Image analysis of cells is commonly used to judge cell state and cell phenotype. In a previous paper, we reported the manual foci-cell identification process’s automation by applying image processing and machine learning methods to fluorescent foci-cell images. Here, we present the details of our approach to improving the proposed automated system. Specifically, we use the Gaussian mixture model (GMM) for image segmentation, depict dead cells as outliers, and add new features not included in scikit-learning regionprops. Thus, we defined new features related to foci cells’ properties, which were not included in the scikit-learn regionprops. Through the new approaches, we improved the accuracy of the regression models to an adequate level. In addition, an analysis of fitted model information showed that the new features were useful for foci-cell identification.

Position and orientation errors of rotary axis average lines are often dominant error sources in the five-axis machining. Many schemes have been studied, and some are now commercially available, such that they can be identified on-machine, and then numerically compensated, by a machine tool user. Many conventional schemes install a measuring instrument or a measured target in a machine spindle, and thus cannot be performed when the spindle is rotating. Rotary axis location errors are often influenced by the machine’s thermal deformation. When the spindle is not rotating, they can be different from actual machining operations. This paper presents the application of a non-contact laser barrier tool measurement system to the identification of rotary axis location errors, when the spindle rotates in the same speed as in actual machining applications. An experimental thermal test is presented to observe the change in rotary axis location errors under continuous machine warm-up by spindle rotation and reciprocal linear axis motions. Experimental comparison with the R-Test, a typical conventional scheme that can be performed only when the spindle does not rotate, shows that rotary axis location errors change quickly after the machine warm-up is terminated.