ARTIFICIAL INTELLIGENCE
Added value: identify where AI makes a real difference
Experts from AIT, MVTec, Irida Labs and Xilinx discussed AI and machine vision during one of our latest webinars. Greg Blackman reports
S
urface inspection and optimising processes beyond the production line, such as helping staff with tasks, were
two areas the panel saw potential for the use of neural networks in manufacturing. But deep learning algorithms for machine vision should not be considered the Holy Grail, the panel warned. At the Austrian Institute of Technology
(AIT), researchers are working on combining classical machine vision approaches and neural networks to overcome some of the problems encountered with deep learning. Petra
Tanner, senior research engineer at AIT, described work into reducing the dependency on the image source – the difference in noise levels from different cameras, for instance – by pre-processing images before applying them to a neural network. She said her team had managed to train a network with pre-processed images – even with images of different optical resolutions – and applied it to an industrial problem with good results. Te group at AIT is also investigating
methods such as one-class learning, a technique to spot anomalies in data consisting of images of only good parts – large datasets of defects are hard to come by in industrial inspection. It is also working on improving the quality of image data using generative adversarial networks (GANs) for data augmentation, a technique that can also help with small datasets. One specific application example Tanner
mentioned was using deep learning to detect cracks and machining marks on metallic surfaces. Olaf Munkelt, managing
20 IMAGING AND MACHINE VISION EUROPE FEBRUARY/MARCH 2021
director of MVTec Software, also noted that deep learning can add a lot to the area of surface inspection, which has traditionally been difficult to solve using rule-based approaches. He also pointed to optical character
recognition (OCR) as an area where deep learning can improve existing technology – MVTec’s Halcon software now has in-built deep learning in its OCR tool. Te firm has millions of samples of industrial printed characters on which to train its neural network. ‘Tere you can really add three percentage points [to improve the recognition rate], which makes the customer happy,’ Munkelt said. Tis illustrates the point that Munkelt and the other panellists made, which is that deep learning has to add value first and foremost. Quenton Hall, AI system architect at chip maker Xilinx, said he’s seen a shift over the last three years in the understanding of what deep learning can accomplish. But that neural networks are best applied to areas where they can increase performance
@imveurope |
www.imveurope.com
Pand P Studio/Shutterstock
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
