TECH FOCUS: DEEP LEARNING


Deep learning neural network undertaking a partial conventional algorithm’s work in only a small part of a 3D image processing pipeline. Poor image quality in the left image is improved with a conventional de-noise algorithm (middle image), but its computational performance is slow and not constant. The neural network (right image) learns to de-noise from the conventional algorithm, and is constant and fast. It can be accelerated thanks to the parallelisation capabilities of neural networks.


certain aspects of a task that are covered by the training data, but is blind to aspects that were inadvertently overlooked. Tanks to the amount and complexity of large data, one should always be aware of the potential for data bias. Terefore, training data should be diligently maintained, extended, as well as repeatedly re-training and evaluating the CNNs. While neural networks


the discriminator can’t distinguish between the counterfeit images and the real images. Te emergence of GANs raised hopes


require exhaustive data for training, lack of data is an inherent problem for real-world problems. In 2014, a new method for artificial data generation with CNNs was published: generative adversarial networks (GANs). Two CNNs are trained to work against each other, a counterfeiter network and a discriminator network. Te counterfeiter network is trained to become better at generating random images, plausibly mimicking the available real training data but providing some new structures. Te discriminator is trained for revealing whether images are artificially generated or real data. As the discriminator improves on revealing counterfeits, the generator network improves on generating plausible looking images until


www.imveurope.com @imveurope We ask users to


integrate deep learning cautiously into diligent data acquisition and image-processing pipelines


that scarce data samples could simply be augmented with enough variation to make up for the lack of real data, for example when training CNNs for inspection tasks. Indeed, in some settings, such as entertainment or fashion applications, remarkable results can be achieved where augmented images are indistinguishable from real images – even humans can’t tell the difference. Tis work uses relatively large real training databases containing enough


structural variation for the GAN to learn. In fact, a GAN cannot generate substantially new artificial data without a clue from real data. For industrial inspection where precision and reliability count, the artificially generated data should be really in line with real image distributions, not only those that look plausible. Nevertheless, even measuring and proving generated data matches real data cannot reliably be accomplished. For some applications, one way to use a GAN is to make it simpler for the GAN by


combining it with conventional artificial data generation methods such as rendering. Tis generates a large amount of geometrical variation but usually fails to imitate the characteristics of the real image acquisition systems correctly. GANs can be used for doing the so-called style transfer, learning and applying the statistical camera properties to the rendered images without disturbing their geometrical content. Image statistics are another potential pitfall


when working with neural networks. It has been shown in various publications that adversarial noise patterns exist that deteriorate the predictions of CNNs. An image showing a truck is correctly classified as a truck by a CNN, but by adding an adversarial noise pattern to that image the CNN fails, although the image content has not changed visibly from a human perspective. Tat disturbing vulnerability to adversarial noise has been shown to be inherent to neural networks. Terefore, one must take care of properly setting up the acquisition system and image pre-processing pipelines, to thoroughly ensure that only properly processed data are used. As deep learning is a fully data-driven


method, one is totally dependent on the data quality. In an industrial environment, one might not be willing to entirely rely on the


August/September 2019 • Imaging and Machine Vision Europe 29


Austrian Institute of Technology


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