The article describes the methodology for testing various cameras for their use in systems using neuro intelligence. This task is vital since the effect of the artificial intellect in recognizing incoming images is highly dependent on the quality of the input image. For these purposes, a detailed review of all relevant parameterization of measures in their assessment is given. The article can be useful for creating new systems oriented to the analysis of video images with a selection of cameras. The given method has been tested on real cameras and described in the article.