What does artificial intelligence mean?

The term artificial intelligence (AI) or AI (artificial intelligence) is not clearly defined. A definition fails simply because the concept of intelligence is not clear. The term artificial intelligence (AI) was created in the 1950s and is therefore historically shaped and subject to many influences. The term reflects the vision and the "big picture". AI touches on several technical and scientific disciplines and is often used (including by us) as a catchy marketing term. When people talk about AI in measurement technology or image processing, they usually mean machine learning (ML, machine learning) or "deep learning" (DL, deep learning). The terms build on each other as follows. Artificial Intelligence (AI)  → Machine Learning (ML)  Deep Learning (DL)

Artificial intelligence to optimize your testing processes

Historical course

Although artificial intelligence is often referred to as a trend, it is by no means a new phenomenon. As early as the 1950s, scientists shared the belief that the process of thinking is not limited to the human brain. After research on the topic stalled, especially in the 80s, technology companies like Google gave the field a new boom in the 2000s. Today artificial intelligence is an integral part of our everyday life.

What does machine learning (ML) mean?

In image processing, there are basically two different ways to deal with a problem:

Rules based programming

  • Manual formulation and programming of rules after the results are calculated or defined

Machine learning

  • Train a model on data
  • Independent learning of patterns from the data
  • Classifying or estimating result quantities
Artificial intelligence to optimize your testing processes

Which approach is better depends on the application and must be carefully assessed or systematically determined. Rule-based approaches, especially in measurement technology and image processing, are well suited to making decisions based on clear measurement features and rules. If the rules are not known or can only be systematically extracted from images with great effort, a machine learning process may be the better approach. Machine learning processes are typically used in image processing for difficult segmentation tasks, in character recognition (OCR / OCV), pattern and anomaly recognition, object and image recognition and image classification. In modern applications, both approaches are usually combined in a meaningful way.

Machine learning (ML) learning techniques

Roughly speaking, there are 3 different learning methods for machine learning.

Artificial intelligence to optimize your testing processes

Deep learning vs. machine learning

Modern AI applications are based almost exclusively on deep artificial neural networks (ANN). The special thing about the networks is that they can also perform complex tasks and manual feature extraction can be completely dispensed with. An ANN is therefore able to independently perform complex tasks.

  • Deep learning is a branch of machine learning
  • DL methods are based on artificial neural networks with several intermediate layers
Artificial intelligence to optimize your testing processes

Artificial Neural Networks (ANN)

Deep learning methods are based on artificial neural networks.
These networks are inspired by the (biological) neural networks, i.e. part of a nervous system. Artificial neural networks are built in layers. A layer or level consists of several artificial neurons. There are several hidden levels between an entrance and exit level. The structure is given the name "deep" neural network because of these hidden levels.

Artificial intelligence to optimize your testing processes
Artificial intelligence to optimize your testing processes

Convolutional Neural Network (CNN)

So-called "convolutional neural networks" (CNN) are mostly used in image processing. These networks, inspired by the visual cortex, are made up of several feature maps. These feature maps correspond to the levels of an artificial neural network and are generated by convolution. The convolution operators produce different characteristics / features, such as edges. In image processing, a CNN should be able to generalize features and represent them in ever higher abstraction lines.

Artificial intelligence to optimize your testing processes

Source: LeCun, Yann, et al. “Gradient-based learning applied to document recognition.” Proceedings of the IEEE 86.11 (1998): 2278-2324

Artificial intelligence to optimize your testing processes

Source: Lee, Honglak, et al. “Unsupervised learning of hierarchical representations with convolutional deep belief networks.” Communications of the ACM 54.10 (2011): 95-103.

Artificial intelligence to optimize your testing processes

MV.MINDNET, the deep learning platform from MABRI.VISION, combines the latest technology and practice-oriented solutions.