News W


For the latest vision industry news, visit www.imveurope.com/news


Quantum cameras show reach of UK programme


ork from the first three years of the £270 million UK National Quantum Technology programme, including that


from the quantum imaging hub, was showcased at an event in London on 22 November. Twenty-five universities and 50 companies


are involved in the programme, with the total investment exceeding £350 million. Te event was held as the European Commission


begins its €1 billion quantum flagship programme, set to run from 2018 to 2028. Te US, China, Singapore and Australia also have their own programmes, as have companies including Google, which is investing heavily in quantum computing. Companies and researchers that are part of the


quantum imaging hub, Quantic, were displaying a range of technologies, all based on photon counting timing. M Squared Lasers was showing its single pixel infrared camera for imaging gases, which the company said was the technology closest to commercialisation of all its projects. Other technology on display included: a camera


developed by Lockheed Martin, among other partners, that can see through scattering media, such as snow and fog; a photon counting silicon chip designed by the University of Edinburgh, fabricated by STMicroelectronics, and incorporated


News from UKIVA By Paul Wilson, UKIVA chairman


Embedded vision, Industry 4.0 and deep learning are some of the current high-profile topics in the world of machine vision. Deep learning is a particular branch of artificial intelligence, which aims to mimic the activity normally associated with layers of neurons in the brain to recognise patterns in digital images. Deep learning is beginning to gain some real traction recently, by virtue of the fact that it is becoming much more widely available through commercial machine vision products.


Although the deep learning approach is still comparatively in its infancy, a variety of neural technology and artificial intelligence approaches have been used in pattern recognition


applications in machine vision for some time, where the systems can be trained to accommodate variations in the objects to be inspected and classified. An excellent recent example of the use of artificial intelligence machine vision algorithms was in the fully automated robot vision inspection system designed by UKIVA member, Industrial Vision Systems, for inspecting multiple parts on an automotive dual pump assembly line. This was the system that won the Most Innovative Vision Project award at the 2017 PPMA Group awards. Deep learning, however, uses a special kind of neural network called a convolutional network (CNN), which is taught how to categorise images by


4 Imaging and Machine Vision Europe • December 2017/January 2018


being shown a large set of example images. The term ‘deep’ refers to the number of layers in the network – the more layers, the deeper the network. CNNs are massively parallel algorithms made up of layers of simple computation nodes, whose behaviour is governed by the way that the nodes are interconnected, the computations that each node performs, and coefficients determined via a training procedure. Deep learning is used in applications where it is difficult to predict the full range of image variations that might be encountered. One UKIVA member has been able to supply a deep learning code reading tool in which the fonts have been pre-trained, which eliminates the


need for the user to carry out their own training. The deep learning approach makes it possible to achieve higher reading rates than with all previous classification methods. The tool can also be used in conjunction with a 3D camera that can verify the size of the text, so the distance from camera to object can be varied.


The seminar programme at


UKIVA’s next Machine Vision Conference and Exhibition (www. machinevisionconference.co.uk) will again have a presentation theatre dedicated to vision innovations. It’s the perfect opportunity to find out about the hottest topics in machine vision at that time. It takes place on 16 May 2018 at Arena MK, Milton Keynes, UK.


@imveurope www.imveurope.com


in a new range of spectrometers by Horiba for time resolved luminescence studies; a portable light source of quantum coupled and correlated photons from the University of Bristol, which is being used for covert imaging studies; and a camera from Tales that can see around corners, with applications in defence and security. Speaking at the event, William Alexander,


technical director at Tales, said that Quantic was fantastic for breaking down the barrier between


academia and industry, and that without Quantic Tales wouldn’t have known about the work being done at Heriot-Watt University developing single- photon avalanche diode (SPAD) detectors that Tales uses in its camera. Te day in London also featured discussions


about building a supply chain of photonics components, as well as training engineers to test and make components, both of which need investment to turn quantum technology into an industry.


Dan Tsantilis and EPSRC


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44