DEEP LEARNING
• Unpredictable false positives: A standard deep learning model often does not know what it does not know. Tat is, a model is often overconfident when inferring on something it has never seen before. As a result, there are chances a change of process or background might impact the system – a new pen mark on each part may appear as a defect, or a screw becoming visible may look like a crack.
• New parts and assembly lines: A manufacturer generally produces different products on several production lines. When doing a first project, the user might want to identify one line and a few products to run the experiment on. One would then expect the model to adapt quickly to new parts with similar defects, but with different geometries or textures. One would also expect the model to be easily deployable on new production lines, where conditions may vary because of real life constraints, such as camera position, lights, conveyor belt, or different integration on the production line.
• New kinds of defect: Because processes change, new kinds of defect can appear. Te user might also want to change the specification and declare defective some characteristics previously considered
benign. A proper deep learning solution should be able to adapt quickly to this specification evolution.
At Scortex we have been studying a few solutions to the open world challenge. Tese are, firstly, data augmentation. Te user can make a model more robust by randomising the images it sees outside of its comfort zone. For example, to make the model robust to a change of camera position, the user can apply random flips, translations, rotations or projections on images during training. Similar transformations can be applied to be robust against external lights (random additions or multiplications) or camera parameters (random contrast or gain). Secondly, add more data and employ active
learning, which is the best solution in terms of model performance, but not always in terms of cost. It necessitates the ability to acquire more data and to annotate it, which can take time and energy. A way to keep the cost down is to label only the data that will lead to the best performance. Tis is known as active learning in the literature. Tirdly, use domain adaptation. Tis
relatively new set of techniques allows a model to generalise better to new environments – acquisition systems, for example. It has been widely studied in
the deep learning driverless car literature where researchers use it to generalise from simulated environments, such as a Grand Teft Auto game engine, to real life. Finally, Scortex has been studying
incremental learning. Tis new field is linked to the update of a model to support a new class under a set of constraints. Te constraints typically are ‘limited’ or ‘no access’ to data previously used for training. Tis can be the case when the user wants to retrain locally or at the edge. By extension, this technique can be used to give faster training of a new class while maintaining the old class’s performance and calibration. None of these techniques alone solve the
problem of open world, but combined they create a robust model at the beginning of a project and allow it to be maintained over time. O
Based in Paris, Scortex was founded in 2016 to automate quality control in manufacturing using artificial intelligence.
Want to write about an industrial imaging project where you have successfully deployed deep learning? Email:
greg.blackman@
europascience.com
BOOTH #238
navitar.com | 800.828.6778
INDUSTRIAL • MACHINE VISION • BIOMEDICAL • LIFE SCIENCES LENSES | CAMERAS | SYSTEMS
specialoptics.com |
pixelink.com
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
