30 research outputs found
Linear system models for lag in flat dynamic x-ray detectors
No full textThe detective quantum efficiency (DQE) is regarded as a suitable parameter to assess the global imaging performance of an x-ray detector. However, residual signals increase the signal-to-noise ratio and therefore artificially increase the measured DQE compared to a lag-free system. In this paper, the impact of lag on the DQE is described for two different sources of lag using linear system models. In addition to the commonly used temporal filtering model for trapping, an increase of the dark current is considered as another potential source of lag. It is shown that the assumed lag model has a crucial impact on the choice of an adequate lag estimation method. Examples are given using the direct conversion material PbO. It turns out that the most general approach is the evaluation of the temporal noise power spectrum. A new algorithm is proposed for the crucial issue of robustly estimating the power spectrum at frequency zero
Implementing machine learning: chances and challenges
No full text90101Finding and implementing a suitable machine learning (ML) solution to a task at hand has several facets. The technical side of ML has widely been discussed in detail, see, e. g., (Heizmann, M., A. Braun, M. Hüttel, C. Klüver, E. Marquardt, M. Overdick and M. Ulrich. 2020. Artificial Intelligence with Neural Networks in Optical Measurement and Inspection Systems. at - Automatisierungstechnik 68(6): 477-487). This contribution focusses on the industrial implementation issues of ML projects, particularly for machine vision (MV) tasks. Especially in small and medium-sized enterprises (SMEs), resources cannot be activated at will in order to use a new technology like ML. We take this into account by, on the one hand, helping to realistically evaluate the opportunities and challenges involved in implementing ML projects for a given task. On the other hand, we consider not only technical aspects, but also organizational, social and customer-related ones. It is discussed which know-how a company itself has to bring into an ML project and which tasks can also be performed by service providers. Here, it becomes clear that ML techniques can be used at different levels of detail. The question of "make or buy"is therefore also an entrepreneurial one when introducing ML into one's own products and processes, and must be answered with a view to one's own possibilities and structures.70
