VDI/VDE/VDMA 2632 Blatt 3:2016-09 - Draft

Quantitative capability analysis is commonly used for measuring (non-classifying) machine vision (industrial image processing) systems. The uncertainty of measurement is usually used as a characteristic. There are well established specifications of how to calculate the uncertainty of measurement and how to derive the qualification for a certain task from this. In contrast, the results of classifying machine vision systems are variable attributes. So far, there are no corresponding qualification indicators for these machine vision systems which are commonly applicable and accepted. This standard introduces indicators describing the classification capability of a machine vision system. Due to the diversity of classifying machine vision systems it is fairly impossible to introduce a common scheme for benchmarking the performance. Thus, the standard proposes procedures for benchmarking the classification performance during the acceptance test of machine vision systems. Typical examples of testing techniques for industrial imaging systems are given that may serve as guidance for similar cases. The standard addresses users as well as suppliers of machine vision systems.

35.240.50

This document has been replaced by: VDI/VDE/VDMA 2632 Blatt 3:2017-10 .