The main goal of DynaVis is the development of machine learning methods for embedded machine vision systems in production and manufacturing to achieve dynamically reconfigurable systems.

Inspection of products by machine vision often has to solve the problem of how to implement a human decision-making process in software. Currently, this requires a step-by-step reprogramming or parameterisation of the software, which may last for several months until satisfying results are obtained. The results of DynaVis will enable us to use Human-machine cooperation to learn complicated inspection tasks instead of set-by-step improvements and adaptations of software.

The project is foused on the development of "trainable" machine vision algorithms and of appropriate machine learning techniques. In order to create such methods we will focus on the following scientific objectives:
(1) machine learning methods for processing the complicated data produced by the vision system.
(2) methods to deal with multiple, possibly contradictory input by the operators.
(3) methods for predicting success or failure of the learning process in early stages of the training process.

The project contributes to the objectives of the call by developing a new way how reconfigurability in automated systems can be achieved. In the case of DynaVis these are embedded machine vision systems such as smart cameras. The project involves advanced control such as fuzzy methods and neural networks. The goal is to use human-machine cooperation and machine learning to dynamically adapt the vision system to the operator's decisions.

The project involves key players in the field of machine learning with a particular focus on machine vision. Companies from the machine vision industry and end-users from various fields complement the consortium. Special attention is given to the dissemination of results to SMEs.