News In brief

North American sales of machine vision systems and components have increased 10 per cent year- on-year to $597 million in the first quarter of 2017, according to AIA statistics.

Teledyne Technologies has completed its £627 million cash acquisition of British firm e2v. The purchase was first announced in December 2016.

Basler has posted 2016 sales of €97.5 million, up 14 per cent from 2015.

Flir Systems has appointed James Cannon as its new president and CEO following Andy Teich’s retirement after 33 years.

On Semiconductor has established a sensor fusion design centre in Bracknell, England, focusing on image sensors for automotive ADAS.

IDS celebrates its 20th anniversary this year.


News from UKIVA By Paul Wilson, UKIVA chairman

The first UKIVA Machine Vision Conference and Exhibition took place on 27 April at MK Arena in Milton Keynes, and we were rewarded with a dynamic event which has attracted extremely positive comments from attendees, the press, UKIVA members and exhibitors alike. The meeting was opened by Iain Stewart, MP for Milton Keynes South, and two of the highlights were the keynote addresses given by Dr Mike Aldred, from Dyson, and Dr Graham Deacon, from Ocado Technology. These attracted huge audiences, with standing room only. The conference programme was also extremely well attended; the presentations on 3D vision proved to be particularly popular. Total audience

levels for the conference exceeded 1,000.

Alongside the conference was an exhibition by 57 of the world’s leading manufacturers and suppliers of machine vision systems and com- ponents. Valerio Del Vecchio, PPMA Group marketing manager, comment- ed: ‘I’d like to congratulate the team who put so much effort into making this occasion such a success and we plan to make the event a regular occurrence. Our aim was to create an informative and educational environ- ment. UKIVA members I have spoken to who made presentations said they were delighted with the numbers of people who came to listen to them. Many of these subsequently visited

6 Imaging and Machine Vision Europe • June/July 2017

them at their exhibition stands for further discussions.’ This was echoed by many of the vis-

itors. Giles Humphrey, senior industrial engineer at Lear Corporation, said: ‘I found the event extremely useful. I had the opportunity to meet potential new suppliers at the exhibition and picked up some useful hints and tips from the seminars that I attended.’ The PPMA Group Awards 2017 are now open for submissions and as usual, one of the categories is for the ‘most innovative vision solution’. This is not restricted to UKIVA members; it is open to vision equipment suppli- ers, system integrators or end users who have manufactured, designed or installed an innovative industrial

vision solution that led to a significant improvement of processing and pack- aging equipment. The submission deadline is 30 June 2017. Each entry must include a short

company profile, a summary of why the company merits an award, and a clear description of the problem, the solution and the outcome. More details can be found at The winner of the award will be an- nounced at the PPMA Group awards event, which will take place on 26 September 2017, the first night of the PPMA show, at the National Mo- torcycle Museum in Birmingham. The PPMA show itself is the next major event on the horizon for UKIVA.


Deep learning assists technicians analyse medical images

trial using deep learning algorithms has shown that artificial intelligence has the potential to assist technicians and detect

human errors in medical image handling. System-on-chip manufacturer Socionext and

Japanese AI soſtware company Soinn presented results from the project at Medtec Japan, held in Tokyo from 19 to 21 April. In the trial, Socionext extracted and delivered

biometric data to Soinn’s Artificial Brain. Soinn learned to read subcutaneous fat thickness from abdominal ultrasound images. Te estimations by Soinn were then compared with the reading results by ultrasound technicians.

Soinn’s Artificial Brain can read fat tissue

thickness from 80 per cent of the data within a 5 per cent margin of error. Tere were noticeable differences between the readings by human and by Soinn for some of the images. Aſter reviewing these data, it was confirmed

that human error, including numerical input, was a common occurrence from data read by a human. Based on the findings, the companies believe that AI has the potential to be used for assisting technicians in reading images and detecting human errors in medical image handling. Soinn’s system needed around 700 images to train.

sfam_photo /

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  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56