
  • Sorting products by class
  • Surface/Textile Inspection

What is Edge and When should it be Used?

Increasingly, it is at the Edge where the processing is taking place. This makes perfect sense, as it is efficiently managing data to send it to the correct place, make the correct decision, at the appropriate time. The processing takes place near the source of data, for example a smart camera, and is increasingly based on chipsets designed for AI/Deep Learning.

Graphics Processor Unit (GPU) is specifically designed to process data rapidly. They perform parallel operations on multiple sets/sources of data and are used increasingly in AI/Deep Learning when repetitive processing is required which is specifically during the training phase.

The Industrial IoT, or Industry 4.0 is utilising edge computing to great effect. This includes machine vision devices for inspection and control of production processes. Deep Learning and vision is also being increasingly used in consumer focused products and is no longer confined to the production-line.

Featured Products for Deep Learning

Deep Learning works by training a neural network, teaching it how to classify a set of reference images. The run-time performance of the process highly depends on how representative and extensive the set of reference images is.  Using a single GPU typically accelerates the learning and the processing phases by a factor of 100